mlsanityData to 7 Oct 2026

InQSS: a speech intelligibility and quality assessment model using a multi-task learning network

arXiv 2111.02585 ↗First posted 4 Nov 2021cs.SD cs.LG eess.AScited by 7

Not on the map. Why?

Abstract (arXiv)

Speech intelligibility and quality assessment models are essential tools for researchers to evaluate and improve speech processing models. However, only a few studies have investigated multi-task models for intelligibility and quality assessment due to the limitations of available data. In this study, we released TMHINT-QI, the first Chinese speech dataset that records the quality and intelligibility scores of clean, noisy, and enhanced utterances. Then, we propose InQSS, a non-intrusive multi-task learning framework for intelligibility and quality assessment. We evaluated the InQSS on both the training-from-scratch and the pretrained models. The experimental results confirm the effectiveness of the InQSS framework. In addition, the resulting model can predict not only the intelligibility scores but also the quality scores of a speech signal.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 19 of its 41 references that are in the map. First posted on arXiv 4 Nov 2021.

Builds on

19 of 41 references.

References · 19

  1. 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,486
  2. 2020DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressorscited by 235
  3. 2021NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced Datasetscited by 189
  4. 2020The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Testing Framework, and Challenge Resultscited by 128
  5. 2019MOSNet: Deep Learning based Objective Assessment for Voice Conversioncited by 126
  6. 2021Generalization Ability of MOS Prediction Networkscited by 69
  7. 2018Kymatio: Scattering Transforms in Pythoncited by 54
  8. 2013Deep Scattering Spectrumcited by 52
  9. 2019A scalable noisy speech dataset and online subjective test frameworkcited by 47
  10. 2020Jointly Fine-Tuning "BERT-like" Self Supervised Models to Improve Multimodal Speech Emotion Recognitioncited by 38
  11. 2021MBNet: MOS Prediction for Synthesized Speech with Mean-Bias Networkcited by 37
  12. 2018Quality-Net: An End-to-End Non-intrusive Speech Quality Assessment Model based on BLSTMcited by 36
7 more
  1. 2019T-GSA: Transformer with Gaussian-weighted self-attention for speech enhancementcited by 34
  2. 2017Raw Waveform-based Speech Enhancement by Fully Convolutional Networkscited by 24
  3. 2021Utilizing Self-supervised Representations for MOS Predictioncited by 20
  4. 2021NORESQA: A Framework for Speech Quality Assessment using Non-Matching Referencescited by 12
  5. 2020Neural MOS Prediction for Synthesized Speech Using Multi-Task Learning With Spoofing Detection and Spoofing Type Classificationcited by 7
  6. 2017An instrumental intelligibility metric based on information theorycited by 5
  7. 2020Noise Tokens: Learning Neural Noise Templates for Environment-Aware Speech Enhancementcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 2; 2024: 0; 2025: 3; 2026: 1.

7 papers.

  1. 2025AudioJudge: Understanding What Works in Large Audio Model Based Speech Evaluationcited by 20
  2. 2023MultiPA: A Multi-task Speech Pronunciation Assessment Model for Open Response Scenarioscited by 7
  3. 2023Fast Word Error Rate Estimation Using Self-Supervised Representations for Speech and Textcited by 4
  4. 2025From Scores to Preferences: Redefining MOS Benchmarking for Speech Quality Reward Modelingcited by 4
  5. 2022BASPRO: a balanced script producer for speech corpus collection based on the genetic algorithmcited by 0
  6. 2025SALF-MOS: Speaker Agnostic Latent Features Downsampled for MOS Predictioncited by 0
  7. 2026CAL-MOS: Bridging Layers with Adapters for Robust MOS Prediction Across Speech Foundation Modelscited by 0