{"total":14,"rows":[{"id":"2505.23170","title":"ZIPA: A family of efficient models for multilingual phone recognition","created":"2025-05-29","cited_by_count":19,"area":null},{"id":"2111.13419","title":"KazNERD: Kazakh Named Entity Recognition Dataset","created":"2021-11-26","cited_by_count":15,"area":null},{"id":"2510.24992","title":"POWSM: A Phonetic Open Whisper-Style Speech Foundation Model","created":"2025-10-28","cited_by_count":14,"area":null},{"id":"2104.08459","title":"KazakhTTS: An Open-Source Kazakh Text-to-Speech Synthesis Dataset","created":"2021-04-17","cited_by_count":13,"area":null},{"id":"2201.05771","title":"KazakhTTS2: Extending the Open-Source Kazakh TTS Corpus With More Data, Speakers, and Topics","created":"2022-01-15","cited_by_count":10,"area":null},{"id":"2407.05006","title":"Recent Advancements and Challenges of Turkic Central Asian Language Processing","created":"2024-07-06","cited_by_count":6,"area":null},{"id":"2107.14419","title":"USC: An Open-Source Uzbek Speech Corpus and Initial Speech Recognition Experiments","created":"2021-07-30","cited_by_count":4,"area":null},{"id":"2108.01280","title":"A Study of Multilingual End-to-End Speech Recognition for Kazakh, Russian, and English","created":"2021-08-03","cited_by_count":4,"area":null},{"id":"2305.15749","title":"Multilingual Text-to-Speech Synthesis for Turkic Languages Using Transliteration","created":"2023-05-25","cited_by_count":2,"area":null},{"id":"2510.04832","title":"How I Built ASR for Endangered Languages with a Spoken Dictionary","created":"2025-10-06","cited_by_count":1,"area":null},{"id":"2608.24707","title":"Lost in Speech: Trilingual Spoken Hallucination Detection Across Audio and Transcripts","created":"2026-08-25","cited_by_count":1,"area":null},{"id":"2107.10637","title":"A baseline model for computationally inexpensive speech recognition for Kazakh using the Coqui STT framework","created":"2021-07-19","cited_by_count":0,"area":null},{"id":"2210.15135","title":"Training Autoregressive Speech Recognition Models with Limited in-domain Supervision","created":"2022-10-27","cited_by_count":0,"area":null},{"id":"2409.08103","title":"The Faetar Benchmark: Speech Recognition in a Very Under-Resourced Language","created":"2024-09-12","cited_by_count":0,"area":null}],"next_cursor":null}