SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks | Paper Citation Record

Observation e5b0fa62-cc15-4b0d-8bdb-819fafbdea60 · outbound

This paper cites FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:41.102675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e07fb11-6f18-4911-a4a6-c6b6b5f1b191 · outbound

This paper cites Ultimate vocal remover.GitHub repository, 2020.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Ultimate vocal remover.GitHub repository, 2020

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:41.196456Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e059a6e2-3ede-44b1-84b5-45540c4c9427 · outbound

This paper cites Qwen Technical Report.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Qwen Technical Report

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:41.280587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50f70143-b4a3-409d-83a3-d9f70d7afe28 · outbound

This paper cites WhisperX: Time-Accurate Speech Transcription of Long-Form Audio.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks WhisperX: Time-Accurate Speech Transcription of Long-Form Audio

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:41.363603Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98db6794-4613-41d4-b1f3-a4e8e93a67df · outbound

This paper cites Curriculum learning.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Curriculum learning

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:41.453324Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0b577c6-f76c-49ab-8ec8-705439e43e4b · outbound

This paper cites Seed2.0, 2026.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Seed2.0, 2026

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:41.534869Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 825e6a81-4696-4ec4-9c5d-072f943e5227 · outbound

This paper cites Seed Speech ASR 2.0 Documentation.BytePlus documentation, 2026.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Seed Speech ASR 2.0 Documentation.BytePlus documentation, 2026

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:41.593752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7bc06fd7-2e8a-4e25-90cd-136a05fd081e · outbound

This paper cites FlexiVoice: Enabling flexible style control in zero-shot TTS with natural language instructions.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks FlexiVoice: Enabling flexible style control in zero-shot TTS with natural language instructions

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:41.675718Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8863186-fa0b-4565-b00b-518392991fb4 · outbound

This paper cites GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:41.762978Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebceb8d1-6133-48d2-9af2-c7551f683a26 · outbound

This paper cites Wavlm: Large-scale self-supervised pre-training for full stack speech processing.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Wavlm: Large-scale self-supervised pre-training for full stack speech processing

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:41.850191Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80a543f5-a0a0-44b8-b3fb-d3e4ff8eec92 · outbound

This paper cites 3d-speaker-toolkit: An open-source toolkit for multimodal speaker verifi- cation and diarization.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks 3d-speaker-toolkit: An open-source toolkit for multimodal speaker verifi- cation and diarization

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:41.931436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2115d0ec-3fc9-4b3c-9ab8-63d41e39a447 · outbound

This paper cites SeniorTalk: A chinese conversation dataset with rich annotations for super-aged seniors.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks SeniorTalk: A chinese conversation dataset with rich annotations for super-aged seniors

Reference 12

Resolution: verified exact; raw_fallback, observed 2026-08-07T00:14:53.843147Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 26617ea3-3047-4c0c-89fa-e2d4ecbb251a · outbound

This paper cites F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:42.071504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bab600fc-9fff-4482-87cb-ad71cb6b8404 · outbound

This paper cites Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:42.146192Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56a395f1-300c-42b5-9e9a-970f52391e57 · outbound

This paper cites an unresolved cited work.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Unresolved cited work

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:42.210992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a894298-99d8-4ad0-9db8-60155983ecf2 · outbound

This paper cites An Unsupervised Autoregressive Model for Speech Representation Learning.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks An Unsupervised Autoregressive Model for Speech Representation Learning

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:42.280938Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5538af60-d184-442e-9b29-e5546f3af888 · outbound

This paper cites GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:42.345506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa4d01e6-0e87-4803-bcab-35f737f7ba19 · outbound

This paper cites DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:42.422224Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 406b16fb-4c00-4ca5-b61a-2ad9403cd726 · outbound

This paper cites High Fidelity Neural Audio Compression.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks High Fidelity Neural Audio Compression

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:42.483675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 629d49a3-6ef6-4718-bcc5-644e9df7c498 · outbound

This paper cites ECAPA-TDNN: Emphasized channel attention, propagation and aggregation in TDNN based speaker verification.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks ECAPA-TDNN: Emphasized channel attention, propagation and aggregation in TDNN based speaker verification

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:42.547078Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e7f5f51-4028-4126-bf09-e77a18dda934 · outbound

This paper cites CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:42.592339Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a2c3f76-4745-4fa3-b25e-6a030932b29c · outbound

This paper cites CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:42.646582Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 275a5ee0-2cdb-44f1-beeb-8887c4937a8c · outbound

This paper cites Stable audio open.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Stable audio open

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:42.701090Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ea08738-fe24-4a9c-b9d0-96302d56204a · outbound

This paper cites Stable Audio 3.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Stable Audio 3

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:42.763577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8ce8da0-1d8f-4a2a-8137-1dab0c692588 · outbound

This paper cites Falk, Chenxi Zheng, and Wai-Yip Chan.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Falk, Chenxi Zheng, and Wai-Yip Chan

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:42.814904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 468a3151-13de-494f-bb8d-c1a995014d54 · outbound

This paper cites Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity.Journal of Machine Learning Research, 23(120):1–39, 2022.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity.Journal of Machine Learning Research, 23(120):1–39, 2022

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:42.943789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee3559cc-902c-4a5e-8aa7-a43b9f23cc53 · outbound

This paper cites Fish-Speech: Leveraging Large Language Models for Advanced Multilingual Text-to-Speech Synthesis.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Fish-Speech: Leveraging Large Language Models for Advanced Multilingual Text-to-Speech Synthesis

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:43.018619Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9fc33832-c003-4685-a1b1-7ee3ac42e8c2 · outbound

This paper cites Fsd50k: an open dataset of human-labeled sound events.IEEE/ACM Transactionson Audio, Speech, and Language Processing, 30:829–852, 2021.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Fsd50k: an open dataset of human-labeled sound events.IEEE/ACM Transactionson Audio, Speech, and Language Processing, 30:829–852, 2021

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:43.073690Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0518d6f5-8d75-48c3-b78a-d633529e7370 · outbound

This paper cites ACE-Step: A Step Towards Music Generation Foundation Model.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks ACE-Step: A Step Towards Music Generation Foundation Model

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:43.128810Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c21aa88-2213-4606-98eb-e49dc3c1c900 · outbound

This paper cites Gemini 2.5 Pro model card, 2025.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Gemini 2.5 Pro model card, 2025

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:43.186318Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1ba9792-4aab-40b9-9f65-7f4614df886a · outbound

This paper cites Gemini 3 Pro model card, 2025.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Gemini 3 Pro model card, 2025

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:43.234916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f428483-1094-474a-94e4-b9c1f8069bcc · outbound

This paper cites Gemini 3.5 Flash model card, 2026.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Gemini 3.5 Flash model card, 2026

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:43.287513Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 398c03d8-690b-4022-b369-76dbf280892e · outbound

This paper cites Gray and John D.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Gray and John D

Reference 33

Resolution: metadata mismatch; raw_fallback, observed 2026-08-07T00:14:53.099472Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 13cb153f-3be4-453e-b761-803c1b53ce09 · outbound

This paper cites MRSAudio: A large-scale multimodal recorded spatial audio dataset with refined annotations.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks MRSAudio: A large-scale multimodal recorded spatial audio dataset with refined annotations

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:43.425923Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3aaee3ad-b073-4f0a-8d1b-5cdf76fa6c1b · outbound

This paper cites TechSinger: Technique Controllable Multilingual Singing Voice Synthesis via Flow Matching.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks TechSinger: Technique Controllable Multilingual Singing Voice Synthesis via Flow Matching

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:43.486294Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0675b870-9e75-46ce-a1c9-36c8511e58e6 · outbound

This paper cites STARS: A unified framework for singing transcription, alignment, and refined style annotation.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks STARS: A unified framework for singing transcription, alignment, and refined style annotation

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:43.568806Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b288ef5-2c01-4a1f-824a-60db308d8ab5 · outbound

This paper cites Classifier-Free Diffusion Guidance.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Classifier-Free Diffusion Guidance

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:43.690618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e949b5c7-b8f6-4f56-b981-51364bb9d405 · outbound

This paper cites VoiceSculptor: Your voice, designed by you.arXiv preprint arXiv:2601.10629, 2026.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks VoiceSculptor: Your voice, designed by you.arXiv preprint arXiv:2601.10629, 2026

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:43.751576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ccfcd34-cce5-4033-b454-67182e2d72ec · outbound

This paper cites Word Level Timestamp Generation for Automatic Speech Recognition and Translation.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Word Level Timestamp Generation for Automatic Speech Recognition and Translation

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:43.788931Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9abdc930-d034-4b06-b470-9efcf5667b65 · outbound

This paper cites python-pinyin: pypinyin, 2023.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks python-pinyin: pypinyin, 2023

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:43.865086Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ad53429-5f47-4f33-9b3a-5a55b1bb9063 · outbound

This paper cites InstructTTSEval: Benchmarking Complex Natural-Language Instruction Following in Text-to-Speech Systems.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks InstructTTSEval: Benchmarking Complex Natural-Language Instruction Following in Text-to-Speech Systems

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:43.938774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cfba38d7-261f-471b-8c81-8e48249828ab · outbound

This paper cites MOSS-VoiceGenerator: Create realistic voices with natural language descriptions.arXiv preprint arXiv:2603.28086, 2026.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks MOSS-VoiceGenerator: Create realistic voices with natural language descriptions.arXiv preprint arXiv:2603.28086, 2026

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:44.013468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f76e05c2-caee-4bb0-833f-acfcd4c9bf27 · outbound

This paper cites Generspeech: Towards style transfer for generalizable out-of-domain text-to-speech.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Generspeech: Towards style transfer for generalizable out-of-domain text-to-speech

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:44.072588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f142beb-f802-45d1-952f-0c0e75de527d · outbound

This paper cites Make-an-audio: Text-to-audio generation with prompt-enhanced diffusion models.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Make-an-audio: Text-to-audio generation with prompt-enhanced diffusion models

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:44.128295Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8bd961c4-c379-4c63-bc1a-f899dad96973 · outbound

This paper cites Categorical Reparameterization with Gumbel-Softmax.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Categorical Reparameterization with Gumbel-Softmax

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:44.188454Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de7de596-658d-464a-afbe-8d5945ac41c2 · outbound

This paper cites UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:44.291965Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65bf9d44-5877-453f-a5c2-dbfd4a626359 · outbound

This paper cites WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:44.413014Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 145311e9-5980-45c6-83c6-68dd594e8f83 · outbound

This paper cites Latent-domain predictive neural speech coding.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Latent-domain predictive neural speech coding

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:44.516351Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1d65616-ac24-4a57-9f4f-cfd2485a6be1 · outbound

This paper cites Mega-tts 2: Boosting prompting mechanisms for zero-shot speech synthesis.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Mega-tts 2: Boosting prompting mechanisms for zero-shot speech synthesis

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:44.603836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf3d068e-ceb0-4675-abbf-063188f005fa · outbound

This paper cites MegaTTS 3: Sparse Alignment Enhanced Latent Diffusion Transformer for Zero-Shot Speech Synthesis.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks MegaTTS 3: Sparse Alignment Enhanced Latent Diffusion Transformer for Zero-Shot Speech Synthesis

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:44.716159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 913701e3-7d01-4e72-8f4d-9caa3d9c1a73 · outbound

This paper cites MoonCast: High-Quality Zero-Shot Podcast Generation.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks MoonCast: High-Quality Zero-Shot Podcast Generation

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:44.813923Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3aee4add-7bbf-4338-8bcb-e00b8f05c8a9 · outbound

This paper cites Libriheavy: A 50,000 hours asr corpus with punctuation casing and context.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Libriheavy: A 50,000 hours asr corpus with punctuation casing and context

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:44.915123Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2372d0f5-d560-4c5a-a9f2-25412638214b · outbound

This paper cites AudioCaps: Generating captions for audios in the wild.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks AudioCaps: Generating captions for audios in the wild

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:45.013023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36bcbb4a-06ce-49ff-8ac1-e50046674a45 · outbound

This paper cites Best-worst scaling more reliable than rating scales: A case study on sentiment intensity annotation.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Best-worst scaling more reliable than rating scales: A case study on sentiment intensity annotation

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:45.110663Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31010d63-83be-4fe6-a15e-d470da4b3634 · outbound

This paper cites Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis.Advances in neural information processing systems, 33:17022–17033, 2020.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis.Advances in neural information processing systems, 33:17022–17033, 2020

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:45.209549Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a0e8681-68a2-4b02-8ca6-9a95ba03e568 · outbound

This paper cites Kubichek.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Kubichek

Reference 56

Resolution: metadata mismatch; raw_fallback, observed 2026-08-07T00:14:52.634038Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 89fb67de-fd30-4c14-b4fc-fa250198c48f · outbound

This paper cites Torchaudio-squim: Reference-less speech quality and intelligibility measures in torchaudio.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Torchaudio-squim: Reference-less speech quality and intelligibility measures in torchaudio

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:45.422509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59066311-494b-4bd7-b822-fd5f4f5b1025 · outbound

This paper cites High-Fidelity Audio Compression with Improved RVQGAN.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks High-Fidelity Audio Compression with Improved RVQGAN

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:45.767421Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 274b58e5-e371-4c0c-bf41-58c2f4508c73 · outbound

This paper cites Parler-TTS.GitHub repository, 2024.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Parler-TTS.GitHub repository, 2024

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:45.897887Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d9dbd49-c119-4d3b-b0cf-76080032ac4d · outbound

This paper cites Towards streaming synchronized spatial audio generation via autoregressive diffusion transformer.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Towards streaming synchronized spatial audio generation via autoregressive diffusion transformer

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:45.972331Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64f66b5f-a00e-4e28-b50c-be9cec58a48d · outbound

This paper cites Robust Singing Voice Transcription Serves Synthesis.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Robust Singing Voice Transcription Serves Synthesis

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:46.067633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f35ae698-ac55-4c9a-a820-2a26e6f09cd4 · outbound

This paper cites SwanVoice: Expressive Long-Form Zero-Shot Speech Synthesis for Both Monologue and Dialogue.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks SwanVoice: Expressive Long-Form Zero-Shot Speech Synthesis for Both Monologue and Dialogue

Reference 63

Resolution: verified exact; local_arxiv, observed 2026-08-07T00:14:52.340147Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation a4190413-a002-4726-96a9-ee972d6a1490 · outbound

This paper cites Flow matching for generative modeling.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Flow matching for generative modeling

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:46.222847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f24b2542-123b-447a-a743-6345e1ce0e7a · outbound

This paper cites UniMoE- Audio: Unified speech and music generation with dynamic-capacity MoE.arXiv preprint arXiv:2510.13344, 2025.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks UniMoE- Audio: Unified speech and music generation with dynamic-capacity MoE.arXiv preprint arXiv:2510.13344, 2025

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:46.318767Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48989418-7daa-453e-99e1-7a3eebd4211b · outbound

This paper cites Decoupled weight decay regularization.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Decoupled weight decay regularization

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:46.430188Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d33c18b7-0caa-4bd3-9a9e-2e5011ebca0f · outbound

This paper cites Natural language guidance of high-fidelity text-to-speech with synthetic annotations.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Natural language guidance of high-fidelity text-to-speech with synthetic annotations

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:46.524756Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5bb9fd7-b8dd-44bc-9ec0-195f0b295945 · outbound

This paper cites MOSS-TTSD.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks MOSS-TTSD

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:46.600213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 528e3f56-ed6d-458b-8d18-2d5f0e93ab3e · outbound

This paper cites Representation Learning with Contrastive Predictive Coding.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Representation Learning with Contrastive Predictive Coding

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:46.711486Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0397d39e-6d29-4f14-96eb-005d53cb285a · outbound

This paper cites A multimodal evaluation framework for spatial audio playback systems: From localization to listener preference.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks A multimodal evaluation framework for spatial audio playback systems: From localization to listener preference

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:46.787489Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 131edcb5-940e-44b9-96ce-f9d35819cbee · outbound

This paper cites Audio Editing in the Era of Foundation Models: A Survey.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Audio Editing in the Era of Foundation Models: A Survey

Reference 71

Resolution: verified exact; local_arxiv, observed 2026-08-07T00:14:52.074519Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 26b3406d-42d4-44ca-bf3e-58a62695a12e · outbound

This paper cites Comprehensive Benchmarking of Long-Form Speech Generation in Diverse Scenarios.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Comprehensive Benchmarking of Long-Form Speech Generation in Diverse Scenarios

Reference 72

Resolution: verified exact; local_arxiv, observed 2026-08-07T00:14:51.835378Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ac8b1340-c8f1-4778-87e3-5c8b05add0ea · outbound

This paper cites Librispeech: an asr corpus based on public domain audio books.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Librispeech: an asr corpus based on public domain audio books

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:47.015110Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7cecd235-87b3-40c3-8f52-32a819df9aab · outbound

This paper cites SAME: A Semantically-Aligned Music Autoencoder.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks SAME: A Semantically-Aligned Music Autoencoder

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:47.082431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85f2379a-1267-444b-ae27-72f2a45d69cd · outbound

This paper cites Scalable diffusion models with transformers.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Scalable diffusion models with transformers

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:47.166984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b72284d2-4250-44f5-b7c9-cbabb5aba932 · outbound

This paper cites VibeVoice Technical Report.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks VibeVoice Technical Report

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:47.221328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fe2f0d6-c32e-4975-87b4-98fba54c03ec · outbound

This paper cites Qwen3-TTS Technical Report.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Qwen3-TTS Technical Report

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:47.314501Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70c51ebe-666a-45fd-ab12-5885f1515156 · outbound

This paper cites Nemo forced aligner and its application to word alignment for subtitle generation.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Nemo forced aligner and its application to word alignment for subtitle generation

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:47.388246Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a87082ea-d441-4166-be99-8a6cc1be3a89 · outbound

This paper cites an unresolved cited work.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Unresolved cited work

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:47.480628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0857a230-ecd5-4c80-aacf-0b37d099e946 · outbound

This paper cites OV-InstructTTS: Towards open-vocabulary instruct text-to-speech.arXiv preprint arXiv:2601.01459, 2026.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks OV-InstructTTS: Towards open-vocabulary instruct text-to-speech.arXiv preprint arXiv:2601.01459, 2026

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:47.571640Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb35624b-16cb-42de-b677-ebf4912623bf · outbound

This paper cites an unresolved cited work.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Unresolved cited work

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:47.640432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e388abd-9eed-4c5f-bef9-13498a556294 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:47.719103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 265648e2-a0c1-4985-8af3-e4ba1b4ce885 · outbound

This paper cites NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:47.793573Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a95b1244-7755-434f-a7bb-b75e33b5c60f · outbound

This paper cites AISHELL-3: A Multi-speaker Mandarin TTS Corpus and the Baselines.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks AISHELL-3: A Multi-speaker Mandarin TTS Corpus and the Baselines

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:47.871653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5dd704b5-fe2f-401b-9b97-bb112eec6049 · outbound

This paper cites Improving the Diffusability of Autoencoders.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Improving the Diffusability of Autoencoders

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:47.940224Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c175b092-2a48-4944-b38b-757f4ae97ea6 · outbound

This paper cites The 2018 signal separation evaluation campaign.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks The 2018 signal separation evaluation campaign

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:48.024601Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1db877a3-803c-4a61-bfc3-812b220892e1 · outbound

This paper cites An algorithm for intelligibility prediction of time–frequency weighted noisy speech.IEEE Transactions on audio, speech, and language processing, 19(7): 2125–2136, 2011.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks An algorithm for intelligibility prediction of time–frequency weighted noisy speech.IEEE Transactions on audio, speech, and language processing, 19(7): 2125–2136, 2011

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:48.098240Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5326b022-af52-4660-bbc9-502176ebfb76 · outbound

This paper cites Seedance 2.0: Advancing Video Generation for World Complexity.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Seedance 2.0: Advancing Video Generation for World Complexity

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:48.166617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9facae7-a25b-4d97-bbf6-c3f310d05aae · outbound

This paper cites FlowTTS-GRPO: Online Reinforcement Learning with Multi-Objective Reward Optimization for Flow-Matching Based Text-to-Speech.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks FlowTTS-GRPO: Online Reinforcement Learning with Multi-Objective Reward Optimization for Flow-Matching Based Text-to-Speech

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:48.234028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dde9d30c-28e3-48db-bfa2-a2f7981db857 · outbound

This paper cites CAM++: A Fast and Efficient Network for Speaker Verification Using Context-Aware Masking.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks CAM++: A Fast and Efficient Network for Speaker Verification Using Context-Aware Masking

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:48.305543Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b45fb951-7073-44ac-a50a-849f3e67cf70 · outbound

This paper cites Auxiliary-Loss-Free Load Balancing Strategy for Mixture-of-Experts.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Auxiliary-Loss-Free Load Balancing Strategy for Mixture-of-Experts

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:48.376493Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9cabb25-a778-4980-9293-5f01de63f73c · outbound

This paper cites Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:48.455337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c59ab591-ccf8-488e-80f9-9d7ac157491b · outbound

This paper cites Soulx-podcast: Towards realistic long-form podcasts with dialectal and paralinguistic diversity.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Soulx-podcast: Towards realistic long-form podcasts with dialectal and paralinguistic diversity

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:48.549099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc61158c-106d-4638-89d6-178270575d88 · outbound

This paper cites FireRedTTS-2: Towards Long Conversational Speech Generation for Podcast and Chatbot.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks FireRedTTS-2: Towards Long Conversational Speech Generation for Podcast and Chatbot

Reference 94

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:48.608557Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbc6b733-63c5-4f8b-85b2-a6837ba82714 · outbound

This paper cites Secap: Speech emotion captioning with large language model.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Secap: Speech emotion captioning with large language model

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:48.682385Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e934298-5e24-4464-893f-e74432a7a2e8 · outbound

This paper cites CSTR VCTK Corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92), 2019.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks CSTR VCTK Corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92), 2019

Reference 96

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:14:55.631663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 2bae1a7d-e835-4a69-95b2-ea307491fa90 · outbound

This paper cites Qwen3 Technical Report.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Qwen3 Technical Report

Reference 97

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:48.819903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1619c124-c65d-48d3-ac09-b57a83db686b · outbound

This paper cites an unresolved cited work.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Unresolved cited work

Reference 98

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:14:55.528938Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation bcd2f08e-ee7f-4ed1-b3c2-e482f20237cf · outbound

This paper cites UniAudio: An Audio Foundation Model Toward Universal Audio Generation.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks UniAudio: An Audio Foundation Model Toward Universal Audio Generation

Reference 99

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:49.016529Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10357896-112d-4d39-bf8e-1e6cb590b7d1 · outbound

This paper cites Weiss, Ye Jia, Zhifeng Chen, and Yonghui Wu.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Weiss, Ye Jia, Zhifeng Chen, and Yonghui Wu

Reference 100

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:14:55.429260Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 6cb030b0-22d5-417f-8608-fd026805c0db · outbound

This paper cites Zezario, Szu-Wei Fu, Chiou-Shann Fuh, Yu Tsao, and Hsin-Min Wang.

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Zezario, Szu-Wei Fu, Chiou-Shann Fuh, Yu Tsao, and Hsin-Min Wang

Reference 101

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:14:55.322898Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers