Timezone: »
While audio-visual speech models can yield superior performance and robustness compared to audio-only models, their development and adoption are hindered by the lack of labeled and unlabeled audio-visual data and the cost to deploy one model per modality. In this paper, we present u-HuBERT, a self-supervised pre-training framework that can leverage both multimodal and unimodal speech with a unified masked cluster prediction objective. By utilizing modality dropout during pre-training, we demonstrate that a single fine-tuned model can achieve performance on par or better than the state-of-the-art modality-specific models. Moreover, our model fine-tuned only on audio can perform well with audio-visual and visual speech input, achieving zero-shot modality generalization for multiple speech processing tasks. In particular, our single model yields 1.2%/1.4%/27.2% speech recognition word error rate on LRS3 with audio-visual/audio/visual input.
Author Information
Wei-Ning Hsu (Facebook, Inc.)
Bowen Shi (TTIC)
More from the Same Authors
-
2023 Poster: Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale »
Matthew Le · Bowen Shi · Apoorv Vyas · Brian Karrer · Leda Sari · Yossi Adi · Vimal Manohar · Jay Mahadeokar · Wei-Ning Hsu -
2021 Poster: Unsupervised Speech Recognition »
Alexei Baevski · Wei-Ning Hsu · Alexis CONNEAU · Michael Auli -
2021 Oral: Unsupervised Speech Recognition »
Alexei Baevski · Wei-Ning Hsu · Alexis CONNEAU · Michael Auli -
2020 : HUBERT: How much can a bad teacher benefit ASR pre-training? »
Wei-Ning Hsu -
2020 : Text-Free Image-to-Speech Synthesis Using Learned Segmental Units »
Wei-Ning Hsu -
2018 : Coffee break + posters 2 »
Jan Kremer · Erik McDermott · Brandon Carter · Albert Zeyer · Andreas Krug · Paul Pu Liang · Katherine Lee · Dominika Basaj · Abelino Jimenez · Lisa Fan · Gautam Bhattacharya · Tzeviya S Fuchs · David Gifford · Loren Lugosch · Orhan Firat · Benjamin Baer · JAHANGIR ALAM · Jamin Shin · Mirco Ravanelli · Paul Smolensky · Zining Zhu · Hamid Eghbal-zadeh · Skyler Seto · Imran Sheikh · Joao Felipe Santos · Yonatan Belinkov · Nadir Durrani · Oiwi Parker Jones · Shuai Tang · André Merboldt · Titouan Parcollet · Wei-Ning Hsu · Krishna Pillutla · Ehsan Hosseini-Asl · Monica Dinculescu · Alexander Amini · Ying Zhang · Taoli Cheng · Alain Tapp -
2018 : Coffee break + posters 1 »
Samuel Myer · Wei-Ning Hsu · Jialu Li · Monica Dinculescu · Lea Schönherr · Ehsan Hosseini-Asl · Skyler Seto · Oiwi Parker Jones · Imran Sheikh · Thomas Manzini · Yonatan Belinkov · Nadir Durrani · Alexander Amini · Johanna Hansen · Gabi Shalev · Jamin Shin · Paul Smolensky · Lisa Fan · Zining Zhu · Hamid Eghbal-zadeh · Benjamin Baer · Abelino Jimenez · Joao Felipe Santos · Jan Kremer · Erik McDermott · Andreas Krug · Tzeviya S Fuchs · Shuai Tang · Brandon Carter · David Gifford · Albert Zeyer · André Merboldt · Krishna Pillutla · Katherine Lee · Titouan Parcollet · Orhan Firat · Gautam Bhattacharya · JAHANGIR ALAM · Mirco Ravanelli -
2017 Poster: Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data »
Wei-Ning Hsu · Yu Zhang · James Glass