MS-HuBERT: Mitigating Pre-training and Inference Mismatch in Masked Language Modelling methods for learning Speech Representations

Hemant Yadav, Sunayana Sitaram, Rajiv Ratn Shah. MS-HuBERT: Mitigating Pre-training and Inference Mismatch in Masked Language Modelling methods for learning Speech Representations. In Itshak Lapidot, Sharon Gannot, editors, 25th Annual Conference of the International Speech Communication Association, Interspeech 2024, Kos, Greece, September 1-5, 2024. ISCA, 2024. [doi]

Authors

Hemant Yadav

This author has not been identified. Look up 'Hemant Yadav' in Google

Sunayana Sitaram

This author has not been identified. Look up 'Sunayana Sitaram' in Google

Rajiv Ratn Shah

This author has not been identified. Look up 'Rajiv Ratn Shah' in Google