{"total":22,"rows":[{"id":"2111.03945","title":"Towards Building ASR Systems for the Next Billion Users","created":"2021-11-06","cited_by_count":47,"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":"2202.07991","title":"ADIMA: Abuse Detection In Multilingual Audio","created":"2022-02-16","cited_by_count":11,"area":null},{"id":"2203.14456","title":"3MASSIV: Multilingual, Multimodal and Multi-Aspect dataset of Social Media Short Videos","created":"2022-03-28","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":"2412.19785","title":"Enhancing Whisper's Accuracy and Speed for Indian Languages through Prompt-Tuning and Tokenization","created":"2024-12-27","cited_by_count":4,"area":null},{"id":"2203.16578","title":"Code Switched and Code Mixed Speech Recognition for Indic languages","created":"2022-03-30","cited_by_count":2,"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":"2305.12518","title":"VAKTA-SETU: A Speech-to-Speech Machine Translation Service in Select Indic Languages","created":"2023-05-21","cited_by_count":2,"area":null},{"id":"2312.12783","title":"Stable Distillation: Regularizing Continued Pre-training for Low-Resource Automatic Speech Recognition","created":"2023-12-20","cited_by_count":2,"area":null},{"id":"2203.16595","title":"Improving Speech Recognition for Indic Languages using Language Model","created":"2022-03-30","cited_by_count":1,"area":null},{"id":"2308.10470","title":"Implicit Self-supervised Language Representation for Spoken Language Diarization","created":"2023-08-21","cited_by_count":1,"area":null},{"id":"2310.17448","title":"Dialect Adaptation and Data Augmentation for Low-Resource ASR: TalTech Systems for the MADASR 2023 Challenge","created":"2023-10-26","cited_by_count":1,"area":null},{"id":"2312.13026","title":"FusDom: Combining In-Domain and Out-of-Domain Knowledge for Continuous Self-Supervised Learning","created":"2023-12-20","cited_by_count":1,"area":null},{"id":"2503.21530","title":"Low-Resource Transliteration for Roman-Urdu and Urdu Using Transformer-Based Models","created":"2025-03-27","cited_by_count":1,"area":null},{"id":"2511.21704","title":"On the Cross-lingual Transferability of Pre-trained wav2vec2-based Models","created":"2025-11-16","cited_by_count":1,"area":null},{"id":"2203.16601","title":"Is Word Error Rate a good evaluation metric for Speech Recognition in Indic Languages?","created":"2022-03-30","cited_by_count":0,"area":null},{"id":"2203.16823","title":"Effectiveness of text to speech pseudo labels for forced alignment and cross lingual pretrained models for low resource speech recognition","created":"2022-03-31","cited_by_count":0,"area":null},{"id":"2204.02263","title":"Multilingual and Multimodal Abuse Detection","created":"2022-04-03","cited_by_count":0,"area":null},{"id":"2306.12913","title":"Implicit spoken language diarization","created":"2023-06-22","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":"2412.01408","title":"Towards Cross-Lingual Audio Abuse Detection in Low-Resource Settings with Few-Shot Learning","created":"2024-12-02","cited_by_count":0,"area":null}],"next_cursor":null}