Multilingual ASR

ASR: Automatic Speech Recognition

Ask about this topic

Overview

Multilingual ASR studies how to turn speech into text reliably across languages, dialects, accents, and mixed-language conversations, including languages with little training data. Systems range from CTC and transducer models to encoder-decoder recognizers such as Whisper and speech-language models connected through lightweight projectors; researchers adapt them with fine-tuning, language-specific adapters, distillation, and synthetic speech. Work increasingly tests real-world conditions such as spontaneous speech, medical terminology, speaker overlap, and code-switching, while benchmarks examine low-resource languages and regional variation. A central challenge is balancing shared cross-language knowledge with language-specific needs, while improving evaluation beyond WER to account for scripts, spelling variation, meaning, and demographic disparities.

Latest papers

CardsList

109 papers13 papers in the last four weeks, down 28% on the four weeks before. 0.1% of all new papers.

  1. Agentic Data Sampling Framework for Multilingual ASR via Linguistic-Aware Error-Driven Optimization

    Oct 27, 2026Zhiheng Qian, Junhao Du, Jing Peng +6Automatic Speech RecognitionMultilingual ASR

    Shanghai Jiao Tong University · AISpeech Co., Ltd. · Nanjing University

  2. Preserve to Expand: Source-Aware Adaptation and Model Merging for Multilingual LLM-Based ASR

    Oct 26, 2026Yuchen Zhang, Haralambos Mouratidis, Ravi ShekharMultilingual ASRAutomatic Speech Recognition

    Institute for Analytics and Data Science, University of Essex · School of Computer Science and Electronic Engineering, University of Essex

  3. Group Relative Policy Optimisation Improves Multilingual Speech Recognition in Low-Resource Languages

    Oct 22, 2026Tim Wenjie Hu, Evelyn Nafula Ouma, Benjamin Akera +1Automatic Speech RecognitionMultilingual ASR

    Sunbird AI, Uganda

  4. Omnilingual-MsASR: Benchmarking Multimodal, Multilingual, Long-Form Multi-Speaker ASR of Omni Large Language Models

    Oct 21, 2026Yuan Ge, Pei Zhang, Xize Cheng +8Multi-Speaker ASRSpeech Recognition Benchmarks

    Northeastern University, China · Alibaba Token Hub, Alibaba · Kunming University of Science and Technology +1

  5. Qwen-Audio-3.1-ASR Technical Report

    Oct 20, 2026Chuanmeng Bian, Daren Chen, Peixin Chen +45Audio-Language ModelsAutomatic Speech Recognition

  6. Monsoon: Scalable Spontaneous Speech Collection for Low-Resource ASR in 50 Languages

    Oct 19, 2026Shobhit Banga, Manas Dhir, Aaditya Pareek +8Speech Corpus ConstructionLow-Resource Speech Recognition

    Voice Arena

  7. SEA-HELM Audio: Evaluating Multilingual ASR-LLM Pipeline Performance Across SEA-HELM Subsets

    Oct 14, 2026Aulia Adila, Yixian Tan, Jonathan Heng +3Voice Agent EvaluationMultilingual Language Model Evaluation

    AI Singapore, Singapore

  8. ELARSpeech: A 30K-Hour Dataset Across 675 Underrepresented Languages for Long-Tail Multilingual Speech Technologies

    Oct 14, 2026Sangmin Lee, Yejin Jeon, David Ifeoluwa AdelaniLow-Resource Language ProcessingMultilingual ASR

    Yonsei University · McGill University · Mila - Quebec AI Institute +1

  9. CAFE: Confining Feature Distillation to Language-Routed Adapters for Compact Multilingual Automatic Speech Recognition

    Oct 13, 2026Tianchi Liu, Nicholas Moratelli, Khurram Azeem Hashmi +5Feature-Based Knowledge DistillationMultilingual ASR

    Tether AI Research

  10. LLM-HB: Language-Aware LLM-Guided Hotword Biasing for Code-Switching ASR

    Oct 12, 2026Yuxuan He, Genshun Wan, Pengcheng Li +3Code-Switching Speech RecognitionMultilingual ASR

    Auditory Cognition and Computational Acoustics Lab, Shanghai Jiao Tong University, Shanghai, China · AI research Institute, iFLYTEK Company Limited, Hefei, Anhui, China · School of Electronic Information, Wuhan University, Wuhan, Hubei, China

  11. Phonological Interference in Multilingual Speech Models

    Oct 8, 2026Moran Yanuka, Raja Giryes, Morris AlperMultilingual ASRAutomatic Speech Recognition

    Tel Aviv University · University of Miami

  12. HINTT Submission to the 2nd MLC-SLM Challenge: Comparing Cascaded and Unified Approaches to Diarization and ASR

    Oct 6, 2026Takanori Ashihara, Kohei Matsuura, Masato MimuraSpeaker-Attributed ASRAutomatic Speech Recognition

    NTT, Inc., Japan

  13. Benchmarking Automatic Speech Recognition Tools for Iberian Languages

    Sep 29, 2026Fernando López, Pablo Gómez, David Solans +2ASR EvaluationAutomatic Speech Recognition

    Telefónica Innovación Digital, Spain · Universidad Autónoma de Madrid, Spain

  14. CoSE-E: A Benchmark for Code-switched Speech Evaluation in Enterprise Settings

    Sep 28, 2026Shama Gupta, Hoang H Nguyen, Chelsea Huang +2Code-Switching Speech RecognitionASR Evaluation

    ServiceNow AI Research · Qualcomm Technologies, Inc.

  15. Almieyar: A Culturally Grounded Benchmark for Multi-Dialect Arabic Speech Recognition

    Sep 28, 2026Omid Ghahroodi, Anas Madkoor, Dima Faris Al Saudi +37ASR EvaluationArabic NLP

    QCRI, HBKU · Qatar University · UDST +15

  16. mu-bench: A Multilingual Utterance Transcription Benchmark

    Sep 25, 2026Andrea Li, Soham RayConversational Speech RecognitionASR Evaluation

    UC Berkeley · Sierra AI

  17. Child ASR Adaptation with Adult Retention: An Empirical Study

    Sep 25, 2026Houssam Eddine-Othman Lachemat, Shammur Absar ChowdhuryChild Speech RecognitionAutomatic Speech Recognition

    Qatar Computing Research Institute

  18. Adaptive Fisher-Whitened Cross-Covariance for Low-Resource Speech Recognition

    Sep 24, 2026Asmee Mishra, Mengjie Qian, Brechtje Post +1Speech Foundation ModelsLow-Resource Speech Recognition

    Department of Engineering, University of Cambridge, United Kingdom · Phonetics Laboratory, University of Cambridge, United Kingdom

  19. Benchmarking and Domain Adaptation of Automatic Speech Recognition (ASR) for Adolescent Health Communication in Ghanaian Languages

    Sep 24, 2026Stephen E. Moore, Akwasi Asare, Mich-Seth Owusu +3ASR EvaluationDomain Adaptation for ASR

    Department of Mathematics, University of Cape Coast, Ghana · Ghana Natural Language Processing, Cape Coast, Ghana

  20. BranchShine-CR: Compact Multilingual IPA Transcription with Self-Conditioned CTC and Consistency Regularization

    Sep 24, 2026Nikhil Navas, Sergio Chevtchenko, Talisson Damiao +1Connectionist Temporal ClassificationSpeech Processing

    International Centre for Neuromorphic Systems, Western Sydney University · Neurabuild

  21. The Second MLC-SLM Challenge: Multilingual Conversational Speech Diarization, Recognition, and Understanding

    Sep 23, 2026Bingshen Mu, Mingchen Shao, Zhennan Lin +7Spoken Language UnderstandingMultilingual Language Model Evaluation

    School of Intelligence Science and Technology, Nanjing University · College of Computing and Data Science, Nanyang Technological University, Singapore · Huawei Technologies, China +1

  22. Vimarsha: Faithful ASR Evaluation for Indian Languages with Demographic Diversity, In-the-Wild Audio and Spelling Variations

    Sep 21, 2026Kaushal Santosh Bhogale, Srija Anand, Sadakopa Ramakrishnan Thothathiri +3ASR EvaluationDemographic Bias in ASR

    Indian Institute of Technology, Madras, India · Sarvam AI, India

  23. Federated Multilingual Speech-LLMs: Architecture and Aggregation Strategy Benchmarking

    Sep 20, 2026Jordi Luque, Aleix Sant, Fernando LópezSpeech Language ModelsFederated Learning

    Telefónica Innovación Digital, Scientific Research

  24. The Spoken Wikipedia Presentation Corpus

    Sep 18, 2026Thomas Ranzenberger, Steffen Freisinger, Tobias Bocklet +1Speech Corpus ConstructionAutomatic Speech Recognition

    Technische Hochschule Nürnberg Nürnberg, Germany

  25. The Hidden Cost of Digits: Number Normalization and WER in ASR Systems

    Sep 17, 2026Stanisław Kacprzak, Mieszko FraśASR EvaluationMultilingual ASR

    AGH University of Krakow, Institute of Electronics, Krakow, Poland

  26. HearInContext: A Benchmark for Implicit Context in Speech Recognition

    Sep 16, 2026Yifan Gao, Yao Tian, Hongbin SuoASR EvaluationContextual ASR

    AI Center, OPPO, Beijing, China

  27. Sequential Adapter Stacking for Cross-Lingual Low-Resource ASR

    Sep 14, 2026Thai Thi Thanh Thao Dang, Mengjie Qian, Kate KnillLow-Resource Speech RecognitionParameter-Efficient Fine-Tuning

    Department of Engineering, University of Cambridge, UK

  28. Building a Production Greek-English Speech Recognizer

    Sep 11, 2026Christos Petrocheilos, Cleopatra Papadopoulou, Chris Porikis +3Automatic Speech RecognitionMultilingual ASR

    Sophea AI Lab, KIEFER SA, Athens, Greece

  29. Whisper-Based Speech Transcription from Videos Across Multiple Languages for Cross-Cultural Understanding

    Sep 10, 2026Michael PichenyDomain Adaptation for ASRAutomatic Speech Recognition

    NYU Courant Institute School of Mathematics, Computing, and Data Science NYU New York, USA

  30. Orukeet: Multilingual ASR with Frozen Gabor Kernels

    Sep 9, 2026Nathan Roll, Irene Yi, Büşra Marşan +6Automatic Speech RecognitionMultilingual ASR

    Oruk AI · Stanford University · OpenWhispr +2