TH3.SC2.3
A Comprehensive Analysis of Tokenization and Self-Supervised Learning in End-to-End Automatic Speech Recognition applied on French Language
Thibault Bañeras-Roux, Nantes University, France; Mickael Rouvier, Avignon University, France; Jane Wottawa, Le Mans University, France; Richard Dufour, Nantes University, France
Session:
TH3.SC2: Speech Recognition Lecture
Track:
ASMSP - Acoustic, Speech and Music Signal Processing
Location:
Saint Clair 2
Presentation Time:
Thu, 29 Aug, 16:50 - 17:10 France Time (UTC +1)
Session Co-Chairs:
Stefan Goetze, University of Sheffield and Andreas Triantafyllopoulos, Technical University of Munich
Presentation
Discussion
Resources
No resources available.
Session TH3.SC2
TH3.SC2.1: Character Error Rate Estimation for Automatic Speech Recognition of Short Utterances
Chanho Park, Hyunsik Kang, Thomas Hain, University of Sheffield, United Kingdom
TH3.SC2.2: IMPROVING ACCENTED SPEECH RECOGNITION USING DATA AUGMENTATION BASED ON UNSUPERVISED TEXT-TO-SPEECH SYNTHESIS
Cong-Thanh Do, Toshiba Europe Limited, United Kingdom; Shuhei Imai, Tohoku University, Japan; Rama Doddipatla, Toshiba Europe Limited, United Kingdom; Thomas Hain, University of Sheffield, United Kingdom
TH3.SC2.3: A Comprehensive Analysis of Tokenization and Self-Supervised Learning in End-to-End Automatic Speech Recognition applied on French Language
Thibault Bañeras-Roux, Nantes University, France; Mickael Rouvier, Avignon University, France; Jane Wottawa, Le Mans University, France; Richard Dufour, Nantes University, France
TH3.SC2.4: Towards Building an End-to-End Multilingual Automatic Lyrics Transcription Model
Jiawen Huang, Emmanouil Benetos, Queen Mary University of London, United Kingdom
TH3.SC2.5: LDASR: An Experimental Study on Layer Drop using Conformer-based Architecture
Abdul Hannan, University of Trento, Italy; Alessio Brutti, Daniele Falavigna, Fondazione Bruno Kessler, Italy