1 citations · 2 across the 4 of their papers we have counts for
4 papers
MixRep: Hidden Representation Mixup for Low-Resource Speech Recognition
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. MixRep interpolates the feature dimensions of hidden repres…
DEFORMER: Coupling Deformed Localized Patterns with Global Context for Robust End-to-end Speech Recognition
Jiamin Xie, John H. L. Hansen
Convolutional neural networks (CNN) have improved speech recognition performance greatly by exploiting localized time-frequency patterns. But these patterns are assumed to appear i…
FeaRLESS: Feature Refinement Loss for Ensembling Self-Supervised Learning Features in Robust End-to-end Speech Recognition
Szu-Jui Chen, Jiamin Xie, John H. L. Hansen
Self-supervised learning representations (SSLR) have resulted in robust features for downstream tasks in many fields. Recently, several SSLRs have shown promising results on automa…
Mixture of Speaker-type PLDAs for Children's Speech Diarization
Jiamin Xie, Suzanna Sia, Paola Garcia +2
In diarization, the PLDA is typically used to model an inference structure which assumes the variation in speech segments be induced by various speakers. The speaker variation is t…