mlsanityData to 7 Oct 2026

DNSMOS P.835: A Non-Intrusive Perceptual Objective Speech Quality Metric to Evaluate Noise Suppressors

arXiv 2110.01763 ↗First posted 5 Oct 2021eess.AS cs.SDcited by 165

Not on the map. Why?

Cited by 42 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Human subjective evaluation is the gold standard to evaluate speech quality optimized for human perception. Perceptual objective metrics serve as a proxy for subjective scores. We have recently developed a non-intrusive speech quality metric called Deep Noise Suppression Mean Opinion Score (DNSMOS) using the scores from ITU-T Rec. P.808 subjective evaluation. The P.808 scores reflect the overall quality of the audio clip. ITU-T Rec. P.835 subjective evaluation framework gives the standalone quality scores of speech and background noise in addition to the overall quality. In this work, we train an objective metric based on P.835 human ratings that outputs 3 scores: i) speech quality (SIG), ii) background noise quality (BAK), and iii) the overall quality (OVRL) of the audio. The developed metric is highly correlated with human ratings, with a Pearson's Correlation Coefficient (PCC)=0.94 for SIG and PCC=0.98 for BAK and OVRL. This is the first non-intrusive P.835 predictor we are aware of. DNSMOS P.835 is made publicly available as an Azure service.

Key facts. Cited by 165 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Oct 2021.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 11; 2023: 15; 2024: 20; 2025: 63; 2026: 55.

165 papers.

Sort:

By area:

  1. 2024CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Modelscited by 282
  2. 2024Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generationcited by 200
  3. 2022Speech Enhancement and Dereverberation with Diffusion-based Generative Modelscited by 195
  4. 2025CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-trainingcited by 142
  5. 2022HiFi++: a Unified Framework for Bandwidth Extension and Speech Enhancementcited by 49
  6. 2022Diffusion-based Generative Speech Source Separationcited by 41
  7. 2024DASB - Discrete Audio and Speech Benchmarkcited by 32
  8. 2024How Should We Extract Discrete Audio Tokens from Self-Supervised Models?cited by 24
  9. 2022DeepFilterNet2: Towards Real-Time Speech Enhancement on Embedded Devices for Full-Band Audiocited by 23
  10. 2025AnyEnhance: A Unified Generative Model with Prompt-Guidance and Self-Critic for Voice Enhancementcited by 23
  11. 2022CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancementcited by 22
  12. 2025FlowSE: Flow Matching-based Speech Enhancementcited by 20
38 more
  1. 2024Laugh Now Cry Later: Controlling Time-Varying Emotional States of Flow-Matching-Based Zero-Shot Text-to-Speechcited by 19
  2. 2025Emilia: A Large-Scale, Extensive, Multilingual, and Diverse Dataset for Speech Generationcited by 19
  3. 2021MetricGAN-U: Unsupervised speech enhancement/ dereverberation based only on noisy/ reverberated speechcited by 18
  4. 2025FocalCodec: Low-Bitrate Speech Coding via Focal Modulation Networkscited by 18
  5. 2025Differentiable Reward Optimization for LLM based TTS systemcited by 15
  6. 2025Ming-UniAudio: Speech LLM for Joint Understanding, Generation and Editing with Unified Representationcited by 15
  7. 2025SpeechJudge: Towards Human-Level Judgment for Speech Naturalnesscited by 15
  8. 2022Diffiner: A Versatile Diffusion-based Generative Refiner for Speech Enhancementcited by 14
  9. 2025ContextASR-Bench: A Massive Contextual Speech Recognition Benchmarkcited by 14
  10. 2023Unsupervised speech enhancement with diffusion-based generative modelscited by 12
  11. 2024The PESQetarian: On the Relevance of Goodhart's Law for Speech Enhancementcited by 12
  12. 2022Self-Supervised Learning for Speech Enhancement through Synthesiscited by 10
  13. 2023I3D: Transformer architectures with input-dependent dynamic depth for speech recognitioncited by 10
  14. 2023Multi-channel Speech Separation Using Spatially Selective Deep Non-linear Filterscited by 10
  15. 2024TSELM: Target Speaker Extraction using Discrete Tokens and Language Modelscited by 10
  16. 2024TouchTTS: An Embarrassingly Simple TTS Framework that Everyone Can Touchcited by 10
  17. 2025VoiceCraft-Dub: Automated Video Dubbing with Neural Codec Language Modelscited by 10
  18. 2026MOSS-TTS Technical Reportcited by 10
  19. 2025OmniTalker: One-shot Real-time Text-Driven Talking Audio-Video Generation With Multimodal Style Mimickingcited by 9
  20. 2025SoloSpeech: Enhancing Intelligibility and Quality in Target Speech Extraction through a Cascaded Generative Pipelinecited by 9
  21. 2025FLM-Audio: Natural Monologues Improves Native Full-Duplex Chatbots via Dual Trainingcited by 9
  22. 2023DDTSE: Discriminative Diffusion Model for Target Speech Extractioncited by 8
  23. 2024Diffusion-based Generative Modeling with Discriminative Guidance for Streamable Speech Enhancementcited by 8
  24. 2024Towards Unifying Evaluation of Counterfactual Explanations: Leveraging Large Language Models for Human-Centric Assessmentscited by 8
  25. 2025Source Separation by Flow Matchingcited by 8
  26. 2025FocalCodec-Stream: Streaming Low-Bitrate Speech Coding via Causal Distillationcited by 8
  27. 2023EMOCONV-DIFF: Diffusion-based Speech Emotion Conversion for Non-parallel and In-the-wild Datacited by 7
  28. 2023Diffusion-based speech enhancement with a weighted generative-supervised learning losscited by 7
  29. 2024FINALLY: fast and universal speech enhancement with studio-like qualitycited by 7
  30. 2025ESPnet-SDS: Unified Toolkit and Demo for Spoken Dialogue Systemscited by 7
  31. 2025Universal Speech Enhancement with Regression and Generative Mambacited by 7
  32. 2025TTSDS2: Resources and Benchmark for Evaluating Human-Quality Text to Speech Systemscited by 7
  33. 2025ZipVoice-Dialog: Non-Autoregressive Spoken Dialogue Generation with Flow Matchingcited by 7
  34. 2025Multi-Metric Preference Alignment for Generative Speech Restorationcited by 7
  35. 2023Rethinking complex-valued deep neural networks for monaural speech enhancementcited by 6
  36. 2025DiTSE: High-Fidelity Generative Speech Enhancement via Latent Diffusion Transformerscited by 6
  37. 2025FlowTSE: Target Speaker Extraction with Flow Matchingcited by 6
  38. 2025MECAT: A Multi-Experts Constructed Benchmark for Fine-Grained Audio Understanding Taskscited by 6

50 most cited of 165 All 165 (JSON)