3 papers
cs.CL2024
Zero-resource Speech Translation and Recognition with LLMs
Karel Mundnich, Xing Niu, Prashant Mathur +10
Despite recent advancements in speech processing, zero-resource speech translation (ST) and automatic speech recognition (ASR) remain challenging problems. In this work, we propose…
cs.SD2024
Improving Lip-synchrony in Direct Audio-Visual Speech-to-Speech Translation
Lucas Goncalves, Prashant Mathur, Xing Niu +5
Audio-Visual Speech-to-Speech Translation typically prioritizes improving translation quality and naturalness. However, an equally critical aspect in audio-visual content is lip-sy…
cs.CL2024
Sequential Editing for Lifelong Training of Speech Recognition Models
Devang Kulshreshtha, Saket Dingliwal, Brady Houston +2
Automatic Speech Recognition (ASR) traditionally assumes known domains, but adding data from a new domain raises concerns about computational inefficiencies linked to retraining mo…