Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens | Paper Citation Record

Observation ca3a1a53-ced5-4735-89a8-7469ee6554d1 · inbound

Muyan-TTS: A Trainable Text-to-Speech Model Optimized for Podcast Scenarios with a $50K Budget cites this paper.

Muyan-TTS: A Trainable Text-to-Speech Model Optimized for Podcast Scenarios with a $50K Budget Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-16T06:05:11.478547Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c99b361-cddf-44b0-b87b-f9819dd76fb3 · inbound

FlowDubber: Movie Dubbing with LLM-based Semantic-aware Learning and Flow Matching based Voice Enhancing cites this paper.

FlowDubber: Movie Dubbing with LLM-based Semantic-aware Learning and Flow Matching based Voice Enhancing Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-16T04:26:03.293855Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 320ec6cd-47ca-4755-b7f4-245507619faa · inbound

Audio Turing Test: Benchmarking the Human-likeness of Large Language Model-based Text-to-Speech Systems in Chinese cites this paper.

Audio Turing Test: Benchmarking the Human-likeness of Large Language Model-based Text-to-Speech Systems in Chinese Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-15T21:02:45.866945Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a745d27-1788-4f6c-9bd8-47e1b4265e34 · inbound

UniTTS: An end-to-end TTS system without decoupling of acoustic and semantic information cites this paper.

UniTTS: An end-to-end TTS system without decoupling of acoustic and semantic information Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T14:53:17.592637Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 658331e9-759f-4387-83f8-826b084a0d92 · inbound

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

CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-17T09:39:51.552824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 083c2582-08da-4a78-b51a-176982c32b9b · inbound

Speaking images. A novel framework for the automated self-description of artworks cites this paper.

Speaking images. A novel framework for the automated self-description of artworks Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T13:17:52.259140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45102f47-a413-4735-b698-7e1c2858eaa9 · inbound

ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching cites this paper.

ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-07T00:45:17.314055Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5f9d465-6cd7-435c-bc08-08a9f234aa88 · inbound

Optimizing Multilingual Text-To-Speech with Accents & Emotions cites this paper.

Optimizing Multilingual Text-To-Speech with Accents & Emotions Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T23:49:29.495278Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7cf52851-2267-4464-ac50-5ebe5ba8e95d · inbound

IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech cites this paper.

IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-06T23:21:59.042807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf87162d-6f74-49b5-b76f-603227d7de29 · inbound

Traceable TTS: Toward Watermark-Free TTS with Strong Traceability cites this paper.

Traceable TTS: Toward Watermark-Free TTS with Strong Traceability Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T20:06:18.858838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a06dcc2-5cfc-46c5-a2c9-3a91297b2948 · inbound

ILT-Iterative LoRA Training through Focus-Feedback-Fix for Multilingual Speech Recognition cites this paper.

ILT-Iterative LoRA Training through Focus-Feedback-Fix for Multilingual Speech Recognition Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T18:23:31.298864Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89afd59f-6147-4c85-95e2-9fa326083994 · inbound

ZipVoice-Dialog: Non-Autoregressive Spoken Dialogue Generation with Flow Matching cites this paper.

ZipVoice-Dialog: Non-Autoregressive Spoken Dialogue Generation with Flow Matching Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-05-19T04:32:03.669368Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation e4ebd70e-7347-4e0b-897d-2364e7a2b092 · inbound

DMOSpeech 2: Reinforcement Learning for Duration Prediction in Metric-Optimized Speech Synthesis cites this paper.

DMOSpeech 2: Reinforcement Learning for Duration Prediction in Metric-Optimized Speech Synthesis Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:20.918034Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a925d1f3-84b8-455a-9fad-945bdf949598 · inbound

Step-Audio 2 Technical Report cites this paper.

Step-Audio 2 Technical Report Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 66

Resolution: verified exact; arxiv_id, observed 2026-05-17T09:39:51.552824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 0c5d9294-2c5c-4955-820b-fd37b48e7a1b · inbound

Adaptive Duration Model for Text Speech Alignment cites this paper.

Adaptive Duration Model for Text Speech Alignment Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T11:34:08.167239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9accb710-3a08-439c-b5ad-e7e7fbbba6c0 · inbound

MoE-TTS: Enhancing Out-of-Domain Text Understanding for Description-based TTS via Mixture-of-Experts cites this paper.

MoE-TTS: Enhancing Out-of-Domain Text Understanding for Description-based TTS via Mixture-of-Experts Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-05T20:04:51.369330Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61f5c358-f70e-48f2-9779-a8badee88a3c · inbound

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis cites this paper.

CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-05T16:01:52.823558Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c68d5cec-178c-4b7f-87a1-08a6cf00b825 · inbound

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

FireRedTTS-2: Towards Long Conversational Speech Generation for Podcast and Chatbot Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-05T12:00:45.305208Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03362d43-70ad-431d-86e9-4539288b7823 · inbound

Audio Deepfake Verification cites this paper.

Audio Deepfake Verification Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-15T16:12:07.934329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af68322a-adf3-429a-9b59-fdc25d09a134 · inbound

DiFlow-TTS: Compact and Low-Latency Zero-Shot Text-to-Speech with Discrete Flow Matching cites this paper.

DiFlow-TTS: Compact and Low-Latency Zero-Shot Text-to-Speech with Discrete Flow Matching Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-04T18:51:21.114170Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ff6b021-b5f3-451e-894c-08844f99ef49 · inbound

DiTReducio: A Training-Free Acceleration for DiT-Based TTS via Progressive Calibration cites this paper.

DiTReducio: A Training-Free Acceleration for DiT-Based TTS via Progressive Calibration Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-04T19:11:59.596167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 825cea1f-649e-4269-ac2d-da8e597cbc63 · inbound

Speaker Anonymisation for Speech-based Suicide Risk Detection cites this paper.

Speaker Anonymisation for Speech-based Suicide Risk Detection Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T15:48:32.047386Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06f231c7-7dd5-4e17-92c0-188fee700bf8 · inbound

UniVoice: Unifying Autoregressive ASR and Flow-Matching based TTS with Large Language Models cites this paper.

UniVoice: Unifying Autoregressive ASR and Flow-Matching based TTS with Large Language Models Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-04T11:29:36.515375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a8b220f-d17b-4d31-b1b5-ea219981fda6 · inbound

UniSE: A Unified Framework for Decoder-Only Autoregressive LM-Based Speech Enhancement cites this paper.

UniSE: A Unified Framework for Decoder-Only Autoregressive LM-Based Speech Enhancement Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T08:29:17.918593Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 815c3a28-de4e-4fe9-94b1-972d24b9bfd3 · inbound

Qwen3-TTS Technical Report cites this paper.

Qwen3-TTS Technical Report Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-17T09:39:51.552824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation d5fc9a45-8b02-43b6-939b-541e33fa06e6 · inbound

DiFlowDubber: Discrete Flow Matching for Automated Video Dubbing via Cross-Modal Alignment and Synchronization cites this paper.

DiFlowDubber: Discrete Flow Matching for Automated Video Dubbing via Cross-Modal Alignment and Synchronization Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 54

Resolution: verified exact; arxiv_id, observed 2026-05-17T09:39:51.552824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 0ee2ca03-4cb0-4c66-ba8b-feabbae8ded2 · inbound

OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models cites this paper.

OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-17T09:39:51.552824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation d3203e74-6950-41b6-b3f9-9b6ad7aae489 · inbound

WAND: Windowed Attention and Knowledge Distillation for Efficient Autoregressive Text-to-Speech Models cites this paper.

WAND: Windowed Attention and Knowledge Distillation for Efficient Autoregressive Text-to-Speech Models Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-17T09:39:51.552824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 032baf92-2d34-4419-a84a-9db2a127cc2c · inbound

ActorMind: Emulating Human Actor Reasoning for Speech Role-Playing cites this paper.

ActorMind: Emulating Human Actor Reasoning for Speech Role-Playing Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-05-17T09:39:51.552824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 9e41184c-0120-46dc-823d-c196fdc6e7cb · inbound

Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey cites this paper.

Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 75

Resolution: verified exact; arxiv_id, observed 2026-05-17T09:39:51.552824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 5bb3292c-5288-40fd-be9f-aa3f4257990a · inbound

Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey cites this paper.

Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 86

Resolution: unresolved; no resolver link, observed 2026-07-12T22:04:31.302192Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7759d619-2cfb-40c0-9a1f-c3b129291c2a · inbound

NVBench: A Benchmark for Speech Synthesis with Non-Verbal Vocalizations cites this paper.

NVBench: A Benchmark for Speech Synthesis with Non-Verbal Vocalizations Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-17T09:39:51.552824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation e1e6834f-1a4a-4a34-9992-c3c0b4df4f7c · inbound

MINT-Bench: A Comprehensive Multilingual Benchmark for Instruction-Following Text-to-Speech cites this paper.

MINT-Bench: A Comprehensive Multilingual Benchmark for Instruction-Following Text-to-Speech Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 33

Resolution: metadata mismatch; arxiv_id, observed 2026-05-17T09:39:51.552824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation cc57d162-1654-46ea-aa7e-a8702aab346b · inbound

RTCFake: Speech Deepfake Detection in Real-Time Communication cites this paper.

RTCFake: Speech Deepfake Detection in Real-Time Communication Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-17T09:39:51.552824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 6c12d119-f452-48b7-828a-6f0fc7a4ea25 · inbound

The False Resonance: A Critical Examination of Emotion Embedding Similarity for Speech Generation Evaluation cites this paper.

The False Resonance: A Critical Examination of Emotion Embedding Similarity for Speech Generation Evaluation Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 59

Resolution: verified exact; arxiv_id, observed 2026-05-17T09:39:51.552824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation efb8d1e8-9160-4f13-8a1a-d8e873d46580 · inbound

The False Resonance: A Critical Examination of Emotion Embedding Similarity for Speech Generation Evaluation cites this paper.

The False Resonance: A Critical Examination of Emotion Embedding Similarity for Speech Generation Evaluation Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-02T15:21:28.920158Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81a62402-3d51-45c6-98cf-bb2906a96b7f · inbound

VITA-QinYu: Expressive Spoken Language Model for Role-Playing and Singing cites this paper.

VITA-QinYu: Expressive Spoken Language Model for Role-Playing and Singing Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 7

Resolution: metadata mismatch; arxiv_id, observed 2026-05-17T09:39:51.552824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 6977a6bd-2144-48d5-99e7-34103be00a11 · inbound

Reducing Linguistic Hallucination in LM-Based Speech Enhancement via Noise-Invariant Acoustic-Semantic Distillation cites this paper.

Reducing Linguistic Hallucination in LM-Based Speech Enhancement via Noise-Invariant Acoustic-Semantic Distillation Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 48

Resolution: verified exact; arxiv_id, observed 2026-05-17T09:39:51.552824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation e007d887-c74f-4f1b-919e-9e9e6e87eee2 · inbound

Kinetic-Optimal Scheduling with Moment Correction for Metric-Induced Discrete Flow Matching in Zero-Shot Text-to-Speech cites this paper.

Kinetic-Optimal Scheduling with Moment Correction for Metric-Induced Discrete Flow Matching in Zero-Shot Text-to-Speech Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-17T09:39:51.552824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 0b14dfbb-e19b-4af2-a375-5ab8589f6bc3 · inbound

How Should LLMs Listen While Speaking? A Study of User-Stream Routing in Full-Duplex Spoken Dialogue cites this paper.

How Should LLMs Listen While Speaking? A Study of User-Stream Routing in Full-Duplex Spoken Dialogue Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 49

Resolution: verified exact; arxiv_id, observed 2026-05-17T09:39:51.552824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 6ae81e12-bb5b-46de-aff7-f569e95e1a1b · inbound

AffectCodec: Emotion-Preserving Neural Speech Codec for Expressive Speech Modeling cites this paper.

AffectCodec: Emotion-Preserving Neural Speech Codec for Expressive Speech Modeling Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 52

Resolution: metadata mismatch; arxiv_id, observed 2026-05-17T09:39:51.552824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 9607944b-5c3b-41ae-b04c-c10646d4901c · inbound

SemaVoice: Semantic-Aware Continuous Autoregressive Speech Synthesis cites this paper.

SemaVoice: Semantic-Aware Continuous Autoregressive Speech Synthesis Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-05-19T19:02:43.603286Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation a98bcf48-2a04-4ac6-8f94-fb52873bf9d3 · inbound

AgentSteerTTS: A Multi-Agent Closed-Loop Framework for Composite-Instruction Text-to-Speech cites this paper.

AgentSteerTTS: A Multi-Agent Closed-Loop Framework for Composite-Instruction Text-to-Speech Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 90

Resolution: verified exact; local_arxiv, observed 2026-05-20T21:19:03.226500Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 29e3e707-dd00-4e28-b5dd-054cff31428d · inbound

RobustSpeechFlow: Learning Robust Text-to-Speech Trajectories via Augmentation-based Contrastive Flow Matching cites this paper.

RobustSpeechFlow: Learning Robust Text-to-Speech Trajectories via Augmentation-based Contrastive Flow Matching Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-05-22T03:00:59.013899Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 1ccef922-c3a6-4f84-9aa0-7095ea3f6202 · inbound

RobustSpeechFlow: Learning Robust Text-to-Speech Trajectories via Augmentation-based Contrastive Flow Matching cites this paper.

RobustSpeechFlow: Learning Robust Text-to-Speech Trajectories via Augmentation-based Contrastive Flow Matching Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-02T13:29:53.566575Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85d2052b-70ad-48c4-94d6-25e41c559dfa · inbound

Hidden in Plain Tokens: Simply Robust, Gradient-Free Watermark for Synthetic Audio cites this paper.

Hidden in Plain Tokens: Simply Robust, Gradient-Free Watermark for Synthetic Audio Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 17

Resolution: metadata mismatch; local_arxiv, observed 2026-06-29T23:14:01.868617Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation b7f74d6d-11cc-4c4a-a803-fb5f05c44891 · inbound

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

SwanVoice: Expressive Long-Form Zero-Shot Speech Synthesis for Both Monologue and Dialogue Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 46

Resolution: verified exact; local_arxiv, observed 2026-07-01T20:26:13.152245Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 8665f702-ea46-4599-849c-b89776716389 · inbound

WavTTS: Towards High-Quality Zero-Shot TTS via Direct Raw Waveform Modeling cites this paper.

WavTTS: Towards High-Quality Zero-Shot TTS via Direct Raw Waveform Modeling Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 86

Resolution: verified exact; local_arxiv, observed 2026-07-02T05:16:39.744079Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 3174fc14-969f-4e16-b1f8-dda8ee890e65 · inbound

CleanCodec: Efficient and Robust Speech Tokenization via Perceptually Guided Encoding cites this paper.

CleanCodec: Efficient and Robust Speech Tokenization via Perceptually Guided Encoding Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-06-28T05:21:39.804685Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 1a1f96d6-7f35-4392-9505-788a2d154bae · inbound

GLASS: GRPO-Trained LoRA for Acoustic Style Steering in Zero-Shot Text-to-Speech cites this paper.

GLASS: GRPO-Trained LoRA for Acoustic Style Steering in Zero-Shot Text-to-Speech Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 28

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T15:27:04.877027Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation e8aeb4cb-e157-4f1e-952e-49575cdc4a3d · inbound

TLDR: Compressing Audio Tokens for Efficient Autoregressive Text-to-Speech cites this paper.

TLDR: Compressing Audio Tokens for Efficient Autoregressive Text-to-Speech Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-07-03T03:07:35.861159Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 4c5aa081-7ff1-4e12-b4b4-28eb23a8961a · inbound

FlashTTS: Fast Streaming TTS with MTP Acceleration and X-pred Mean Flow Distillation cites this paper.

FlashTTS: Fast Streaming TTS with MTP Acceleration and X-pred Mean Flow Distillation Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-07-03T03:27:36.146102Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 0491a8e6-a336-4ea9-82c2-9999197fb4a0 · inbound

End-to-End Training for Discrete Token LLM based TTS System cites this paper.

End-to-End Training for Discrete Token LLM based TTS System Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-07-03T03:27:34.903098Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation aa152316-2677-43d6-9aa4-a45bfef35ba0 · inbound

SDP-Codec: A Speaker-Decoupled Speech Codec with Pitch Injection for Low-Bitrate Coding and Zero-Shot Voice Conversion cites this paper.

SDP-Codec: A Speaker-Decoupled Speech Codec with Pitch Injection for Low-Bitrate Coding and Zero-Shot Voice Conversion Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-07-04T07:39:38.407351Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 587579d2-b9a5-4802-a375-8e9153cda095 · inbound

LambdaMark: Semantic Audio Watermarking for Robustness and Radioactivity cites this paper.

LambdaMark: Semantic Audio Watermarking for Robustness and Radioactivity Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 57

Resolution: metadata mismatch; local_arxiv, observed 2026-07-04T07:39:39.524651Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 86040e40-24ad-4087-9471-978b9f711cf6 · inbound

Streaming T5-based Text-to-Speech Synthesis with Limited Lookahead cites this paper.

Streaming T5-based Text-to-Speech Synthesis with Limited Lookahead Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-07-04T08:29:41.337402Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation f2ca7e14-86e9-45ab-9112-d512c0572d1c · inbound

AugCodec: A Low-Bitrate Disentangled Neural Speech Codec via Data Augmentation cites this paper.

AugCodec: A Low-Bitrate Disentangled Neural Speech Codec via Data Augmentation Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-07-04T08:29:41.882848Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation b6ca7271-a549-4947-87c6-96b4d5e84e2f · inbound

ISCSLP 2026 CoT-TTS Challenge: Chain-of-Thought Reasoning for Context-Aware Text-to-Speech cites this paper.

ISCSLP 2026 CoT-TTS Challenge: Chain-of-Thought Reasoning for Context-Aware Text-to-Speech Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 43

Resolution: verified exact; local_arxiv, observed 2026-07-04T08:29:42.158604Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation d3c53df9-fa03-4088-a98d-fc2409abcfd6 · inbound

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

FlowTTS-GRPO: Online Reinforcement Learning with Multi-Objective Reward Optimization for Flow-Matching Based Text-to-Speech Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-07-04T12:19:49.663900Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 863ace9b-822c-4cb7-b5f6-4a8a1a89481e · inbound

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

FlowTTS-GRPO: Online Reinforcement Learning with Multi-Objective Reward Optimization for Flow-Matching Based Text-to-Speech Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-12T12:44:20.831164Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc2309cc-a33c-4d8a-854a-4a958ba64342 · inbound

CrossAccent-TTS: Cross-Lingual Accent-Intensity Controllable Text-to-Speech via Disentangled Speaker and Accent Representations cites this paper.

CrossAccent-TTS: Cross-Lingual Accent-Intensity Controllable Text-to-Speech via Disentangled Speaker and Accent Representations Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-07-04T20:20:07.170409Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 526c3869-1c27-4d3b-a04b-08bda1d6c4c1 · inbound

FlexiSLM: A Dynamic and Controllable Frame Rate Spoken Language Model cites this paper.

FlexiSLM: A Dynamic and Controllable Frame Rate Spoken Language Model Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 209

Resolution: metadata mismatch; local_arxiv, observed 2026-07-01T11:45:47.168565Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation bd6ce112-e622-4ab7-8cbf-dba419703643 · inbound

DELTA-TTS: Adapting Autoregressive Model into Diffusion Language Model for Text-to-Speech cites this paper.

DELTA-TTS: Adapting Autoregressive Model into Diffusion Language Model for Text-to-Speech Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-11T21:24:36.925360Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9825cfb-f65c-4be8-9c6a-9eae8e64d9fa · inbound

Unified Audio Intelligence Without Regressing on Text Intelligence cites this paper.

Unified Audio Intelligence Without Regressing on Text Intelligence Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 243

Resolution: metadata mismatch; local_arxiv, observed 2026-07-08T00:04:22.654037Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 308b3215-00ce-4f70-b0cf-f6b0318882bd · inbound

Unified Audio Intelligence Without Regressing on Text Intelligence cites this paper.

Unified Audio Intelligence Without Regressing on Text Intelligence Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 243

Resolution: unresolved; no resolver link, observed 2026-07-11T07:46:49.059192Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a83b9699-f724-4176-8de1-21615976fa81 · inbound

ReGen: Hierarchical Multi-Prompt Representation Generation for Efficient Waveform Diffusion Models cites this paper.

ReGen: Hierarchical Multi-Prompt Representation Generation for Efficient Waveform Diffusion Models Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 101

Resolution: unresolved; no resolver link, observed 2026-07-13T05:10:26.667731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ed4bf9d-46f4-47da-b1d1-88d7a861b82c · inbound

FreyaTTS: A Compact Tokenizer-Free Flow-Matching Transformer for Turkish-First Speech Synthesis cites this paper.

FreyaTTS: A Compact Tokenizer-Free Flow-Matching Transformer for Turkish-First Speech Synthesis Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-13T02:22:47.820537Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efa9c8c8-f4b2-4418-9237-48cb0f51b532 · inbound

FreyaTTS: A Compact Tokenizer-Free Flow-Matching Transformer for Turkish-First Speech Synthesis cites this paper.

FreyaTTS: A Compact Tokenizer-Free Flow-Matching Transformer for Turkish-First Speech Synthesis Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-02T07:39:23.645758Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69ce9690-b3f7-48be-9344-2ff340b19901 · inbound

Faster IndexTTS-2: Accelerating and Streaming Autoregressive Zero-Shot Text-to-Speech Synthesis on GPUs cites this paper.

Faster IndexTTS-2: Accelerating and Streaming Autoregressive Zero-Shot Text-to-Speech Synthesis on GPUs Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T08:40:27.564412Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20c6fb94-ab8a-4374-abb5-e373528bc0a0 · inbound

Qwen-Audio-3.0-TTS: Freely Controllable and Highly Robust Speech Synthesis with Multi-Stage Training Paradigm cites this paper.

Qwen-Audio-3.0-TTS: Freely Controllable and Highly Robust Speech Synthesis with Multi-Stage Training Paradigm Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-31T23:35:21.089160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65821001-88bc-4a4f-8301-65f88dc8ba45 · inbound

MMAC: A Massive Multi-dimensional Benchmark for Audio Captioning cites this paper.

MMAC: A Massive Multi-dimensional Benchmark for Audio Captioning Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-30T11:37:00.186862Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c693153-dad8-4601-af31-ad398c47d5ec · inbound

MMAC: A Massive Multi-dimensional Benchmark for Audio Captioning cites this paper.

MMAC: A Massive Multi-dimensional Benchmark for Audio Captioning Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T09:59:39.136823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ca58211-2071-4b36-82ff-2a6c4b26cb4b · inbound

Stable Autoregressive Speech Generation with Low-Frame-Rate High-Dimensional Continuous Tokens cites this paper.

Stable Autoregressive Speech Generation with Low-Frame-Rate High-Dimensional Continuous Tokens Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 104

Resolution: unresolved; no resolver link, observed 2026-08-03T08:35:55.557807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94e003f1-8bd2-432f-a719-819c7391d48c · inbound

Experience-Calibrated Contrastive Decoding for Mitigating Hallucinations in LM-Based Text-to-Speech cites this paper.

Experience-Calibrated Contrastive Decoding for Mitigating Hallucinations in LM-Based Text-to-Speech Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-15T15:22:08.955751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f826f4d-6309-454f-a685-1ce916139be0 · inbound

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks cites this paper.

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 94

Resolution: unresolved; no resolver link, observed 2026-08-04T16:29:29.149236Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

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

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks cites this paper.

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 9efab4d2-cd97-49f1-94fa-edeb1e746723 · inbound

MeloCodec: Harnessing Melodic Priors for High-Fidelity Singing Voice Representation cites this paper.

MeloCodec: Harnessing Melodic Priors for High-Fidelity Singing Voice Representation Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-08T04:20:42.539324Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c966cb8-0a3c-4ff9-953c-929f7103eef2 · inbound

SemBridge: Semantic Token Anchoring for Continuous-Latent Autoregressive Speech Generation cites this paper.

SemBridge: Semantic Token Anchoring for Continuous-Latent Autoregressive Speech Generation Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 117

Resolution: unresolved; no resolver link, observed 2026-08-10T04:20:42.137255Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2000ce91-14ae-4b79-9ae6-bb88bd612383 · inbound

Luna-TTS Family Technical Report cites this paper.

Luna-TTS Family Technical Report Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-16T00:40:24.975736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1c13e3b-44d7-4ed7-934c-2568ce3b2d8d · inbound

Phoenix TTS: High-Fidelity Synthesis and Voice Conversion via Flow-Matching-Driven Speech Tokenization cites this paper.

Phoenix TTS: High-Fidelity Synthesis and Voice Conversion via Flow-Matching-Driven Speech Tokenization Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-16T00:37:04.986772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f4fc372-c793-4fc4-96fd-5ad5fa39434e · inbound

Rethinking Language Model-Based Generative Speech Enhancement in the Latent Space of a Neural Audio Codec cites this paper.

Rethinking Language Model-Based Generative Speech Enhancement in the Latent Space of a Neural Audio Codec Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-16T00:22:15.051545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers