InterSpeech 2021

Neural Network Training Methods and Architectures for ASR

Self-paced ensemble learning for speech and audio classification
(Oral presentation)

Nicolae-Cătălin Ristea (UPB, Romania), Radu Tudor Ionescu (University of Bucharest, Romania)

Multi-Encoder Learning and Stream Fusion for Transformer-Based End-to-End Automatic Speech Recognition
(Oral presentation)

Timo Lohrenz (Technische Universität Braunschweig, Germany), Zhengyang Li (Technische Universität Braunschweig, Germany), Tim Fingscheidt (Technische Universität Braunschweig, Germany)

Conditional Independence for Pretext Task Selection in Self-Supervised Speech Representation Learning
(Oral presentation)

Salah Zaiem (LTCI (UMR 5141), France), Titouan Parcollet (LIA (EA 4128), France), Slim Essid (LTCI (UMR 5141), France)

Investigating Methods to Improve Language Model Integration for Attention-based Encoder-Decoder ASR Models
(Oral presentation)

Mohammad Zeineldeen (RWTH Aachen University, Germany), Aleksandr Glushko (RWTH Aachen University, Germany), Wilfried Michel (RWTH Aachen University, Germany), Albert Zeyer (RWTH Aachen University, Germany), Ralf Schlüter (RWTH Aachen University, Germany), Hermann Ney (RWTH Aachen University, Germany)