Self-Supervised Speech Representation Learning

Follow this topic Ask about this topic

Momentum

12 papers in the last four weeks, up 300% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 70

All topics

Mitigating Accent-Language Confusion in Self-Supervised Speech Representations for Language Identification
Oct 7, 2026Minu Kim, Jihwan Lee, David R. Mortensen +1Language Identification Algorithmic Bias
Signal Analysis and Interpretation Lab (SAIL), University of Southern California, USA · Language Technologies Institute, Carnegie Mellon University, USA
Do Speech Representations Preserve Regional Accent Across Read and Spontaneous Speech?
Oct 5, 2026Paula A. Perez-Toro, Tomas Arias-Vergara, Annette Schwarz +4Audio Representation Learning Self-Supervised Speech Representation Learning
Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany. · Leibniz Institute for Educational Trajectories (LIfBi), Bamberg, Germany. · Otto-Friedrich-Universität Bamberg, Bamberg, Germany.
Beyond Decodability: Do Acoustic Factors Drive Predictions in Speech-Based Alzheimer's Assessment?
Oct 1, 2026Serli Kopar, Alkis Koudounas, Roshan P. Rane +3Audio Representation Learning Speech-Based Dementia Detection
Hertie Institute for AI in Brain Health, Germany · Tübingen AI Center, Germany · Sony Group Corporation, Japan +1
GLaS-JEPA: Gaussian-Regularized Speech SSL without Engineered Prediction Targets
Sep 29, 2026Gaspard Botté, Séverin Baroudi, Samir Sadok +5Joint-Embedding Predictive Architecture Predictive Representation Learning
Concordia University · Mila – Qu´ebec AI Institute · Univ Toulon, Aix Marseille Univ, CNRS, LIS +4
GLAD: Global-Local Adaptive Detector for Robust Speech Deepfake Detection
Sep 28, 2026Zelin Zhao, Guanjie Huang, Danny Hin Kwok Tsang +1Audio Deepfake Detection Domain Generalization
The Hong Kong University of Science and Technology (Guangzhou)
OpenWhistle: A Large-Scale Longitudinal Dataset and Benchmark of Bottlenose Dolphin Vocalizations
Sep 28, 2026Faadil Mustun, Chiara Semenzin, Roberto Dessi +7Sound Event Detection Bioacoustics
Institut de Biologie de l’École normale supérieure, CNRS, INSERM, Université PSL, Paris, France · Earth Species Project, France · Not Diamond, San Francisco, USA +4
SPEAR-Gen: Generation-Aware Pre-training for Unified Speech Representations
Sep 28, 2026Xiaoyu Yang, Arthur Hinsvark, Antonios Alexos +3Representation Learning Self-Supervised Speech Representation Learning
Department of Engineering, University of Cambridge, Cambridge, UK · Meta Superintelligence Labs, Menlo Park, USA
What Survives the Codec Shift: Pooled No-Vocals Residuals for Speech Deepfake Detection
Sep 27, 2026Jiajun Xu, Menglu Li, Xiao-Ping ZhangAudio Representation Learning Audio Deepfake Detection
Department of Engineering Physics Tsinghua University Beijing, China · Tsinghua Shenzhen International Graduate School Tsinghua University Shenzhen, China
Language Discrimination Improves Linguistic Learning in Multilingual Speech Models
Sep 27, 2026Maureen de Seyssel, Jie Chi, Zakaria AldenehSelf-Supervised Speech Representation Learning
Apple
Do Audio Language Models Hear and Read Distinctive Features Alike?
Sep 24, 2026Yuanhao Chen, Peter ChinAudio-Language Models Self-Supervised Speech Representation Learning
Thayer School of Engineering, Dartmouth College, Hanover, NH, USA
BiMamba2 Masked Discrete-Unit Prediction for Multilingual Speech Representation for Unsupervised Speech in the Wild Challenge
Sep 23, 2026Prakriti Subedi, Howard Prioleau, Saurav K AryalSpeech Processing Self-Supervised Speech Representation Learning
Howard University, Washington D.C., USA
ToneCL: Contrastive Learning for Few-Shot Syllable-Level Tone Classification
Sep 21, 2026Qisheng Liao, Youngah DoContrastive Learning Few-Shot Audio Classification
Department of Linguistics The University of Hong Kong
End-to-end Jordanian dialect speech-to-text self-supervised learning framework
Sep 21, 2026Ali A. Safieh, Ibrahim Abu Alhaol, Rawan GhnematAutomatic Speech Recognition Self-Supervised Speech Representation Learning
Data Science Department, King Hussein School of Computing Sciences, Princess Sumaya University for Technology, Amman, Jordan
Do speech foundation models really learn words?
Sep 9, 2026Robin Huo, Ewan DunbarRepresentation Learning Speech Foundation Models
University of Toronto, Canada
Is Semantics Enough for Speech Mean Opinion Score Prediction?
Sep 3, 2026Tianyu Lan, Yufei Shi, Yang Ai +3Human Preference Evaluation Neural Audio Codecs
National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China
Cluster Assignments in Soft Targets Shape Speech Representations: Evidence from S-JEPA
Aug 19, 2026Wenxuan He, Yunpeng Li, Zewei Li +4Soft-Label Learning Unsupervised Clustering
Department of Intelligent Science, School of Advanced Technology, Xi’an Jiaotong-Liverpool University, Suzhou, China
Motor, Cognitive, or Corpus? What Survives Cross-Lingual Transfer in Speech-Based Parkinsons Disease Detection
Aug 13, 2026Serli Kopar, Sam Gijsen, Abner Hernandez +2Speech Processing Parkinson's Disease
Hertie Institute for AI in Brain Health, University of Tübingen, Tübingen, Germany · Tübingen AI Center, University of Tübingen, Tübingen, Germany · Charité–Universitätsmedizin, Department of Psychiatry and Psychotherapy, Berlin, Germany +1
The Learning Objective Governs Perceptual Narrowing: A Cross-Lingual, Layer-Wise, Ten-Seed Study of Self-Supervised Speech Encoders
Aug 1, 2026Sejin YooAudio Understanding Self-Supervised Speech Representation Learning
Independent Researcher
Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens
Jul 28, 2026Daigo Takizawa, Tomohiko Nakamura, Samuele Cornell +3Audio Representation Learning Neural Audio Codecs
National Institute of Advanced Industrial Science and Technology (AIST), Japan · Carnegie Mellon University, USA
Multi-Phonation Graph Learning with Self-Supervised Speech Embeddings for ALS Detection and Progression Prediction
Jul 28, 2026Behrad TaghiBeyglou, Fatemeh Bagheri, Ervin SejdicGraph Representation Learning Clinical Outcome Prediction
Department of Electrical and Computer Engineering, University of Toronto, Canada · North York General Hospital, Canada
Content is What Remains: Invariant Speech Tokenization from Parallel Utterances
Jul 21, 2026Laurin Wagner, Bernhard Thallinger, Miroslav Stankovic +1Audio Tokenization Self-Supervised Speech Representation Learning
nyra labs · nyra labs, Austria
Rethinking Speech Foundation Model Fine-tuning: Better SFT or Better Match?
Jul 15, 2026Wangjin Zhou, Yizhou Zhang, Yichi Wang +1Supervised Fine-Tuning Fine-Tuning
Graduate School of Informatics, Kyoto University, Kyoto, Japan
GigaAM Multilingual: Foundation Model for Underrepresented Languages
Jul 11, 2026Andrei Kuzmenko, Alexandr Maximenko, Aleksandr Kutsakov +5Speech Foundation Models Speech Processing
SaluteDevices, Russia
InsideSSL: Understanding Self-Supervised Speech Representations using a Model-Centric Perspective
Jul 7, 2026Samir Sadok, Xavier Alameda-PinedaRepresentation Geometry Self-Supervised Speech Representation Learning
Inria, Universit´e Grenoble Alpes CNRS, LJK, France
When and why do handcrafted cues help self-supervised anti-spoofing? A causal and faithfulness analysis
Jul 5, 2026Yugwon WonAudio Deepfake Detection ASVspoof
AI Security R&D Team, RaonSecure Co., Ltd., Seoul, Republic of Korea
Speaker-Disentangled Chunk-Wise Regression for Syllabic Tokenization
Jul 5, 2026Ryota Komatsu, Kota Kawakita, Takuma Okamoto +1Audio Tokenization Self-Supervised Speech Representation Learning
Institute of Science Tokyo, Meguro, Tokyo 152-8550, Japan · National Institute of Information and Communications Technology, Kyoto 619-0289, Japan
How Bilingual Are SSL Speech Models? Cross-Lingual Probing of Articulatory Encoding with Finnish and Russian EMA
Jun 30, 2026Ailín Pollio San Pedro, Tomi Kinnunen, Alexandre Nikolaev +1Speech Processing Self-Supervised Speech Representation Learning
University Grenoble Alpes, CNRS, Grenoble INP, GIPSA-lab, France · University of Eastern Finland, Computational Speech Group, Finland
OLIVE: View-Augmented Latent Prediction with Waveform Reconstruction for Speech SSL
Jun 29, 2026Karl El Hajal, Mathew Magimai. -DossPredictive Representation Learning Self-Supervised Speech Representation Learning
Idiap Research Institute, Switzerland · EPFL, Switzerland
BEST-RQ-2: Contextualize-Then-Predict, a Two-Step Approach for Self-Supervised Audio Representations
Jun 29, 2026Ludovic K. Tuncay, Etienne Labbé, Thomas PellegriniAudio Representation Learning Self-Supervised Pre-Training
IRIT-SAMoVA · IRIT, Université de Toulouse, CNRS, Toulouse INP, Toulouse, France
Enhancing BEST-RQ Pseudo-Label Quality through Online Refinement for Automatic Speech Recognition
Jun 24, 2026Jingjing Xu, Zijian Yang, Mohammad Zeineldeen +3Automatic Speech Recognition Vector Quantization
Machine Learning and Human Language Technology Group, RWTH Aachen University, Germany · Apptek GmbH, Aachen, Germany

Oct 7, 2026, eess.ASJ/K move · Enter open · S save

Mitigating Accent-Language Confusion in Self-Supervised Speech Representations for Language Identification

Minu Kim, Jihwan Lee, David R. Mortensen, Shrikanth Narayanan

Signal Analysis and Interpretation Lab (SAIL), University of Southern California, USA · Language Technologies Institute, Carnegie Mellon University, USA

Language Identification Algorithmic Bias Self-Supervised Speech Representation Learning

Open paper AskPDF arXiv

Spoken language identification (LID) aims to recognize the target language regardless of accent. In practice, however, LID models fine-tuned from self-supervised speech representations frequently confuse accents with languages, misclassifying non-native (L2) speech as the speaker's first language (L1). We show that non-native speech representations lie between native target-language and native L1 poles, causing systematic misclassification. To address this, we introduce a geometric projection that estimates an L1-bias direction solely from native speech and removes it before the frozen LID head. Across five MMS-LID models and non-native corpora, this projection substantially improves target language identification for L2-accented speech while preserving predictions for native speech. These results show that accent-induced L1 bias can be corrected directly within the representation space without L2 training data or model adaptation.

Momentum

Related topics

Latest papers 70