# DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressors

arXiv: https://arxiv.org/abs/2010.15258 · HTML: https://mlsanity.com/paper/2010.15258/

## Key facts

- Cited by 241 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Oct 2020.

## Built on by (most cited first, 30 of 241)

- [AudioPaLM: A Large Language Model That Can Speak and Listen](https://mlsanity.com/paper/2306.12925/) (2023)
- [Speech Enhancement and Dereverberation with Diffusion-based Generative Models](https://mlsanity.com/paper/2208.05830/) (2022)
- [VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2406.05370/) (2024)
- [MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement](https://mlsanity.com/paper/2104.03538/) (2021)
- [SoundStorm: Efficient Parallel Audio Generation](https://mlsanity.com/paper/2305.09636/) (2023)
- [SpeechX: Neural Codec Language Model as a Versatile Speech Transformer](https://mlsanity.com/paper/2308.06873/) (2023)
- [EARS: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberation](https://mlsanity.com/paper/2406.06185/) (2024)
- [HiFi++: a Unified Framework for Bandwidth Extension and Speech Enhancement](https://mlsanity.com/paper/2203.13086/) (2022)
- [Interspeech 2021 Deep Noise Suppression Challenge](https://mlsanity.com/paper/2101.01902/) (2021)
- [Zero-shot Voice Conversion with Diffusion Transformers](https://mlsanity.com/paper/2411.09943/) (2024)
- [MOVA: Towards Scalable and Synchronized Video-Audio Generation](https://mlsanity.com/paper/2602.08794/) (2026)
- [Deep Learning-based Non-Intrusive Multi-Objective Speech Assessment Model with Cross-Domain Features](https://mlsanity.com/paper/2111.02363/) (2021)
- [VABench: A Comprehensive Benchmark for Audio-Video Generation](https://mlsanity.com/paper/2512.09299/) (2025)
- [Unsupervised Speech Enhancement using Dynamical Variational Auto-Encoders](https://mlsanity.com/paper/2106.12271/) (2021)
- [MaskSR: Masked Language Model for Full-band Speech Restoration](https://mlsanity.com/paper/2406.02092/) (2024)
- [CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancement](https://mlsanity.com/paper/2209.11112/) (2022)
- [SimpleSpeech: Towards Simple and Efficient Text-to-Speech with Scalar Latent Transformer Diffusion Models](https://mlsanity.com/paper/2406.02328/) (2024)
- [SpoofCeleb: Speech Deepfake Detection and SASV In The Wild](https://mlsanity.com/paper/2409.17285/) (2024)
- [AudioJudge: Understanding What Works in Large Audio Model Based Speech Evaluation](https://mlsanity.com/paper/2507.12705/) (2025)
- [SpeechLMScore: Evaluating speech generation using speech language model](https://mlsanity.com/paper/2212.04559/) (2022)
- [MetricGAN-U: Unsupervised speech enhancement/ dereverberation based only on noisy/ reverberated speech](https://mlsanity.com/paper/2110.05866/) (2021)
- [SimpleSpeech 2: Towards Simple and Efficient Text-to-Speech with Flow-based Scalar Latent Transformer Diffusion Models](https://mlsanity.com/paper/2408.13893/) (2024)
- [InstructTTSEval: Benchmarking Complex Natural-Language Instruction Following in Text-to-Speech Systems](https://mlsanity.com/paper/2506.16381/) (2025)
- [Unsupervised Noise Adaptive Speech Enhancement by Discriminator-Constrained Optimal Transport](https://mlsanity.com/paper/2111.06316/) (2021)
- [TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling](https://mlsanity.com/paper/2504.07053/) (2025)
- [StreamVC: Real-Time Low-Latency Voice Conversion](https://mlsanity.com/paper/2401.03078/) (2024)
- [ContextASR-Bench: A Massive Contextual Speech Recognition Benchmark](https://mlsanity.com/paper/2507.05727/) (2025)
- [Self-Supervised Visual Acoustic Matching](https://mlsanity.com/paper/2307.15064/) (2023)
- [NonverbalTTS: A Public English Corpus of Text-Aligned Nonverbal Vocalizations with Emotion Annotations for Text-to-Speech](https://mlsanity.com/paper/2507.13155/) (2025)
- [Unsupervised speech enhancement with diffusion-based generative models](https://mlsanity.com/paper/2309.10450/) (2023)

## 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. The conventional and widely used metrics require a reference clean speech signal, which is unavailable in real recordings. The no-reference approaches correlate poorly with human ratings and are not widely adopted in the research community. One of the biggest use cases of these perceptual objective metrics is to evaluate noise suppression algorithms. This paper introduces a multi-stage self-teaching based perceptual objective metric that is designed to evaluate noise suppressors. The proposed method generalizes well in challenging test conditions with a high correlation to human ratings.