mlsanityData to 14 Oct 2026

WenetSpeech4TTS: A 12,800-hour Mandarin TTS Corpus for Large Speech Generation Model Benchmark

arXiv 2406.05763 ↗First posted 9 Jun 2024eess.AScited by 40

Not on the map. Why?

Abstract (arXiv)

With the development of large text-to-speech (TTS) models and scale-up of the training data, state-of-the-art TTS systems have achieved impressive performance. In this paper, we present WenetSpeech4TTS, a multi-domain Mandarin corpus derived from the open-sourced WenetSpeech dataset. Tailored for the text-to-speech tasks, we refined WenetSpeech by adjusting segment boundaries, enhancing the audio quality, and eliminating speaker mixing within each segment. Following a more accurate transcription process and quality-based data filtering process, the obtained WenetSpeech4TTS corpus contains 12,800 hours of paired audio-text data. Furthermore, we have created subsets of varying sizes, categorized by segment quality scores to allow for TTS model training and fine-tuning. VALL-E and NaturalSpeech 2 systems are trained and fine-tuned on these subsets to validate the usability of WenetSpeech4TTS, establishing baselines on benchmark for fair comparison of TTS systems. The corpus and corresponding benchmarks are publicly available on huggingface.

Key facts. Cited by 40 papers in the map (data through 14 Oct 2026). First posted on arXiv 9 Jun 2024.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 7; 2025: 23; 2026: 10.

40 papers.

Sort:

By area:

  1. 2024F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matchingcited by 361
  2. 2025Kimi-Audio Technical Reportcited by 222
  3. 2024Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generationcited by 204
  4. 2025Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokenscited by 113
  5. 2025Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesiscited by 70
  6. 2025VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Modelcited by 31
  7. 2025F5R-TTS: Improving Flow-Matching based Text-to-Speech with Group Relative Policy Optimizationcited by 24
  8. 2025Emilia: A Large-Scale, Extensive, Multilingual, and Diverse Dataset for Speech Generationcited by 20
  9. 2025ContextASR-Bench: A Massive Contextual Speech Recognition Benchmarkcited by 15
  10. 2024TouchTTS: An Embarrassingly Simple TTS Framework that Everyone Can Touchcited by 10
  11. 2025Pseudo-Autoregressive Neural Codec Language Models for Efficient Zero-Shot Text-to-Speech Synthesiscited by 10
  12. 2025WenetSpeech-Chuan: A Large-Scale Sichuanese Corpus with Rich Annotation for Dialectal Speech Processingcited by 8
28 more
  1. 2025UniSS: Unified Expressive Speech-to-Speech Translation with Your Voicecited by 7
  2. 2025Step-Audio-EditX Technical Reportcited by 7
  3. 2025DialogueAgents: A Hybrid Agent-Based Speech Synthesis Framework for Multi-Party Dialoguecited by 6
  4. 2026FlowTTS-GRPO: Online Reinforcement Learning with Multi-Objective Reward Optimization for Flow-Matching Based Text-to-Speechcited by 5
  5. 2024TouchASP: Elastic Automatic Speech Perception that Everyone Can Touchcited by 3
  6. 2025VoiceCraft-X: Unifying Multilingual, Voice-Cloning Speech Synthesis and Speech Editingcited by 3
  7. 2024The NPU-HWC System for the ISCSLP 2024 Inspirational and Convincing Audio Generation Challengecited by 2
  8. 2025UniTTS: An end-to-end TTS system without decoupling of acoustic and semantic informationcited by 2
  9. 2025TELEVAL: A Benchmark Designed for Spoken Language Models in Chinese Interactive Scenarioscited by 2
  10. 2025Mitigating Hallucinations in LM-Based TTS Models via Distribution Alignment Using GFlowNetscited by 2
  11. 2024Flow-TSVAD: Target-Speaker Voice Activity Detection via Latent Flow Matchingcited by 1
  12. 2024The ISCSLP 2024 Conversational Voice Clone (CoVoC) Challenge: Tasks, Results and Findingscited by 1
  13. 2025MFLA: Monotonic Finite Look-ahead Attention for Streaming Speech Recognitioncited by 1
  14. 2025Eliminating stability hallucinations in llm-based tts models via attention guidancecited by 1
  15. 2026A Unified Spoken Language Model with Injected Emotional-Attribution Thinking for Human-like Interactioncited by 1
  16. 2026Eureka-Audio: Triggering Audio Intelligence in Compact Language Modelscited by 1
  17. 2026Efficient Training for Cross-lingual Speech Language Modelscited by 1
  18. 2026VITA-QinYu: Expressive Spoken Language Model for Role-Playing and Singingcited by 1
  19. 2026FlashTTS: Fast Streaming TTS with MTP Acceleration and X-pred Mean Flow Distillationcited by 1
  20. 2025Capybara-OMNI: An Efficient Paradigm for Building Omni-Modal Language Modelscited by 0
  21. 2025Teochew-Wild: The First In-the-wild Teochew Dataset with Orthographic Annotationscited by 0
  22. 2025Voice Adaptation for Swiss Germancited by 0
  23. 2025Balalaika: Data-Centric, Prosody-Aware Annotation Pipeline for Russian Speechcited by 0
  24. 2025Adaptive Duration Model for Text Speech Alignmentcited by 0
  25. 2026SB-RF: Schr"odinger Bridge Rectified Flow for One-Step Robust Speech Enhancementcited by 0
  26. 2026Phoenix TTS: High-Fidelity Synthesis and Voice Conversion via Flow-Matching-Driven Speech Tokenizationcited by 0
  27. 2026Scalable Direction-Following TTS via Voice Impression-Guided Pseudo Triplet Constructioncited by 0
  28. 2026ELARSpeech: A 30K-Hour Dataset Across 675 Underrepresented Languages for Long-Tail Multilingual Speech Technologiescited by 0