56 citations · 213 across the 43 of their papers we have counts for
Showing 2023 · eess.ASShow all
3 papers · 2 filters
eess.AS2023★ 1 cited
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…
eess.AS2023★ 1 cited
What Can an Accent Identifier Learn? Probing Phonetic and Prosodic Information in a Wav2vec2-based Accent Identification Model
Mu Yang, Ram C. M. C. Shekar, Okim Kang +1
This study is focused on understanding and quantifying the change in phoneme and prosody information encoded in the Self-Supervised Learning (SSL) model, brought by an accent ident…
eess.AS2023
Improving Transformer-based Networks With Locality For Automatic Speaker Verification
Mufan Sang, Yong Zhao, Gang Liu +2
Recently, Transformer-based architectures have been explored for speaker embedding extraction. Although the Transformer employs the self-attention mechanism to efficiently model th…