mlsanityData to 14 Oct 2026

Multilingual and code-switching ASR challenges for low resource Indian languages

arXiv 2104.00235 ↗First posted 1 Apr 2021cs.CL eess.AScited by 53

Not on the map. Why?

Abstract (arXiv)

Recently, there is increasing interest in multilingual automatic speech recognition (ASR) where a speech recognition system caters to multiple low resource languages by taking advantage of low amounts of labeled corpora in multiple languages. With multilingualism becoming common in today's world, there has been increasing interest in code-switching ASR as well. In code-switching, multiple languages are freely interchanged within a single sentence or between sentences. The success of low-resource multilingual and code-switching ASR often depends on the variety of languages in terms of their acoustics, linguistic characteristics as well as the amount of data available and how these are carefully considered in building the ASR system. In this challenge, we would like to focus on building multilingual and code-switching ASR systems through two different subtasks related to a total of seven Indian languages, namely Hindi, Marathi, Odia, Tamil, Telugu, Gujarati and Bengali. For this purpose, we provide a total of ~600 hours of transcribed speech data, comprising train and test sets, in these languages including two code-switched language pairs, Hindi-English and Bengali-English. We also provide a baseline recipe for both the tasks with a WER of 30.73% and 32.45% on the test sets of multilingual and code-switching subtasks, respectively.

Key facts. Cited by 53 papers in the map (data through 14 Oct 2026). Builds on 11 of its 39 references that are in the map. First posted on arXiv 1 Apr 2021.

Builds on

11 of 39 references.

References · 11

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015MUSAN: A Music, Speech, and Noise Corpuscited by 425
  3. 2020Massively Multilingual ASR: 50 Languages, 1 Model, 1 Billion Parameterscited by 110
  4. 2017Multilingual Speech Recognition With A Single End-To-End Modelcited by 87
  5. 2019A Survey of Code-switched Speech and Language Processingcited by 75
  6. 2018Bytes are All You Need: End-to-End Multilingual Speech Recognition and Synthesis with Bytescited by 54
  7. 2016Challenges of Computational Processing of Code-Switchingcited by 20
  8. 2020Language-agnostic Multilingual Modelingcited by 17
  9. 2020DARTS-ASR: Differentiable Architecture Search for Multilingual Speech Recognition and Adaptationcited by 15
  10. 2019Multilingual Graphemic Hybrid ASR with Massive Data Augmentationcited by 13
  11. 2017Multilingual Adaptation of RNN Based ASR Systemscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 5; 2022: 9; 2023: 7; 2024: 5; 2025: 8; 2026: 19.

53 papers.

Sort:

By area:

  1. 2021Recent Advances in End-to-End Automatic Speech Recognitioncited by 140
  2. 2021Towards Building ASR Systems for the Next Billion Userscited by 47
  3. 2024IndicVoices: Towards building an Inclusive Multilingual Speech Dataset for Indian Languagescited by 41
  4. 2022IndicSUPERB: A Speech Processing Universal Performance Benchmark for Indian languagescited by 40
  5. 2022The Decades Progress on Code-Switching Research in NLP: A Systematic Survey on Trends and Challengescited by 35
  6. 2023Vistaar: Diverse Benchmarks and Training Sets for Indian Language ASRcited by 21
  7. 2023CL-MASR: A Continual Learning Benchmark for Multilingual ASRcited by 17
  8. 2022Effectiveness of Mining Audio and Text Pairs from Public Data for Improving ASR Systems for Low-Resource Languagescited by 16
  9. 2022Towards Zero-Shot Code-Switched Speech Recognitioncited by 15
  10. 2025CS-FLEURS: A Massively Multilingual and Code-Switched Speech Datasetcited by 12
  11. 2024LAHAJA: A Robust Multi-accent Benchmark for Evaluating Hindi ASR Systemscited by 10
  12. 2021Unsupervised Domain Adaptation Schemes for Building ASR in Low-resource Languagescited by 9
38 more
  1. 2023Unified model for code-switching speech recognition and language identification based on a concatenated tokenizercited by 8
  2. 2022Vakyansh: ASR Toolkit for Low Resource Indic languagescited by 7
  3. 2022Language-agnostic Code-Switching in Sequence-To-Sequence Speech Recognitioncited by 7
  4. 2023Exploring the Landscape of Natural Language Processing Researchcited by 7
  5. 2023Generative error correction for code-switching speech recognition using large language modelscited by 7
  6. 2021Dual Script E2E framework for Multilingual and Code-Switching ASRcited by 6
  7. 2023Adapting the adapters for code-switching in multilingual ASRcited by 6
  8. 2024The Second DISPLACE Challenge : DIarization of SPeaker and LAnguage in Conversational Environmentscited by 6
  9. 2022Benchmarking Evaluation Metrics for Code-Switching Automatic Speech Recognitioncited by 5
  10. 2024Synthetic Data Generation and Joint Learning for Robust Code-Mixed Translationcited by 5
  11. 2025Can we train ASR systems on Code-switch without real code-switch data? Case study for Singapore's languagescited by 5
  12. 2025Beyond Monolingual Assumptions: A Survey of Code-Switched NLP in the Era of Large Language Models across Modalitiescited by 5
  13. 2025Code-Switching in End-to-End Automatic Speech Recognition: A Systematic Literature Reviewcited by 4
  14. 2022Annotated Speech Corpus for Low Resource Indian Languages: Awadhi, Bhojpuri, Braj and Magahicited by 3
  15. 2023Iteratively Improving Speech Recognition and Voice Conversioncited by 2
  16. 2025SAGE: Spliced-Audio Generated Data for Enhancing Foundational Models in Low-Resource Arabic-English Code-Switched Speech Recognitioncited by 2
  17. 2025NIRANTAR: Continual Learning with New Languages and Domains on Real-world Speech Datacited by 2
  18. 2025UniCoM: A Universal Code-Switching Speech Generatorcited by 2
  19. 2026Dialect Matters: Cross-Lingual ASR Transfer for Low-Resource Indic Language Varietiescited by 2
  20. 2021A Dual-Decoder Conformer for Multilingual Speech Recognitioncited by 1
  21. 2022Adversarial synthesis based data-augmentation for code-switched spoken language identificationcited by 1
  22. 2026Dynamic Multi-Expert Projectors with Stabilized Routing for Multilingual Speech Recognitioncited by 1
  23. 2026ALARM: Audio-Language Alignment for Reasoning Modelscited by 1
  24. 2026Benchmarking Commercial ASR Systems on Code-Switching Speech: Arabic, Persian, and Germancited by 1
  25. 2024Methods of Automatic Matrix Language Determination for Code-Switched Speechcited by 0
  26. 2025Dhvani: A Weakly-supervised Phonemic Error Detection and Personalized Feedback System for Hindicited by 0
  27. 2026Responsible AI for General-Purpose Systems: Overview, Challenges, and A Path Forwardcited by 0
  28. 2026Task-Lens: Cross-Task Utility Based Speech Dataset Profiling for Low-Resource Indian Languagescited by 0
  29. 2026Voice of India: A Large-Scale Benchmark for Real-World Speech Recognition in Indiacited by 0
  30. 2026Keyword spotting using convolutional neural network for speech recognition in Hindicited by 0
  31. 2026Benchmarking AI for low-resource contexts: Thinking beyond leaderboardscited by 0
  32. 2026Jointly Improving Dialect Identification and ASR in Indian Languages using Multimodal Feature Fusioncited by 0
  33. 2026The Exact Worst-Case Tail Probability under Bounded Kurtosiscited by 0
  34. 2026Mapping Written Words to Spoken Words in a Different Language Using Only Visual Groundingcited by 0
  35. 2026SETU: An Agentic Ecosystem for Multilingual, Persona-Aware Communication Coachingcited by 0
  36. 2026BuzzASR: A Swarm of 100+ Monolingual Speech Recognition Modelscited by 0
  37. 2026Vimarsha: Faithful ASR Evaluation for Indian Languages with Demographic Diversity, In-the-Wild Audio and Spelling Variationscited by 0
  38. 2026Turning Speech Language Models into Multilingual Listenerscited by 0

50 most cited of 53 All 53 (JSON)