1 code implementation • 27 Oct 2023 • Jiamin Xie, John H. L. Hansen
In this paper, we present MixRep, a simple and effective data augmentation strategy based on mixup for low-resource ASR.
no code implementations • 22 Sep 2023 • Jiamin Xie, Ke Li, Jinxi Guo, Andros Tjandra, Yuan Shangguan, Leda Sari, Chunyang Wu, Junteng Jia, Jay Mahadeokar, Ozlem Kalinli
In this work, we propose the use of an adaptive masking approach in two scenarios for pruning a multilingual ASR model efficiently, each resulting in sparse monolingual models or a sparse multilingual model (named as Dynamic ASR Pathways).
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 4 Jul 2022 • Jiamin Xie, John H. L. Hansen
Convolutional neural networks (CNN) have improved speech recognition performance greatly by exploiting localized time-frequency patterns.
no code implementations • 30 Jun 2022 • Szu-Jui Chen, Jiamin Xie, John H. L. Hansen
As such, we further propose a feature refinement loss for decorrelation to efficiently combine the set of input features.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2