10 papers
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…
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…
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…
HLTCOE JHU Submission to the Voice Privacy Challenge 2024
Henry Li Xinyuan, Zexin Cai, Ashi Garg +5
We present a number of systems for the Voice Privacy Challenge, including voice conversion based systems such as the kNN-VC method and the WavLM voice Conversion method, and text-t…
Clean Label Attacks against SLU Systems
Henry Li Xinyuan, Sonal Joshi, Thomas Thebaud +3
Poisoning backdoor attacks involve an adversary manipulating the training data to induce certain behaviors in the victim model by inserting a trigger in the signal at inference tim…
Privacy versus Emotion Preservation Trade-offs in Emotion-Preserving Speaker Anonymization
Zexin Cai, Henry Li Xinyuan, Ashi Garg +5
Advances in speech technology now allow unprecedented access to personally identifiable information through speech. To protect such information, the differential privacy field has…
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,…
Learning a Formality-Aware Japanese Sentence Representation
Henry Li Xinyuan, Ray Lee, Jerry Chen +1
While the way intermediate representations are generated in encoder-decoder sequence-to-sequence models typically allow them to preserve the semantics of the input sentence, input…