CoBERT: Self-Supervised Speech Representation Learning Through Code Representation Learning

By Chutong Meng, Junyi Ao, Tom Ko, Mingxuan Wang, Haizhou Li. 2022

7 citations recorded by the source corpus.

Speech is the surface form of a finite set of phonetic units, which can be represented by discrete codes. We propose the Code BERT (CoBERT) approach for self-supervised speech representation learning. The idea is to convert an utterance to a sequence of discrete codes, and perform code representation learning, where we predict the code representations based on a masked view of the original speech input. Unlike the prior self-distillation approaches of which the teacher and the student are of the same modality, our target model predicts representations from a different modality. CoBERT outperforms the most recent state-of-the-art performance on the ASR task and brings significant improvements on the SUPERB speech translation (ST) task. Our code and models are released at https://github.com/mct10/CoBERT.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Rong Ye
2. Dong Zhang
3. Yaqian Zhou
4. Tom Ko
5. Mingxuan Wang
6. Daniel Povey
7. Sanjeev Khudanpur
8. Shinji Watanabe

Citations in the corpus

• DUB: Discrete Unit Back-translation for Speech Translation (2023, background): “…(Sicher-man and Adi, 2023; Lakhotia et al., 2021), leading to significant improvements in the speech tasks, such as automatic speech recognition (Meng et al., 2022), text-to-speech (Dunbar et al., 2019), and speech-to-speech translation (Zhang et al., 2021; Lee et al., 2022; Inaguma et al.,…”