InterSpeech 2021

Miscellanous topics in ASR

The Energy and Carbon Footprint of Training End-to-End Speech Recognizers
(Oral presentation)

Titouan Parcollet (LIA (EA 4128), France), Mirco Ravanelli (Mila, Canada)

Radically Old Way of Computing Spectra: Applications in End-to-End ASR
(Oral presentation)

Samik Sadhu (Johns Hopkins University, USA), Hynek Hermansky (Johns Hopkins University, USA)

Self-supervised End-to-End ASR for Low Resource L2 Swedish
(Oral presentation)

Ragheb Al-Ghezi (Aalto University, Finland), Yaroslav Getman (Aalto University, Finland), Aku Rouhe (Aalto University, Finland), Raili Hildén (University of Helsinki, Finland), Mikko Kurimo (Aalto University, Finland)