Final intern talk: Distilling Self-Supervised-Learning-Based Speech Quality Assessment into Compact
104
Microsoft Research334 тыс
Следующее
88 дней – 1 0291:02:04Популярные
297 дней – 1 7263:27
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
3 дня – 1 5559:21
4 дня – 1972:41
4 дня – 1 007 69716:58
4 дня – 6 2192:08
29 дней – 6 8210:18Случайные видео
179 дней – 4 4390:28
232 дня – 52 3390:33
21.07.23 – 29446:34
2 дня – 3971:32
3 дня – 1 6160:16
4 дня – 17 74127:30
4 дня – 976 5401:00
5 дней – 8 2212:06
2 дня – 14 60121:30