Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-03T06:36:33.887146Z
Paper Citation Record · LEDGER
Evaluating and Rewarding LALMs for Expressive Role-Play TTS via Mean Continuation Log-Probability
As of 23 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 0 inbound Pith citation observations for arXiv:2601.22661.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links
A source-named dated measurement, never combined with another source.
Source: cited_works
Reference resolution
24 of 24 outbound references displayed
- verified exact0
- verified fuzzy0
- unresolved24
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 64fed19a-4d58-49a6-867f-8977988efecd · outbound
This paper cites TTS-1 Technical Report.
Evaluating and Rewarding LALMs for Expressive Role-Play TTS via Mean Continuation Log-Probability TTS-1 Technical Report
Reference 1
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T06:36:31.523597Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 187d4839-c0fb-4345-b711-fafa91a4708a · outbound
This paper cites CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models.
Evaluating and Rewarding LALMs for Expressive Role-Play TTS via Mean Continuation Log-Probability CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models
Reference 5
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T06:36:32.017309Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5669cd96-e95c-4b59-a58c-f0a29b7d705e · outbound
This paper cites Differentiable Reward Optimization for LLM based TTS system.
Evaluating and Rewarding LALMs for Expressive Role-Play TTS via Mean Continuation Log-Probability Differentiable Reward Optimization for LLM based TTS system
Reference 7
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T06:36:32.240560Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 38d72d7a-b07b-4921-b6cc-eb25bd3d5477 · outbound
This paper cites Prompttts: Controllable text-to-speech with text descriptions.
Evaluating and Rewarding LALMs for Expressive Role-Play TTS via Mean Continuation Log-Probability Prompttts: Controllable text-to-speech with text descriptions
Reference 8
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T06:36:32.326580Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 87f751dc-da9c-46cb-9382-42db3a39acff · outbound
This paper cites Qwen3-TTS Technical Report.
Evaluating and Rewarding LALMs for Expressive Role-Play TTS via Mean Continuation Log-Probability Qwen3-TTS Technical Report
Reference 9
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T06:36:32.393867Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7a67601c-c652-4d21-ab6c-cf428f010520 · outbound
This paper cites Speechrole: A large-scale dataset and benchmark for evaluating speech role-playing agents.
Evaluating and Rewarding LALMs for Expressive Role-Play TTS via Mean Continuation Log-Probability Speechrole: A large-scale dataset and benchmark for evaluating speech role-playing agents
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T06:36:32.453974Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 41bc5a40-4de2-4557-a59c-22cda5da7818 · outbound
This paper cites PromptTTS 2: Describing and Generating Voices with Text Prompt.
Evaluating and Rewarding LALMs for Expressive Role-Play TTS via Mean Continuation Log-Probability PromptTTS 2: Describing and Generating Voices with Text Prompt
Reference 11
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T06:36:32.513360Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7f05627a-4879-44d3-83b5-c725b6760a3d · outbound
This paper cites AudioRole: An Audio Dataset for Character Role-Playing in Large Language Models.
Evaluating and Rewarding LALMs for Expressive Role-Play TTS via Mean Continuation Log-Probability AudioRole: An Audio Dataset for Character Role-Playing in Large Language Models
Reference 12
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T06:36:32.600302Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8c2c6535-9aa0-4a03-8ede-cde0e03d33f1 · outbound
This paper cites Reinforcement Learning for Emotional Text-to-Speech Synthesis with Improved Emotion Discriminability.
Evaluating and Rewarding LALMs for Expressive Role-Play TTS via Mean Continuation Log-Probability Reinforcement Learning for Emotional Text-to-Speech Synthesis with Improved Emotion Discriminability
Reference 13
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T06:36:32.668134Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 15b907bd-a0de-4e76-a710-3cdf41b45d8d · outbound
This paper cites Hybrid transform- ers for music source separation.
Evaluating and Rewarding LALMs for Expressive Role-Play TTS via Mean Continuation Log-Probability Hybrid transform- ers for music source separation
Reference 15
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T06:36:32.814773Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 924b277b-9b4b-4a20-8414-1fb637b15a98 · outbound
This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.
Evaluating and Rewarding LALMs for Expressive Role-Play TTS via Mean Continuation Log-Probability DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
Reference 16
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T06:36:32.939198Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 75574330-b66f-4077-b7de-0e26c3cb36da · outbound
This paper cites Speech-drame: A frame- work for human-aligned benchmarks in speech role-play.
Evaluating and Rewarding LALMs for Expressive Role-Play TTS via Mean Continuation Log-Probability Speech-drame: A frame- work for human-aligned benchmarks in speech role-play
Reference 17
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T06:36:33.055238Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 790dd417-4554-47a2-8075-15009e99c47e · outbound
This paper cites Rrpo: Robust reward policy optimization for llm-based emotional tts.arXiv preprint arXiv:2512.04552,.
Evaluating and Rewarding LALMs for Expressive Role-Play TTS via Mean Continuation Log-Probability Rrpo: Robust reward policy optimization for llm-based emotional tts.arXiv preprint arXiv:2512.04552,
Reference 19
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T06:36:33.244749Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2c2610fc-6b84-4fc3-a315-671642161b80 · outbound
This paper cites Step-Audio 2 Technical Report.
Evaluating and Rewarding LALMs for Expressive Role-Play TTS via Mean Continuation Log-Probability Step-Audio 2 Technical Report
Reference 20
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T06:36:33.364746Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 351a3903-35eb-426c-973b-757458d38f9f · outbound
This paper cites Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis.
Evaluating and Rewarding LALMs for Expressive Role-Play TTS via Mean Continuation Log-Probability Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis
Reference 21
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T06:36:33.475394Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0a09d3b0-8e4b-48a4-8c89-aa5866e2b82a · outbound
This paper cites Wenetspeech: A 10000+ hours multi-domain mandarin corpus for speech recognition.
Evaluating and Rewarding LALMs for Expressive Role-Play TTS via Mean Continuation Log-Probability Wenetspeech: A 10000+ hours multi-domain mandarin corpus for speech recognition
Reference 22
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T06:36:33.674758Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5f075c68-f66a-4551-bea9-ff9ec60c0b40 · outbound
This paper cites Mimo-audio: Audio language models are few-shot learners.arXiv preprint arXiv:2512.23808, 2025a.
Evaluating and Rewarding LALMs for Expressive Role-Play TTS via Mean Continuation Log-Probability Mimo-audio: Audio language models are few-shot learners.arXiv preprint arXiv:2512.23808, 2025a
Reference 23
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T06:36:33.830007Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation dde0822b-38ab-4c94-9f46-3701b307eb16 · outbound
This paper cites drama_name.
Evaluating and Rewarding LALMs for Expressive Role-Play TTS via Mean Continuation Log-Probability drama_name
Reference 24
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T06:36:33.887146Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c7d6f970-913a-41b2-9fca-53b48d88bd28 · outbound
This paper cites Ov-instructtts: Towards open-vocabulary instruct text-to-speech.arXiv preprint arXiv:2601.01459,.
Evaluating and Rewarding LALMs for Expressive Role-Play TTS via Mean Continuation Log-Probability Ov-instructtts: Towards open-vocabulary instruct text-to-speech.arXiv preprint arXiv:2601.01459,
Reference 2021
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T06:36:32.729198Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 78d2d6a9-4041-44da-9dfb-4a344fb57ac6 · outbound
This paper cites Audiobox: Unified Audio Generation with Natural Language Prompts.
Evaluating and Rewarding LALMs for Expressive Role-Play TTS via Mean Continuation Log-Probability Audiobox: Unified Audio Generation with Natural Language Prompts
Reference 2022
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T06:36:33.115934Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 69053db0-0cbd-4e31-9b02-cea958287e84 · outbound
This paper cites Flexivoice: Enabling flexible style control in zero- shot tts with natural language instructions.arXiv preprint arXiv:2601.04656,.
Evaluating and Rewarding LALMs for Expressive Role-Play TTS via Mean Continuation Log-Probability Flexivoice: Enabling flexible style control in zero- shot tts with natural language instructions.arXiv preprint arXiv:2601.04656,
Reference 2023
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T06:36:31.747286Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 013a0647-317f-4345-9b7f-f67b38f00c34 · outbound
This paper cites CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training.
Evaluating and Rewarding LALMs for Expressive Role-Play TTS via Mean Continuation Log-Probability CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training
Reference 2024
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T06:36:32.118897Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 11aa3de7-df12-4be4-9338-347592404301 · outbound
This paper cites Qwen3-VL Technical Report.
Evaluating and Rewarding LALMs for Expressive Role-Play TTS via Mean Continuation Log-Probability Qwen3-VL Technical Report
Reference 2025
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T06:36:31.646881Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 21fdd2b4-abf1-44b8-a7b8-baf9025ebf8e · outbound
This paper cites VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizers.
Evaluating and Rewarding LALMs for Expressive Role-Play TTS via Mean Continuation Log-Probability VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizers
Reference 2026
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T06:36:31.871558Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Pith citing papers
No inbound Pith citation observations are available.