{"total":40,"rows":[{"id":"2411.00860","title":"Survey of Cultural Awareness in Language Models: Text and Beyond","created":"2024-10-30","cited_by_count":103,"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":"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":"2505.20564","title":"The NaijaVoices Dataset: Cultivating Large-Scale, High-Quality, Culturally-Rich Speech Data for African Languages","created":"2025-05-26","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":"2411.04699","title":"Towards Building Large Scale Datasets and State-of-the-Art Automatic Speech Translation Systems for 14 Indian Languages","created":"2024-11-07","cited_by_count":5,"area":null},{"id":"2508.01691","title":"Voxlect: A Speech Foundation Model Benchmark for Modeling Dialects and Regional Languages Around the Globe","created":"2025-08-03","cited_by_count":5,"area":null},{"id":"2510.07437","title":"LASER: An LLM-based ASR Scoring and Evaluation Rubric","created":"2025-10-08","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":"2406.10993","title":"CoSTA: Code-Switched Speech Translation using Aligned Speech-Text Interleaving","created":"2024-06-16","cited_by_count":4,"area":null},{"id":"2505.18609","title":"RASMALAI: Resources for Adaptive Speech Modeling in Indian Languages with Accents and Intonations","created":"2025-05-24","cited_by_count":4,"area":null},{"id":"2512.10967","title":"ASR Under the Stethoscope: Evaluating Biases in Clinical Speech Recognition across Indian Languages","created":"2025-11-30","cited_by_count":3,"area":null},{"id":"2606.19157","title":"IndicContextEval: A Benchmark for Evaluating Context Utilisation in Audio Large Language Models Across 8 Indic Languages","created":"2026-06-17","cited_by_count":3,"area":null},{"id":"2407.13435","title":"Enhancing Out-of-Vocabulary Performance of Indian TTS Systems for Practical Applications through Low-Effort Data Strategies","created":"2024-07-18","cited_by_count":2,"area":null},{"id":"2410.17901","title":"ELAICHI: Enhancing Low-resource TTS by Addressing Infrequent and Low-frequency Character Bigrams","created":"2024-10-23","cited_by_count":2,"area":null},{"id":"2505.20693","title":"Phir Hera Fairy: An English Fairytaler is a Strong Faker of Fluent Speech in Low-Resource Indian Languages","created":"2025-05-27","cited_by_count":2,"area":null},{"id":"2506.03793","title":"Mark My Words: A Robust Multilingual Model for Punctuation in Text and Speech Transcripts","created":"2025-06-04","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":"2502.12050","title":"SpeechT: Findings of the First Mentorship in Speech Translation","created":"2025-02-17","cited_by_count":1,"area":null},{"id":"2510.23252","title":"Are ASR foundation models generalized enough to capture features of regional dialects for low-resource languages?","created":"2025-10-27","cited_by_count":1,"area":null},{"id":"2512.07277","title":"Efficient ASR for Low-Resource Languages: Leveraging Cross-Lingual Unlabeled Data","created":"2025-12-08","cited_by_count":1,"area":null},{"id":"2606.25403","title":"CrossAccent-TTS: Cross-Lingual Accent-Intensity Controllable Text-to-Speech via Disentangled Speaker and Accent Representations","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2607.23808","title":"Indic DiarBench: A Multilingual Joint Diarization and ASR Benchmark for Indian Languages","created":"2026-07-26","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":"2609.15758","title":"Sequential Adapter Stacking for Cross-Lingual Low-Resource ASR","created":"2026-09-14","cited_by_count":1,"area":null},{"id":"2410.13445","title":"Parameter-efficient Adaptation of Multilingual Multimodal Models for Low-resource ASR","created":"2024-10-17","cited_by_count":0,"area":null},{"id":"2411.18368","title":"AMPS: ASR with Multimodal Paraphrase Supervision","created":"2024-11-27","cited_by_count":0,"area":null},{"id":"2507.19616","title":"HITSZ's End-To-End Speech Translation Systems Combining Sequence-to-Sequence Auto Speech Recognition Model and Indic Large Language Model for IWSLT 2025 in Indic Track","created":"2025-07-25","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":"2605.03073","title":"The TTS-STT Flywheel: Synthetic Entity-Dense Audio Closes the Indic ASR Gap Where Commercial and Open-Source Systems Fail","created":"2026-05-04","cited_by_count":0,"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":"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":"2608.06027","title":"FormBharo: Designing and Evaluating a Voice Agent for Conversational Form Filling in Rural India","created":"2026-08-06","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":"2608.21853","title":"PUMA: A Polish Benchmark for Culturally Grounded Multimodal Understanding","created":"2026-08-22","cited_by_count":0,"area":null},{"id":"2609.19879","title":"V\\={a}kQA: A Benchmark and Evaluation Study for Telugu Spoken Factoid Question Answering","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":"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}