Shuwen Yang

A Comparative Study of Self-supervised Speech Representation Based Voice Conversion

2022 · arXiv (Cornell University)

We present a large-scale comparative study of self-supervised speech representation (S3R)-based voice conversion (VC). In the context of recognition-synthesis VC, S3Rs are attractive owing to their potential to replace expensive supervised representations such as phonetic …

Progressive Evidence Refinement for Open-domain Multimodal Retrieval Question Answering

2023 · arXiv (Cornell University)

Pre-trained multimodal models have achieved significant success in retrieval-based question answering. However, current multimodal retrieval question-answering models face two main challenges. Firstly, utilizing compressed evidence features as input to the model results in the loss …