{"total":46,"rows":[{"id":"2305.13516","title":"Scaling Speech Technology to 1,000+ Languages","created":"2023-05-22","cited_by_count":411,"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":"2310.00274","title":"AfriSpeech-200: Pan-African Accented Speech Dataset for Clinical and General Domain ASR","created":"2023-09-30","cited_by_count":35,"area":null},{"id":"2211.09536","title":"Towards Building Text-To-Speech Systems for the Next Billion Users","created":"2022-11-17","cited_by_count":27,"area":null},{"id":"2210.02884","title":"Vision+X: A Survey on Multimodal Learning in the Light of Data","created":"2022-10-05","cited_by_count":22,"area":null},{"id":"2202.12576","title":"A Survey of Multilingual Models for Automatic Speech Recognition","created":"2022-02-25","cited_by_count":21,"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":"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":"2212.08486","title":"BLASER: A Text-Free Speech-to-Speech Translation Evaluation Metric","created":"2022-12-16","cited_by_count":16,"area":null},{"id":"2402.02302","title":"Predicting positive transfer for improved low-resource speech recognition using acoustic pseudo-tokens","created":"2024-02-03","cited_by_count":11,"area":null},{"id":"2306.00253","title":"AfriNames: Most ASR models \"butcher\" African Names","created":"2023-06-01","cited_by_count":7,"area":null},{"id":"2211.05103","title":"Accidental Learners: Spoken Language Identification in Multilingual Self-Supervised Models","created":"2022-11-09","cited_by_count":6,"area":null},{"id":"2408.14026","title":"Empowering Low-Resource Language ASR via Large-Scale Pseudo Labeling","created":"2024-08-26","cited_by_count":5,"area":null},{"id":"2603.00941","title":"Towards Orthographically-Informed Evaluation of Speech Recognition Systems for Indian Languages","created":"2026-03-01","cited_by_count":5,"area":null},{"id":"2306.04374","title":"Label Aware Speech Representation Learning For Language Identification","created":"2023-06-07","cited_by_count":4,"area":null},{"id":"2406.10993","title":"CoSTA: Code-Switched Speech Translation using Aligned Speech-Text Interleaving","created":"2024-06-16","cited_by_count":4,"area":null},{"id":"2305.15405","title":"Textless Speech-to-Speech Translation With Limited Parallel Data","created":"2023-05-24","cited_by_count":3,"area":null},{"id":"2510.06188","title":"BanglaTalk: Towards Real-Time Speech Assistance for Bengali Regional Dialects","created":"2025-10-07","cited_by_count":3,"area":null},{"id":"2203.16973","title":"Analyzing the factors affecting usefulness of Self-Supervised Pre-trained Representations for Speech Recognition","created":"2022-03-31","cited_by_count":2,"area":null},{"id":"2209.08119","title":"An Automatic Speech Recognition System for Bengali Language based on Wav2Vec2 and Transfer Learning","created":"2022-09-16","cited_by_count":2,"area":null},{"id":"2506.00145","title":"Vedavani: A Benchmark Corpus for ASR on Vedic Sanskrit Poetry","created":"2025-05-30","cited_by_count":2,"area":null},{"id":"2509.25516","title":"Beyond WER: Probing Whisper's Sub-token Decoder Across Diverse Language Resource Levels","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2602.03868","title":"Benchmarking Automatic Speech Recognition for Indian Languages in Agricultural Contexts","created":"2026-01-31","cited_by_count":2,"area":null},{"id":"2604.25476","title":"PSP: An Interpretable Per-Dimension Accent Benchmark for Indic Text-to-Speech","created":"2026-04-28","cited_by_count":1,"area":null},{"id":"2608.10670","title":"Seeds Before Objectives: Rethinking Evaluation for Low-Resource Garhwali ASR","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2204.00348","title":"WavFT: Acoustic model finetuning with labelled and unlabelled data","created":"2022-04-01","cited_by_count":0,"area":null},{"id":"2307.10982","title":"MASR: Multi-label Aware Speech Representation","created":"2023-07-20","cited_by_count":0,"area":null},{"id":"2308.03150","title":"\"We care\": Improving Code Mixed Speech Emotion Recognition in Customer-Care Conversations","created":"2023-08-06","cited_by_count":0,"area":null},{"id":"2309.10567","title":"Multimodal Modeling For Spoken Language Identification","created":"2023-09-19","cited_by_count":0,"area":null},{"id":"2310.06702","title":"Temporally Aligning Long Audio Interviews with Questions: A Case Study in Multimodal Data Integration","created":"2023-10-10","cited_by_count":0,"area":null},{"id":"2507.04966","title":"LAPS-Diff: A Diffusion-Based Framework for Singing Voice Synthesis With Language Aware Prosody-Style Guided Learning","created":"2025-07-07","cited_by_count":0,"area":null},{"id":"2510.22492","title":"The Limits of Data Scaling: Sub-token Utilization and Acoustic Saturation in Multilingual ASR","created":"2025-10-26","cited_by_count":0,"area":null},{"id":"2512.07265","title":"TeluguST-46: A Benchmark Corpus and Comprehensive Evaluation for Telugu-English Speech Translation","created":"2025-12-08","cited_by_count":0,"area":null},{"id":"2512.16401","title":"Navigating the Reality Gap: On-Device Continual Adaptation of ASR for Clinical Telephony","created":"2025-12-18","cited_by_count":0,"area":null},{"id":"2603.07554","title":"Nw\\=ach\\=a Mun\\=a: A Devanagari Speech Corpus and Proximal Transfer Benchmark for Nepal Bhasha ASR","created":"2026-03-08","cited_by_count":0,"area":null},{"id":"2603.19256","title":"ShobdoSetu: A Data-Centric Framework for Bengali Long-Form Speech Recognition and Speaker Diarization","created":"2026-02-25","cited_by_count":0,"area":null},{"id":"2604.19797","title":"Enhancing ASR Performance in the Medical Domain for Dravidian Languages","created":"2026-04-10","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":"2607.06544","title":"Rethinking Indic AI from a Lens of Cultural Heritage Preservation","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2607.17164","title":"Robust Assamese Speech Recognition through Controlled Fine-Tuning of Whisper Models","created":"2026-07-19","cited_by_count":0,"area":null},{"id":"2608.12327","title":"Comparative Analysis of Multilingual Pre-trained Models for Nepali Automatic Speech Recognition","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2609.20504","title":"Model-Agnostic and Language-Agnostic Voice Pipeline Improvement for the Agriculture Domain","created":"2026-09-17","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":"2609.29146","title":"BanglaKontho: Closing the Long-Form Gap in Bangla Text-to-Speech","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2610.05681","title":"Automatic Speech Recognition for Low-Resource Sinhala: A Critical Review of Methods, Challenges, and Future Directions","created":"2026-10-05","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}