Audio and acoustics
Publication
Knowledge boosting during low-latency inference
Project
Convert and Speak: Zero-shot Accent Conversion with MinimumSupervision
Demo page for the research paper accepted in ACM MM2024 Low resource of parallel data is the key challenge of accent conversion(AC) problem in which both the pronunciation units and prosody pattern need to be…
Project
TransVIP
Speech to Speech Translation System with Voice and Isochrony Preservation We introduce a novel model framework TransVIP that leverages diverse datasets in a cascade fashion yet facilitates end-to-end inference through joint probability. Furthermore, we propose…
Video
MSR Talk: Unsupervised Speech Reverberation Control with Diffusion Implicit Bridges
Speaker(s): Eloi MolinerHost: Hannes Gamper Speech reverberation control involves the manipulation of acoustic characteristics in speech recordings, including tasks like speech dereverberation or reverberation time reduction. Diffusion implicit bridges are a recently proposed domain translation…
