Speech Quality Assessment

Follow this topic Ask about this topic

Speech quality assessment studies how listeners perceive speech and how reliably systems can measure qualities such as naturalness, intelligibility, pronunciation, prosody, and speaker similarity. Methods range from human mean-opinion and pairwise-preference ratings to reference-based metrics and non-intrusive predictors built from acoustic features, self-supervised speech representations, or audio-language models. Researchers also develop targeted assessments for settings such as speech enhancement, text-to-speech, accents, and pathological speech, often using benchmarks that test multiple dimensions and domains. A central challenge is that high metric scores do not always match human judgments or downstream usefulness, especially when systems encounter new speakers, languages, or speaking styles.

Latest papers

69 papers12 papers in the last four weeks, up 33% on the four weeks before. 0.1% of all new papers.

Something from Nothing: Data Augmentation for Robust Severity Level Estimation of Dysarthric Speech
Mar 16, 2026Jaesung Bae, Xiuwen Zheng, Minje Kim +2Speech Quality Assessment Dysarthria Assessment
University of Illinois Urbana-Champaign, IL, USA · Korea Advanced Institute of Science & Technology, KR
PhonemeDF: A Synthetic Speech Dataset for Audio Deepfake Detection and Naturalness Evaluation
Mar 16, 2026Vamshi Nallaguntla, Aishwarya Fursule, Shruti Kshirsagar +1Audio Deepfake Detection Speech Generation Evaluation
Wichita State University, Wichita, Kansas, USA · Institut national de la recherche scientifique (INRS-EMT), Université du Québec, Canada · INRS-UQO Mixed Research Unit on Cybersecurity, Gatineau, Canada
CodecMOS-Accent: A MOS Benchmark of Resynthesized and TTS Speech from Neural Codecs Across English Accents
Mar 15, 2026Wen-Chin Huang, Nicholas Sanders, Erica CooperTTS Evaluation Speech Quality Assessment
Nagoya University, Japan · University of Edinburgh, United Kingdom · National Institute Of Information And Communications Technology, Japan
AnimeScore: A Preference-Based Dataset and Framework for Evaluating Anime-Like Speech Style
Mar 12, 2026Joonyong Park, Jerry LiAutomated Evaluation Speech Quality Assessment
Spellbrush, USA
Calibration-Reasoning Framework for Descriptive Speech Quality Assessment
Mar 10, 2026Elizaveta Kostenok, Mathieu Salzmann, Milos CernakSpeech Quality Assessment Audio-Language Models
EPFL, Lausanne, Switzerland · Logitech, Lausanne, Switzerland
PathBench: Speech Intelligibility Benchmark for Automatic Pathological Speech Assessment
Mar 9, 2026Bence Mark Halpern, Thomas Tienkamp, Defne Abur +1Benchmark Design Speech Quality Assessment
1Nagoya University, Japan · Department of Neurology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Germany · University of Groningen, The Netherlands
Rubric-Guided Fine-tuning of SpeechLLMs for Multi-Aspect, Multi-Rater L2 Reading-Speech Assessment
Feb 28, 2026Aditya Kamlesh Parikh, Cristian Tejedor-Garcia, Catia Cucchiarini +1Speech Quality Assessment Speech Language Models
Centre for Language Studies, Radboud University, The Netherlands
Bottleneck Transformer-Based Approach for Improved Automatic STOI Score Prediction
Feb 17, 2026Amartyaveer, Murali Kadambi, Chandra Mohan Sharma +2Speech Quality Assessment Transformer
Spire Lab, Dept of Electrical Engg Indian Institue of Science (IISc) Bengaluru, India · Center for Artificial Intelligence and Robotics (CAIR), DRDO India
SA-SSL-MOS: Self-supervised Learning MOS Prediction with Spectral Augmentation for Generalized Multi-Rate Speech Assessment
Feb 16, 2026Fengyuan Cao, Xinyu Liang, Fredrik Cumlin +4Speech Quality Assessment Self-Supervised Speech Representation Learning
KTH Royal Institute of Technology, Stockholm, Sweden · Google LLC

Mar 16, 2026J/K move · Enter open · S save

Something from Nothing: Data Augmentation for Robust Severity Level Estimation of Dysarthric Speech

Jaesung Bae, Xiuwen Zheng, Minje Kim, Chang D. Yoo+1

University of Illinois Urbana-Champaign, IL, USA · Korea Advanced Institute of Science & Technology, KR

Speech Quality Assessment Dysarthria Assessment Clinical Speech Processing

Open paper AskPDF arXiv

Dysarthric speech quality assessment (DSQA) is critical for clinical diagnostics and inclusive speech technologies. However, subjective evaluation is costly and difficult to scale, and the scarcity of labeled data limits robust objective modeling. To address this, we propose a three-stage framework that leverages unlabeled dysarthric speech and large-scale typical speech datasets to scale training. A teacher model first generates pseudo-labels for unlabeled samples, followed by weakly supervised pretraining using a label-aware contrastive learning strategy that exposes the model to diverse speakers and acoustic conditions. The pretrained model is then fine-tuned for the downstream DSQA task. Experiments on five unseen datasets spanning multiple etiologies and languages demonstrate the robustness of our approach. Our Whisper-based baseline significantly outperforms SOTA DSQA predictors such as SpICE, and the full framework achieves an average SRCC of 0.761 across unseen test datasets.