Roger Tseng

Speech Processing & Machine Learning Lab @ntu_spml | National Taiwan University

[Roger Tseng @RogerTseng]

@PuyuanPeng Big congrats Puyuan!

[Roger Tseng @RogerTseng]

@Musical_sophie Hello! May I ask if it's still available? Sorry for the public comment, can't message you

[Roger Tseng @RogerTseng]

@itsaidanneee_ Yes! Could you send me a message so we can work out the details?

[Roger Tseng @RogerTseng]

Code, Video & Poster: https://t.co/5h3DzSlm4R
Full paper: https://t.co/vq9CnXibql

If you find this topic interesting, come chat!
I'll present our paper tomorrow from 3:40 PM - 5:10 PM at the Audio and Text Segmentation, Tagging and Parsing (SLT-P9) poster session at #ICASSP2023

[Roger Tseng @RogerTseng]

Unsupervised models that learn from raw speech have been limited to discovering acoustic/lexical information, such as phonemes or words.

Can we build unsupervised speech models that learn high-level linguistic information like syntax?

#ICASSP2023

[Roger Tseng @RogerTseng]

Another interesting discovery I wish to highlight is that Approach 2, when trained without any textual data, still shows signs of learning the different branching directions (a lang.-specific syntactic property) of English and Korean from speech directly.

[Sung-Feng Huang @SungFengHuang]

The research topic I've been working on for a long time is going to be incorporated into iOS 17 by Apple (of course, I didn't write the code in iOS): https://t.co/32tkhYAiXo

[arXiv Sound @ArxivSound]

``Analysing Discrete Self Supervised Speech Representation for Spoken Language Modeling. (arXiv:2301.00591v1 [https://t.co/JosjykNw75]),'' Amitay Sicherman, Yossi Adi, https://t.co/RN8v6GPEIx

[Roger Tseng @RogerTseng]

https://t.co/7dPcZjkmRC

[Hung-yi Lee (李宏毅) @HungyiLee2]

Abdelrahman Mohamed (Meta), Shinji Watanabe (CMU), Tara Sainath (Google), Karen Livescu (TTIC), Shang-Wen Li (Meta), Shu-wen Yang (NTU), Katrin Kirchhoff (Amazon), and I will give a tutorial about self-supervised learning for speech at NAACL 2022. https://t.co/fWt1oR6vaF

[Roger Tseng @RogerTseng]

Note to self to check this out later. What does this suggest for unsupervised language acquisition?

[Sepp Hochreiter @HochreiterSepp]

ArXiv https://t.co/wiFnvxf0ap: Empirical study on NNs for learning formal languages. RNNs and Transformers fail to generalize on non-regular tasks, LSTMs solve regular and counter-language tasks, and only NNs with structured memory learn context-free and context-sensitive tasks.

[Davis Blalock @davisblalock]

"Progressive Stage-wise Learning for Unsupervised Feature Representation Enhancement"

Someone finally beat regular backpropagation on a realistic problem—specifically, in the context of self-supervised learning (SSL). [1/12]

[Roger Tseng @RogerTseng]

Note to self to check this out later. What does this mean for unsupervised language acquisition?

[Sepp Hochreiter @HochreiterSepp]

ArXiv https://t.co/wiFnvxf0ap: Empirical study on NNs for learning formal languages. RNNs and Transformers fail to generalize on non-regular tasks, LSTMs solve regular and counter-language tasks, and only NNs with structured memory learn context-free and context-sensitive tasks.

[Yisong Yue @yisongyue]

Great advice by @EugeneVinitsky

-- Run the simplest experiment first

-- Write a mini-version of your paper before getting started

-- Keep an ultra-detailed notebook

-- Every paper should be reproducible via 1 script

-- Save all your videos in one place

-- Present regularly

[arXiv Sound @ArxivSound]

``Self-supervised Learning with Random-projection Quantizer for Speech Recognition. (arXiv:2202.01855v2 [https://t.co/JosjykNw75] UPDATED),'' Chung-Cheng Chiu, James Qin, Yu Zhang, Jiahui Yu, Yonghui Wu, https://t.co/YO0NaV6iVc

[Hao-Wen (Herman) Dong 董皓文 @hermanhwdong]

A very interesting read! There's indeed a huge gap between usable tech a musician would enjoy and "fancy" tech the AI community finds worth investigating!🧐

On the Development and Practice of AI Technology for Contemporary Popular Music Production: https://t.co/58A0LQVm75