DinoSR: Self-Distillation and Online Clustering for Self-supervised Speech Representation Learning

Alexander H. Liu, Heng-Jui Chang, Michael Auli, Wei-Ning Hsu, James R. Glass

DinoSR: Self-Distillation and Online Clustering for Self-supervised Speech Representation Learning: 4 upvotes on Hugging Face Daily Papers, #5 of 16 papers on 2023-05-18. Day-by-day upvote history.

In this paper, we introduce self-distillation and online clustering for self-supervised speech representation learning (DinoSR) which combines masked language modeling, self-distillation, and online clustering. We show that these concepts complement each other and result in a strong representation learning model for speech. DinoSR first extracts contextualized embeddings from the input audio with a teacher network, then runs an online clustering system on the embeddings to yield a machine-discovered phone inventory, and finally uses the discretized tokens to guide a student network. We show that DinoSR surpasses previous state-of-the-art performance in several downstream tasks, and provide a detailed analysis of the model and the learned discrete units. The source code will be made available after the anonymity period.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.