{"total":16,"rows":[{"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":"2409.05356","title":"IndicVoices-R: Unlocking a Massive Multilingual Multi-speaker Speech Corpus for Scaling Indian TTS","created":"2024-09-09","cited_by_count":16,"area":null},{"id":"2305.09688","title":"OOD-Speech: A Large Bengali Speech Recognition Dataset for Out-of-Distribution Benchmarking","created":"2023-05-15","cited_by_count":9,"area":null},{"id":"2308.05269","title":"A Novel Self-training Approach for Low-resource Speech Recognition","created":"2023-08-10","cited_by_count":7,"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":"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":"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":"2210.16739","title":"DuDe: Dual-Decoder Multilingual ASR for Indian Languages using Common Label Set","created":"2022-10-30","cited_by_count":1,"area":null},{"id":"2506.16251","title":"End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data","created":"2025-06-19","cited_by_count":1,"area":null},{"id":"2605.09167","title":"WorldSpeech: A Multilingual Speech Corpus from Around the World","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2605.13087","title":"Vividh-ASR: A Complexity-Tiered Benchmark and Optimization Dynamics for Robust Indic Speech Recognition","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.20712","title":"SCRIBE: Diagnostic Evaluation and Rich Transcription Models for Indic ASR","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2605.28438","title":"Breaking the Script Barrier: Enabling Automatic Alignment for PoS-based ASR Error Analysis in Non-Latin Scripts","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.06740","title":"Multilingual Multi-Speaker Unit Vocoders: A Systematic Analysis of Discrete Speech Representations","created":"2026-06-04","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}],"next_cursor":null}