ISCA-SIGML
@iscasigml
Followers
72
Following
0
Media
16
Statuses
41
ISCA Special Interest Group on Machine Learning for Speech and Language Technology (SIGML)
Joined March 2021
The recording of Saurabhchand's talk "Segmental Contrastive Predictive Coding for Unsupervised Acoustic Segmentation" is now available at
In our next meeting (and the last meeting this year), we are happy to have Saurabhchand Bhati from @jhuclsp to talk about segmental contrastive predictive coding. More details:
0
0
0
The recording of @mzboito's talk "Attention-based Unsupervised Word Segmentation" is now available at The audio before 37:10 was missing due to technical issues. Apologies to the speaker and the people who cannot attend the talk.
0
0
4
In our next meeting (and the last meeting this year), we are happy to have Saurabhchand Bhati from @jhuclsp to talk about segmental contrastive predictive coding. More details:
0
1
0
The recording for Kushal Lakhotia's talk "Generative Spoken Language Modeling from Raw Audio" is now available at
0
1
3
The recording for Shammur Absar Chowdhury's talk "Fine-Grained Interpretation of End-to-End Speech Models" is now available at
In our next meeting, 2 Nov at 12pm (UTC+0), we are happy to have Shammur Absar Chowdhury from @QatarComputing to talk about the analysis of end-to-end speech models. More details:
0
0
1
In our next meeting, 2 Nov at 12pm (UTC+0), we are happy to have Shammur Absar Chowdhury from @QatarComputing to talk about the analysis of end-to-end speech models. More details:
0
1
0
The recording for Kaizhi Qian's talk "Unsupervised Speech Disentanglement for Speech Style Transfer" is now available at
0
0
1
The recordings for MLSLP 2021 are now available. Part 1: Part 2: Apologies to the speakers and to the audience who cannot attend. Due to technical difficulty, we lost some part of Jan Chorowski's and Michael Auli's talk.
Our workshop MLSLP 2021, a satellite workshop of Interspeech 2021, is welcoming submissions of 4-page papers and 2-page abstracts!. More details:
0
1
1
The schedule for MLSLP 2021 is now on the website. We have a great set of talks on cutting-edge unsupervised and self-supervised learning! @INTERSPEECH2021. More details:
Our workshop MLSLP 2021, a satellite workshop of Interspeech 2021, is welcoming submissions of 4-page papers and 2-page abstracts!. More details:
0
4
3
We still have a few slots available. Registration will be open until all slots are filled up. If you plan to attend the workshop, please register!.
Our workshop MLSLP 2021, a satellite workshop of Interspeech 2021, is welcoming submissions of 4-page papers and 2-page abstracts!. More details:
0
0
0
The recording of Lea's talk "Adversarially Robust Speech Recognition" is now available at
In our next meeting, 11 Aug at 4pm (UTC+0), we are happy to have Lea Shoenherr @leaschnherr from @CASA_EXC to talk about adversarial robustness of speech and speaker recognition!. More details:
0
1
2
The recording of Felix's talk "From Supervised to Self-Supervised: Phoneme Boundary Detection using Novel Neural Architectures" is now available at
In our next meeting, 28 Jul at 4pm (UTC+0), we are happy to have Felix Kreuk @FelixKreuk from @ubarilan to talk about self-supervised phoneme segmentation!. More details:
0
0
1
In our next meeting, 11 Aug at 4pm (UTC+0), we are happy to have Lea Shoenherr @leaschnherr from @CASA_EXC to talk about adversarial robustness of speech and speaker recognition!. More details:
0
0
5
Registration for MLSLP 2021 is now open!. More details:
Our workshop MLSLP 2021, a satellite workshop of Interspeech 2021, is welcoming submissions of 4-page papers and 2-page abstracts!. More details:
0
0
0
Reminder: Felix Kreuk is speaking this Wednesday! Subscribe to our mailing list to joint the meeting
In our next meeting, 28 Jul at 4pm (UTC+0), we are happy to have Felix Kreuk @FelixKreuk from @ubarilan to talk about self-supervised phoneme segmentation!. More details:
0
0
0
In our next meeting, 28 Jul at 4pm (UTC+0), we are happy to have Felix Kreuk @FelixKreuk from @ubarilan to talk about self-supervised phoneme segmentation!. More details:
0
2
2
The recording for Weiran's talk "Improving ASR for Small Data with Self-Training and Pre-Training" is now available at
In our next meeting, 14 Jul at 6pm (UTC+0), we are happy to have Weiran Wang from @Google to talk about self-training and pre-training for ASR. More details:
0
0
2
Reminder: Weiran Wang is speaking this Wednesday! Subscribe to our mailing list to joint the meeting
In our next meeting, 14 Jul at 6pm (UTC+0), we are happy to have Weiran Wang from @Google to talk about self-training and pre-training for ASR. More details:
0
0
1
The recording of Zack's talk "Controlling Prosody with Insufficient Context" is now available at
In our next meeting, 30 Jun at 4pm (UTC+0), we are happy to have Zack Hodari from @InfAtEd to talk about controlling prosody in TTS. More details:
0
0
0
In our next meeting, 14 Jul at 6pm (UTC+0), we are happy to have Weiran Wang from @Google to talk about self-training and pre-training for ASR. More details:
0
2
5