{"total":53,"rows":[{"id":"2111.01690","title":"Recent Advances in End-to-End Automatic Speech Recognition","created":"2021-11-02","cited_by_count":140,"area":null},{"id":"2111.03945","title":"Towards Building ASR Systems for the Next Billion Users","created":"2021-11-06","cited_by_count":47,"area":null},{"id":"2403.01926","title":"IndicVoices: Towards building an Inclusive Multilingual Speech Dataset for Indian Languages","created":"2024-03-04","cited_by_count":41,"area":null},{"id":"2208.11761","title":"IndicSUPERB: A Speech Processing Universal Performance Benchmark for Indian languages","created":"2022-08-24","cited_by_count":40,"area":null},{"id":"2212.09660","title":"The Decades Progress on Code-Switching Research in NLP: A Systematic Survey on Trends and Challenges","created":"2022-12-19","cited_by_count":35,"area":null},{"id":"2305.15386","title":"Vistaar: Diverse Benchmarks and Training Sets for Indian Language ASR","created":"2023-05-24","cited_by_count":21,"area":null},{"id":"2310.16931","title":"CL-MASR: A Continual Learning Benchmark for Multilingual ASR","created":"2023-10-25","cited_by_count":17,"area":null},{"id":"2208.12666","title":"Effectiveness of Mining Audio and Text Pairs from Public Data for Improving ASR Systems for Low-Resource Languages","created":"2022-08-26","cited_by_count":16,"area":null},{"id":"2211.01458","title":"Towards Zero-Shot Code-Switched Speech Recognition","created":"2022-11-02","cited_by_count":15,"area":null},{"id":"2509.14161","title":"CS-FLEURS: A Massively Multilingual and Code-Switched Speech Dataset","created":"2025-09-17","cited_by_count":12,"area":null},{"id":"2408.11440","title":"LAHAJA: A Robust Multi-accent Benchmark for Evaluating Hindi ASR Systems","created":"2024-08-21","cited_by_count":10,"area":null},{"id":"2109.05494","title":"Unsupervised Domain Adaptation Schemes for Building ASR in Low-resource Languages","created":"2021-09-12","cited_by_count":9,"area":null},{"id":"2306.08753","title":"Unified model for code-switching speech recognition and language identification based on a concatenated tokenizer","created":"2023-06-14","cited_by_count":8,"area":null},{"id":"2203.16512","title":"Vakyansh: ASR Toolkit for Low Resource Indic languages","created":"2022-03-30","cited_by_count":7,"area":null},{"id":"2210.08992","title":"Language-agnostic Code-Switching in Sequence-To-Sequence Speech Recognition","created":"2022-10-17","cited_by_count":7,"area":null},{"id":"2307.10652","title":"Exploring the Landscape of Natural Language Processing Research","created":"2023-07-20","cited_by_count":7,"area":null},{"id":"2310.13013","title":"Generative error correction for code-switching speech recognition using large language models","created":"2023-10-17","cited_by_count":7,"area":null},{"id":"2106.01400","title":"Dual Script E2E framework for Multilingual and Code-Switching ASR","created":"2021-06-02","cited_by_count":6,"area":null},{"id":"2310.07423","title":"Adapting the adapters for code-switching in multilingual ASR","created":"2023-10-11","cited_by_count":6,"area":null},{"id":"2406.09494","title":"The Second DISPLACE Challenge : DIarization of SPeaker and LAnguage in Conversational Environments","created":"2024-06-13","cited_by_count":6,"area":null},{"id":"2211.16319","title":"Benchmarking Evaluation Metrics for Code-Switching Automatic Speech Recognition","created":"2022-11-22","cited_by_count":5,"area":null},{"id":"2403.16771","title":"Synthetic Data Generation and Joint Learning for Robust Code-Mixed Translation","created":"2024-03-25","cited_by_count":5,"area":null},{"id":"2506.14177","title":"Can we train ASR systems on Code-switch without real code-switch data? Case study for Singapore's languages","created":"2025-06-17","cited_by_count":5,"area":null},{"id":"2510.07037","title":"Beyond Monolingual Assumptions: A Survey of Code-Switched NLP in the Era of Large Language Models across Modalities","created":"2025-10-08","cited_by_count":5,"area":null},{"id":"2507.07741","title":"Code-Switching in End-to-End Automatic Speech Recognition: A Systematic Literature Review","created":"2025-07-10","cited_by_count":4,"area":null},{"id":"2206.12931","title":"Annotated Speech Corpus for Low Resource Indian Languages: Awadhi, Bhojpuri, Braj and Magahi","created":"2022-06-26","cited_by_count":3,"area":null},{"id":"2305.15055","title":"Iteratively Improving Speech Recognition and Voice Conversion","created":"2023-05-24","cited_by_count":2,"area":null},{"id":"2506.22143","title":"SAGE: Spliced-Audio Generated Data for Enhancing Foundational Models in Low-Resource Arabic-English Code-Switched Speech Recognition","created":"2025-06-27","cited_by_count":2,"area":null},{"id":"2507.00534","title":"NIRANTAR: Continual Learning with New Languages and Domains on Real-world Speech Data","created":"2025-07-01","cited_by_count":2,"area":null},{"id":"2508.15244","title":"UniCoM: A Universal Code-Switching Speech Generator","created":"2025-08-21","cited_by_count":2,"area":null},{"id":"2601.04373","title":"Dialect Matters: Cross-Lingual ASR Transfer for Low-Resource Indic Language Varieties","created":"2026-01-07","cited_by_count":2,"area":null},{"id":"2109.03277","title":"A Dual-Decoder Conformer for Multilingual Speech Recognition","created":"2021-08-22","cited_by_count":1,"area":null},{"id":"2205.15747","title":"Adversarial synthesis based data-augmentation for code-switched spoken language identification","created":"2022-05-30","cited_by_count":1,"area":null},{"id":"2601.19451","title":"Dynamic Multi-Expert Projectors with Stabilized Routing for Multilingual Speech Recognition","created":"2026-01-27","cited_by_count":1,"area":"moe"},{"id":"2603.09556","title":"ALARM: Audio-Language Alignment for Reasoning Models","created":"2026-03-10","cited_by_count":1,"area":"lr"},{"id":"2605.19069","title":"Benchmarking Commercial ASR Systems on Code-Switching Speech: Arabic, Persian, and German","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2410.02521","title":"Methods of Automatic Matrix Language Determination for Code-Switched Speech","created":"2024-10-03","cited_by_count":0,"area":null},{"id":"2506.02166","title":"Dhvani: A Weakly-supervised Phonemic Error Detection and Personalized Feedback System for Hindi","created":"2025-06-02","cited_by_count":0,"area":null},{"id":"2601.13122","title":"Responsible AI for General-Purpose Systems: Overview, Challenges, and A Path Forward","created":"2026-01-19","cited_by_count":0,"area":null},{"id":"2602.23388","title":"Task-Lens: Cross-Task Utility Based Speech Dataset Profiling for Low-Resource Indian Languages","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2604.19151","title":"Voice of India: A Large-Scale Benchmark for Real-World Speech Recognition in India","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2605.02928","title":"Keyword spotting using convolutional neural network for speech recognition in Hindi","created":"2026-04-26","cited_by_count":0,"area":null},{"id":"2605.28508","title":"Benchmarking AI for low-resource contexts: Thinking beyond leaderboards","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2607.02862","title":"Jointly Improving Dialect Identification and ASR in Indian Languages using Multimodal Feature Fusion","created":"2026-07-03","cited_by_count":0,"area":null},{"id":"2607.05226","title":"The Exact Worst-Case Tail Probability under Bounded Kurtosis","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2608.26925","title":"Mapping Written Words to Spoken Words in a Different Language Using Only Visual Grounding","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2608.27524","title":"SETU: An Agentic Ecosystem for Multilingual, Persona-Aware Communication Coaching","created":"2026-08-27","cited_by_count":0,"area":"agents"},{"id":"2609.09554","title":"BuzzASR: A Swarm of 100+ Monolingual Speech Recognition Models","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.24199","title":"Vimarsha: Faithful ASR Evaluation for Indian Languages with Demographic Diversity, In-the-Wild Audio and Spelling Variations","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.33204","title":"Turning Speech Language Models into Multilingual Listeners","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.18726","title":"Code-Switching Detection via Language-Selective Dimensions in Speech Foundation Models","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.20263","title":"Anuvani-LID: Robust and Calibrated Spoken Language Identification for Indian Languages","created":"2026-10-14","cited_by_count":0,"area":null},{"id":"2610.20327","title":"Anuvani-Diarization: Zero Shot Speaker Diarization and Annotation Conventions Across 22 Languages","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}