March 27, 2023
Self-supervised learning leverages unlabeled data effectively, improving label efficiency and generalization to domains without labeled data. While recent work has studied generalization to more acoustic/linguistic domains, languages, and modalities, these investigations are limited to single-source speech with one primary speaker in the recording. This paper presents Cocktail HuBERT, a self-supervised learning framework that generalizes to mixture speech using a masked pseudo source separation objective. This objective encourages the model to identify the number of sources, separate and understand the context, and infer the content of masked regions represented as discovered units. Cocktail HuBERT outperforms state-of-the-art results with 69% lower WER on multispeaker ASR, 31% lower DER on diarization, and is competitive on single- and multi-speaker tasks from SUPERB.
Publisher
ICASSP
November 13, 2026
Ellis Brown, Chris Hoang, Shang-Wen Li, Mike Lewis, Marjan Ghazvininejad, Luke Zettlemoyer, Lucas Beyer, Mengye Ren, Jakob Verbeek, Saining Xie, Hu Xu
November 13, 2026
November 04, 2026
Yosuke Higuchi, Tom Fizycki, Mahi Luthra, Charles-Éric Saint-James, Azeez Syed, Angel Villar Corrales, Mido Assran, Nicolas Ballas, Jiayi Shen, Dongyan Lin, Phillip Rust, Surya Parimi, Vanessa Stark, Alexandre Allauzen, Balázs Kegl, Juan Pino, Emmanuel Dupoux
November 04, 2026
October 20, 2026
Kyuyoung Kim, Zilin Xiao, Zhiyuan Wang, Avinash Atreya, Ke Yang, Jinwoo Shin, Kecheng Hao
October 20, 2026
October 19, 2026
Muse Glimmer team
October 19, 2026
