6 papers
HK-LegiCoST: Leveraging Non-Verbatim Transcripts for Speech Translation
Cihan Xiao, Henry Li Xinyuan, Jinyi Yang +4
We introduce HK-LegiCoST, a new three-way parallel corpus of Cantonese-English translations, containing 600+ hours of Cantonese audio, its standard traditional Chinese transcript,…
Universal Speech Content Factorization
Henry Li Xinyuan, Zexin Cai, Lin Zhang +5
We propose Universal Speech Content Factorization (USCF), a simple and invertible linear method for extracting a low-rank speech representation in which speaker timbre is suppresse…
GenVC: Self-Supervised Zero-Shot Voice Conversion
Zexin Cai, Henry Li Xinyuan, Ashi Garg +5
Most current zero-shot voice conversion methods rely on externally supervised components, particularly speaker encoders, for training. To explore alternatives that eliminate this d…
Rapidly Adapting to New Voice Spoofing: Few-Shot Detection of Synthesized Speech Under Distribution Shifts
Ashi Garg, Zexin Cai, Henry Li Xinyuan +5
We address the challenge of detecting synthesized speech under distribution shifts -- arising from unseen synthesis methods, speakers, languages, or audio conditions -- relative to…
Scalable Controllable Accented TTS
Henry Li Xinyuan, Zexin Cai, Ashi Garg +5
We tackle the challenge of scaling accented TTS systems, expanding their capabilities to include much larger amounts of training data and a wider variety of accent labels, even for…
ShiftySpeech: A Large-Scale Synthetic Speech Dataset with Distribution Shifts
Ashi Garg, Zexin Cai, Lin Zhang +6
The problem of synthetic speech detection has enjoyed considerable attention, with recent methods achieving low error rates across several established benchmarks. However, to what…