Robust learning of acoustic representations from diverse speech data
J Fainberg - 2021 - era.ed.ac.uk
Automatic speech recognition is increasingly applied to new domains. A key challenge is to
robustly learn, update and maintain representations to cope with transient acoustic …
robustly learn, update and maintain representations to cope with transient acoustic …
[PDF][PDF] CACTAS-Collaborative Audio Categorization and Transcription for ASR Systems.
We present a web based tool that allows collaborative analysis and/or transcription of
audios with respect to Automatic Speech Recognition (ASR) systems. The tool presents a …
audios with respect to Automatic Speech Recognition (ASR) systems. The tool presents a …