mlsanityData to 7 Oct 2026

NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced Datasets

arXiv 2104.09494 ↗First posted 19 Apr 2021eess.AS cs.AI cs.LGcited by 189

Not on the map. Why?

Cited by 22 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

In this paper, we present an update to the NISQA speech quality prediction model that is focused on distortions that occur in communication networks. In contrast to the previous version, the model is trained end-to-end and the time-dependency modelling and time-pooling is achieved through a Self-Attention mechanism. Besides overall speech quality, the model also predicts the four speech quality dimensions Noisiness, Coloration, Discontinuity, and Loudness, and in this way gives more insight into the cause of a quality degradation. Furthermore, new datasets with over 13,000 speech files were created for training and validation of the model. The model was finally tested on a new, live-talking test dataset that contains recordings of real telephone calls. Overall, NISQA was trained and evaluated on 81 datasets from different sources and showed to provide reliable predictions also for unknown speech samples. The code, model weights, and datasets are open-sourced.

Key facts. Cited by 189 papers in the map (data through 7 Oct 2026). Builds on 8 of its 37 references that are in the map. First posted on arXiv 19 Apr 2021.

Builds on

8 of 37 references.

References · 8

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Testing Framework, and Challenge Resultscited by 128
  3. 2020ViSQOL v3: An Open Source Production Ready Objective Speech and Audio Metriccited by 76
  4. 2018Quality-Net: An End-to-End Non-intrusive Speech Quality Assessment Model based on BLSTMcited by 36
  5. 2020An Open source Implementation of ITU-T Recommendation P.808 with Validationcited by 27
  6. 2020SESQA: semi-supervised learning for speech quality assessmentcited by 13
  7. 2019Non-intrusive speech quality assessment using neural networkscited by 11
  8. 2020A Pyramid Recurrent Network for Predicting Crowdsourced Speech-Quality Ratings of Real-World Signalscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 9; 2023: 11; 2024: 22; 2025: 71; 2026: 74.

189 papers.

Sort:

By area:

  1. 2024Recent Advances in Speech Language Models: A Surveycited by 85
  2. 2025VISTA: A Test-Time Self-Improving Video Generation Agentcited by 26
  3. 2025Audio Large Language Models Can Be Descriptive Speech Quality Evaluatorscited by 25
  4. 2025AnyEnhance: A Unified Generative Model with Prompt-Guidance and Self-Critic for Voice Enhancementcited by 23
  5. 2024Towards Controllable Speech Synthesis in the Era of Large Language Models: A Systematic Surveycited by 22
  6. 2025VABench: A Comprehensive Benchmark for Audio-Video Generationcited by 22
  7. 2025AudioJudge: Understanding What Works in Large Audio Model Based Speech Evaluationcited by 20
  8. 2025T2AV-Compass: Towards Unified Evaluation for Text-to-Audio-Video Generationcited by 19
  9. 2024PolyGlotFake: A Novel Multilingual and Multimodal DeepFake Datasetcited by 16
  10. 2024Enabling Auditory Large Language Models for Automatic Speech Quality Evaluationcited by 13
  11. 2024Convert and Speak: Zero-shot Accent Conversion with Minimum Supervisioncited by 11
  12. 2025Evaluating Robustness of Large Audio Language Models to Audio Injection: An Empirical Studycited by 11
38 more
  1. 2022Self-Supervised Learning for Speech Enhancement through Synthesiscited by 10
  2. 2025EchoMind: An Interrelated Multi-level Benchmark for Evaluating Empathetic Speech Language Modelscited by 10
  3. 2023Fake the Real: Backdoor Attack on Deep Speech Classification via Voice Conversioncited by 9
  4. 2024Noise-robust Speech Separation with Fast Generative Correctioncited by 9
  5. 2025SoloSpeech: Enhancing Intelligibility and Quality in Target Speech Extraction through a Cascaded Generative Pipelinecited by 9
  6. 2023Perceive and predict: self-supervised speech representation based loss functions for speech enhancementcited by 8
  7. 2024Diffusion-based Generative Modeling with Discriminative Guidance for Streamable Speech Enhancementcited by 8
  8. 2024SLIM: Style-Linguistics Mismatch Model for Generalized Audio Deepfake Detectioncited by 8
  9. 2024High-Resolution Speech Restoration with Latent Diffusion Modelcited by 8
  10. 2021InQSS: a speech intelligibility and quality assessment model using a multi-task learning networkcited by 7
  11. 2024Self-Supervised Speech Quality Estimation and Enhancement Using Only Clean Speechcited by 7
  12. 2024DLPO: Diffusion Model Loss-Guided Reinforcement Learning for Fine-Tuning Text-to-Speech Diffusion Modelscited by 7
  13. 2025Universal Speech Enhancement with Regression and Generative Mambacited by 7
  14. 2025TTSDS2: Resources and Benchmark for Evaluating Human-Quality Text to Speech Systemscited by 7
  15. 2025Multi-Metric Preference Alignment for Generative Speech Restorationcited by 7
  16. 2023Towards General-Purpose Text-Instruction-Guided Voice Conversioncited by 6
  17. 2024Speaking in Wavelet Domain: A Simple and Efficient Approach to Speed up Speech Diffusion Modelcited by 6
  18. 2025Prosody-Adaptable Audio Codecs for Zero-Shot Voice Conversion via In-Context Learningcited by 6
  19. 2025Flex-Judge: Text-Only Reasoning Unleashes Zero-Shot Multimodal Evaluatorscited by 6
  20. 2025MECAT: A Multi-Experts Constructed Benchmark for Fine-Grained Audio Understanding Taskscited by 6
  21. 2026MuQ-Eval: An Open-Source Per-Sample Quality Metric for AI Music Generation Evaluationcited by 6
  22. 2024Learn from Real: Reality Defender's Submission to ASVspoof5 Challengecited by 5
  23. 2025LauraTSE: Target Speaker Extraction using Auto-Regressive Decoder-Only Language Modelscited by 5
  24. 2025SpeechWeave: Diverse Multilingual Synthetic Text & Audio Data Generation Pipeline for Training Text to Speech Modelscited by 5
  25. 2025VoXtream: Full-Stream Text-to-Speech with Extremely Low Latencycited by 5
  26. 2025OASIS: A Multilingual and Multimodal Dataset for Culturally Grounded Spoken Visual QAcited by 5
  27. 2023Conditional Diffusion Model for Target Speaker Extractioncited by 4
  28. 2024SonicSim: A customizable simulation platform for speech processing in moving sound source scenarioscited by 4
  29. 2025AGAV-Rater: Adapting Large Multimodal Model for AI-Generated Audio-Visual Quality Assessmentcited by 4
  30. 2025Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Frameworkcited by 4
  31. 2025A Study of the Scale Invariant Signal to Distortion Ratio in Speech Separation with Noisy Referencescited by 4
  32. 2025VoiceBridge: General Speech Restoration with One-step Latent Bridge Modelscited by 4
  33. 2025From Scores to Preferences: Redefining MOS Benchmarking for Speech Quality Reward Modelingcited by 4
  34. 2025UniSE: A Unified Framework for Decoder-Only Autoregressive LM-Based Speech Enhancementcited by 4
  35. 2025SpeechQualityLLM: LLM-Based Multimodal Assessment of Speech Qualitycited by 4
  36. 2025TriDF: Evaluating Perception, Detection, and Hallucination for Interpretable DeepFake Detectioncited by 4
  37. 2025Real-Time Streamable Generative Speech Restoration with Flow Matchingcited by 4
  38. 2026TVTSyn: Content-Synchronous Time-Varying Timbre for Streaming Voice Conversion and Anonymizationcited by 4

50 most cited of 189 All 189 (JSON)