5 citations · 11 across the 6 of their papers we have counts for
3 papers · 1 filter
Less is More: Data Curation Matters in Scaling Speech Enhancement
Chenda Li, Wangyou Zhang, Wei Wang +10
The vast majority of modern speech enhancement systems rely on data-driven neural network models. Conventionally, larger datasets are presumed to yield superior model performance,…
Aligning Speech to Languages to Enhance Code-switching Speech Recognition
Hexin Liu, Xiangyu Zhang, Haoyang Zhang +4
Code-switching (CS) refers to the switching of languages within a speech signal and results in language confusion for automatic speech recognition (ASR). To address language confus…
ESPnet-ST IWSLT 2021 Offline Speech Translation System
Hirofumi Inaguma, Brian Yan, Siddharth Dalmia +4
This paper describes the ESPnet-ST group's IWSLT 2021 submission in the offline speech translation track. This year we made various efforts on training data, architecture, and audi…