Final intern talk: Distilling Self-Supervised-Learning-Based Speech Quality Assessment into Compact
112
Microsoft Research335 тыс
Следующее
119 дней – 1 0461:02:04Популярные
05.12.23 – 3 74220:57
Опубликовано 27 августа 2024, 15:41
Speaker: Benjamin Stahl
Host: Hannes Gamper
In this talk, we explore advancements in computational models for speech quality assessment. Self-supervised learning models have emerged as powerful front-ends, outperforming supervised-only models. However, their large size renders them impractical for production tasks. We discuss strategies to distill self-supervised learning-based models into more compact forms using unlabeled data, achieving significant size reduction while maintaining an advantage over supervised-only models.
See more at microsoft.com/en-us/research/v...
Host: Hannes Gamper
In this talk, we explore advancements in computational models for speech quality assessment. Self-supervised learning models have emerged as powerful front-ends, outperforming supervised-only models. However, their large size renders them impractical for production tasks. We discuss strategies to distill self-supervised learning-based models into more compact forms using unlabeled data, achieving significant size reduction while maintaining an advantage over supervised-only models.
See more at microsoft.com/en-us/research/v...
Свежие видео
6 дней – 17 7130:21
13 дней – 86 81817:41
15 дней – 75254:37
15 дней – 140 6580:31Случайные видео
23 дня – 11 9773:34
294 дня – 5 3180:41
24.05.23 – 182:35:25
08.05.23 – 171 6020:33
04.02.21 – 635 9974:26
23.04.12 – 177 23624:46
6 дней – 864 4382:21:48
8 дней – 1695:20
9 дней – 85 69314:44
11 дней – 5 1920:31
