My ICASSP 2020 Programm
As this years ICASSP is a virtual conference and registratoion is free, I thought I just share my programm and the sessions that interested me the most. I will provide a link to every talk or session in my shedule. It’s packed with speech and deep learning for speech recognition topics so it will take a couple of weeks to process everything and be back on top of all the reading to do.
Below there is a list of all the workshops/sessions I will try to attend. Switching sessions should be easier than ever as nobody will be blocking your way! Though you still will have to make some hard choices when it comes to workshops or tutorials you might want to attend.
I especially would recommend checking out the late session on Friday were my friends Julian Fritsch and Juan Camilo Vasquez-Correa share their work. Have fun!
Monday
https://2020.ieeeicassp.org/program/schedule/tutorials/
- Monday, 4 May, 9:30 - 13:00
Sony Workshop
All about their successfull audio processing programs and audio source separation Deep Learning models. Not sure though, if I am really interested in their deep learning toolkit as I currently see not advantages to research only to production. https://2020.ieeeicassp.org/program/workshops/sony-workshop/
- Monday, 4 May, 9:30 - 13:00
Robust Data Science
Don’t let your model by brought down my non gaussians or outliers. Sounds very interesting. Session Link
- Monday, 4 May, 13:30 - 18:00
Graph Neural Networks
Sounds very interesting and the possibility to learn a lot, as I have no prior knowledge about them. The workshop description states that they will develop the concept of GNN’s and want to show how it helps to extend CNNs to the processing of high dimensional data in non-Euclidean domains. Session Link
Tueseday
- Tuesday, 5 May, 11:30 - 13:30
Deep Learning for Audio Classification
- Tuesday, 5 May, 11:30 - 13:30
Deep Learning for Speech and Audio
- Tuesday, 5 may, 15:00 - 16:00
Plenary talk: Deep Representation Learning
That should be an interesting one by Yoshua Bengio. Session Link
- Tuesday, 5 May, 16:30 - 18:30
TU2.I: Speech Analysis and Coding
Wednesday
- Wednesday, 6 May, 09:00 - 11:00
WE1.I: Acoustic Event Detection
- Wednesday, 6 May, 09:00 - 11:00
WE1.I: Deep Speaker Recognition Models
- Wednesday, 6 May, 09:00 - 11:00
WE1.I: Speech Recognition: Acoustic Modelling I
- Wednesday, 6 May, 11:30 - 13:30
WE2.I: Robust Speech Recognition
Thursday
- Thursday, 7 May, 09:00 - 11:00
TH1.I: Speaker Diarization and Characterization
- Thursday, 7 May, 09:00 - 11:00
TH1.I: Emotion
- Thursday, 7 May, 16:30 - 18:30
TH3.I: Speech Recognition: Representations and Embeddings
- Thursday, 7 May, 16:30 - 18:30
TH3.I: Speaker Recognition/Identification/Verification
- Thursday, 7 May, 16:30 - 18:30
TH3.I: Speech Recognition: Adaptation
Friday
- Friday, 8 May, 10:30 - 11:30
Plenary Talk: Conversational systems and the marriage of speech and language
Hopfully a very interesting talk, as this is where we all want to go. Processing speech from the signal to text representation and then extract meaning from it. Session Link
- Time: Friday, 8 May, 11:45 - 13:45
Speech Recognition: Acoustic Modelling II
- Friday, 8 May, 15:15 - 17:15
SPE-L17: Paralinguistics Modeling
Check out this session were my friends Julian Fritsch Idiap Research Institute and Juan Camilo Vasquez-Correa from Friedrich-Alexander Universität Erlangen-Nürnberg share their work. Session Link
- Time: Friday, 8 May, 15:15 - 17:15
General Speech Recognition