mlsanityData to 7 Oct 2026

UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022

arXiv 2204.02152 ↗First posted 5 Apr 2022cs.SD eess.AScited by 381

Not on the map. Why?

Cited by 71 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We present the UTokyo-SaruLab mean opinion score (MOS) prediction system submitted to VoiceMOS Challenge 2022. The challenge is to predict the MOS values of speech samples collected from previous Blizzard Challenges and Voice Conversion Challenges for two tracks: a main track for in-domain prediction and an out-of-domain (OOD) track for which there is less labeled data from different listening tests. Our system is based on ensemble learning of strong and weak learners. Strong learners incorporate several improvements to the previous fine-tuning models of self-supervised learning (SSL) models, while weak learners use basic machine-learning methods to predict scores from SSL features. In the Challenge, our system had the highest score on several metrics for both the main and OOD tracks. In addition, we conducted ablation studies to investigate the effectiveness of our proposed methods.

Key facts. Cited by 381 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Apr 2022.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 11; 2024: 58; 2025: 130; 2026: 178.

381 papers.

Sort:

By area:

  1. 2024NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Modelscited by 222
  2. 2024XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Modelcited by 174
  3. 2024LLaMA-Omni: Seamless Speech Interaction with Large Language Modelscited by 169
  4. 2023Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesiscited by 150
  5. 2024WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modelingcited by 124
  6. 2024The T05 System for The VoiceMOS Challenge 2024: Transfer Learning from Deep Image Classifier to Naturalness MOS Prediction of High-Quality Synthetic Speechcited by 78
  7. 2024Addressing Representation Collapse in Vector Quantized Models with One Linear Layercited by 77
  8. 2025LLaMA-Omni2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesiscited by 75
  9. 2024Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Modelcited by 70
  10. 2025Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesiscited by 69
  11. 2025Baichuan-Audio: A Unified Framework for End-to-End Speech Interactioncited by 68
  12. 2025DiTAR: Diffusion Transformer Autoregressive Modeling for Speech Generationcited by 56
38 more
  1. 2024Multimodal Latent Language Modeling with Next-Token Diffusioncited by 47
  2. 2025Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Surveycited by 38
  3. 2023HierSpeech++: Bridging the Gap between Semantic and Acoustic Representation of Speech by Hierarchical Variational Inference for Zero-shot Speech Synthesiscited by 35
  4. 2025EmoVoice: LLM-based Emotional Text-To-Speech Model with Freestyle Text Promptingcited by 33
  5. 2024DASB - Discrete Audio and Speech Benchmarkcited by 32
  6. 2025SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Modelcited by 32
  7. 2025ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matchingcited by 30
  8. 2025URO-Bench: Towards Comprehensive Evaluation for End-to-End Spoken Dialogue Modelscited by 29
  9. 2025VibeVoice Technical Reportcited by 28
  10. 2024RALL-E: Robust Codec Language Modeling with Chain-of-Thought Prompting for Text-to-Speech Synthesiscited by 26
  11. 2023The Singing Voice Conversion Challenge 2023cited by 25
  12. 2025SALMONN-omni: A Standalone Speech LLM without Codec Injection for Full-duplex Conversationcited by 25
  13. 2024How Should We Extract Discrete Audio Tokens from Self-Supervised Models?cited by 24
  14. 2024EmoSphere-TTS: Emotional Style and Intensity Modeling via Spherical Emotion Vector for Controllable Emotional Text-to-Speechcited by 23
  15. 2024ESPnet-SPK: full pipeline speaker embedding toolkit with reproducible recipes, self-supervised front-ends, and off-the-shelf modelscited by 22
  16. 2024FlashSpeech: Efficient Zero-Shot Speech Synthesiscited by 22
  17. 2024SpoofCeleb: Speech Deepfake Detection and SASV In The Wildcited by 22
  18. 2024Towards Controllable Speech Synthesis in the Era of Large Language Models: A Systematic Surveycited by 22
  19. 2026OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Modelscited by 22
  20. 2024Preference Alignment Improves Language Model-Based TTScited by 21
  21. 2024DFADD: The Diffusion and Flow-Matching Based Audio Deepfake Datasetcited by 20
  22. 2024SpeechPrune: Context-aware Token Pruning for Speech Information Retrievalcited by 20
  23. 2025AudioJudge: Understanding What Works in Large Audio Model Based Speech Evaluationcited by 20
  24. 2022SpeechLMScore: Evaluating speech generation using speech language modelcited by 19
  25. 2024Sylber: Syllabic Embedding Representation of Speech from Raw Audiocited by 19
  26. 2025NExT-OMNI: Towards Any-to-Any Omnimodal Foundation Models with Discrete Flow Matchingcited by 19
  27. 2024Coding Speech through Vocal Tract Kinematicscited by 18
  28. 2025FocalCodec: Low-Bitrate Speech Coding via Focal Modulation Networkscited by 18
  29. 2025Fun-Audio-Chat Technical Reportcited by 17
  30. 2024IntrinsicVoice: Empowering LLMs with Intrinsic Real-time Voice Interaction Abilitiescited by 16
  31. 2025VocalNet: Speech LLM with Multi-Token Prediction for Faster and High-Quality Generationcited by 16
  32. 2025TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modelingcited by 15
  33. 2025VocalBench: Benchmarking the Vocal Conversational Abilities for Speech Interaction Modelscited by 15
  34. 2025SpeechJudge: Towards Human-Level Judgment for Speech Naturalnesscited by 15
  35. 2024TTSDS -- Text-to-Speech Distribution Scorecited by 14
  36. 2024StableVC: Style Controllable Zero-Shot Voice Conversion with Conditional Flow Matchingcited by 14
  37. 2025NVSpeech: An Integrated and Scalable Pipeline for Human-Like Speech Modeling with Paralinguistic Vocalizationscited by 14
  38. 2024Enabling Auditory Large Language Models for Automatic Speech Quality Evaluationcited by 13

50 most cited of 381 All 381 (JSON)