4 papers
Pretrained ASR Pseudo-labeling for Noisy Police Audio
Kaavya Chaparala, Su Huang, Stephen L. Miller +3
Pretrained ASR systems perform poorly on noisy Broadcast Police Communication (BPC), hindering efforts to understand police decision-making. Pseudo-labeling offers an unsupervised…
When Text Misleads: Inconsistent-Aware Reasoning for Audio-Grounded Dialogue
Yen-Ju Lu, Yuzhe Wang, Yaohan Guan +8
Understanding spoken dialogue requires joint reasoning over lexical content and paralinguistic acoustic signals such as emotion and conversational intent. However, existing evaluat…
Beyond Transcripts: Iterative Peer-Editing with Audio Unlocks High-Quality Human Summaries of Conversational Speech
Kaavya Chaparala, Thomas Thebaud, Jesús Villalba López +3
There are not enough established benchmarks for the task fo speech summarization. Creating new benchmarks demands human annotation, as LLMs could embed systemic errors and bias int…
Mai Ho'omāuna i ka 'Ai: Language Models Improve Automatic Speech Recognition in Hawaiian
Kaavya Chaparala, Guido Zarrella, Bruce Torres Fischer +2
In this paper we address the challenge of improving Automatic Speech Recognition (ASR) for a low-resource language, Hawaiian, by incorporating large amounts of independent text dat…