Benjamin Bolte
Benjamin Bolte has 2 papers on this site, in 2021, most of them on Language models & pretraining, Speech & spoken language; often with Abdelrahman Mohamed, Kushal Lakhotia, Wei-Ning Hsu.
No OpenAlex profile matched yet.
Topics
Papers
- HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units (2021 · 3 441 citations)
Unsupervised speech representation learning is harder than in text or vision for three reasons. Each utterance contains many sounds, there is no ready-made inventory of discrete units, and unit boundaries are unknown. HuBERT (Hidden-Unit BERT) handles this by first clustering acoustic frames offline, starting with… - On Generative Spoken Language Modeling from Raw Audio (2021 · 165 citations)
The paper introduces Generative Spoken Language Modeling (GSLM): learning both the sound system and the linguistic structure of a language directly from raw audio, without transcripts or labels.
Co-authors here
- Abdelrahman Mohamed ×2
- Kushal Lakhotia ×2
- Wei-Ning Hsu ×2
- Alexei Baevski
- Emmanuel Dupoux
- Eugene Kharitonov
- Jade Copet
- Ruslan Salakhutdinov
- Yao-Hung Hubert Tsai
- Yossi Adi
Cited by
This page in Markdown → https://md.research.elamur.ai/free/en/authors/benjamin-bolte/