Yusheng Tian

Improving End-to-End Speech-to-Intent Classification with Reptile

2020 · arXiv (Cornell University)

End-to-end spoken language understanding (SLU) systems have many advantages over conventional pipeline systems, but collecting in-domain speech data to train an end-to-end system is costly and time consuming. One question arises from this: how to …

Convolution-Based Channel-Frequency Attention for Text-Independent Speaker Verification

2022 · arXiv (Cornell University)

Deep convolutional neural networks (CNNs) have been applied to extracting speaker embeddings with significant success in speaker verification. Incorporating the attention mechanism has shown to be effective in improving the model performance. This paper presents …