[icassp 2020] mockingjay: unsupervised speech representation learning (speaker: andy t. liu)
Published 4 years ago • 5.1K plays • Length 15:00Download video MP4
Download video MP3
Similar videos
-
![[icassp 2020] towards unsupervised speech recognition and synthesis (speaker: tao tu)](https://i.ytimg.com/vi/cnZdfLSqwiE/mqdefault.jpg)
11:55
[icassp 2020] towards unsupervised speech recognition and synthesis (speaker: tao tu)
-
![[icassp 2020] what does a network layer hear? (speaker: chung-yi li)](https://i.ytimg.com/vi/6gtn7H-pWr8/mqdefault.jpg)
13:30
[icassp 2020] what does a network layer hear? (speaker: chung-yi li)
-
![[icassp 2020] one-shot voice conversion by vector quantization (speaker: da-yi wu)](https://i.ytimg.com/vi/W3t8FHgV90M/mqdefault.jpg)
13:37
[icassp 2020] one-shot voice conversion by vector quantization (speaker: da-yi wu)
-
![[icassp 2020] interrupted and cascaded pit for speech separation (speaker: gene-ping yang)](https://i.ytimg.com/vi/RUhkc6ihyYI/mqdefault.jpg)
11:53
[icassp 2020] interrupted and cascaded pit for speech separation (speaker: gene-ping yang)
-
![[icassp 2020] defense against adversarial attacks on spoofing countermeasures (speaker: haibin wu)](https://i.ytimg.com/vi/sKwz5GvxGgI/mqdefault.jpg)
12:48
[icassp 2020] defense against adversarial attacks on spoofing countermeasures (speaker: haibin wu)
-
1:41
review speaker split zevox zs 622 bc, mid bahan carbon kevlar
-
![[icassp 2020] training code-switching language model with monolingual data (speaker: shun-po chuang)](https://i.ytimg.com/vi/qf0j0A0-SVM/mqdefault.jpg)
12:06
[icassp 2020] training code-switching language model with monolingual data (speaker: shun-po chuang)
-
![[icassp 2020] asr with word embedding regularization and fused decoding (speaker: alexander h. liu)](https://i.ytimg.com/vi/1j46kdawA4Q/mqdefault.jpg)
11:09
[icassp 2020] asr with word embedding regularization and fused decoding (speaker: alexander h. liu)
-
second joint public hearing of the house quad-committee
-
![[interspeech 2020] defense for black-box attacks on anti-spoofing models by self-supervised learning](https://i.ytimg.com/vi/k81atCYWpzg/mqdefault.jpg)
14:57
[interspeech 2020] defense for black-box attacks on anti-spoofing models by self-supervised learning
-
![[interspeech 2020] understanding self-attention of self-supervised audio transformers](https://i.ytimg.com/vi/RJq_B416V1Q/mqdefault.jpg)
14:57
[interspeech 2020] understanding self-attention of self-supervised audio transformers
-
0:16
superresolution for thicker samples, part 2
-
7:28
s24 recitation 0i: datasets part 1
-
0:15
my wacky in-sync dance
-
0:31
az-02 "clear choice"
-
3:01
rrs 2016 plenary speaker jac nickoloff
-
![[dlhlp 2020] speech separation (2/2) - tasnet](https://i.ytimg.com/vi/G0O1A7lONSY/mqdefault.jpg)
41:04
[dlhlp 2020] speech separation (2/2) - tasnet
-
0:59
covid-19 watch: 4,334 new cases, nationwide icu bed usage at 58.5pc