Hung-yi Lee (李宏毅) @HungyiLee2 Twitter profile

Last Seen Profiles

@Sauceriffic

@_valeriagandara

@livsdiors

@mariagardl

@Poffactio

@stoppkotte13046

@yemen775050

@hahalabubu

@tvrain_english

@penyukastw21

@AcleTomasini

@BobLonte

@kloven70

@c00chieeater900

@pebepe12

@ObsessedPianist

@Ochano16

@wangyusi1996

@stwmaniax

@florschulmaiste

@sandee_atchison

@elie2222

@Fatmacerann

@wedresday

@Web3_Memento

@hazemmohammad22

@adamkocvara

@yumejiya1

@stw_pdg

@luizcunhao

@FRMSEagles

@ibubohay2

@whotfisLarita

@Kaede4760816970

@bokeplokalmalam

@FortnitePL

Hung-yi Lee (李宏毅)

@HungyiLee2

7 months

Fine-tuning the LLaMA-2-Chat model may degrade its original capabilities (). But here's a lifeline: Chat Vector () keeps a chat model's original capability (it also works on Mistral). Recommend to everyone fine-tuning their LLMs.

2

81

365

Hung-yi Lee (李宏毅)

@HungyiLee2

6 months

Discover the cutting-edge world of spoken LLMs with this comprehensive survey! link:

3

58

211

Hung-yi Lee (李宏毅)

@HungyiLee2

8 months

Thrilled to see the team continuously enhancing the materials based on my online lectures! 🚀 Despite never having met them in person, their dedication truly impresses me. Check out the amazing work at

GitHub - datawhalechina/leedl-tutorial: 《李宏毅深度学习教程》（李宏毅老师推荐👍，苹果书🍎），PDF下载地址：https://github.com/d...

《李宏毅深度学习教程》（李宏毅老师推荐👍，苹果书🍎），PDF下载地址：https://github.com/datawhalechina/leedl-tutorial/releases - datawhalechina/leedl-tutorial

github.com

4

35

202

Hung-yi Lee (李宏毅)

@HungyiLee2

2 years

I will attend NAACL 2022 to present the work, "Meta Learning for Natural Language Processing: A Survey" (). The overview paper is written by me, Shang-Wen Li and Ngoc Thang Vu.

Meta Learning for Natural Language Processing: A Survey

Deep learning has been the mainstream technique in natural language processing (NLP) area. However, the techniques require many labeled data and are less generalizable across domains....

arxiv.org

0

40

197

Hung-yi Lee (李宏毅)

@HungyiLee2

28 days

I'll give an overview talk on Spoken Language Models at INTERSPEECH 2024! Join me tomorrow, September 3rd, from 13:30 to 14:10 in the "Lasso" room. link of slides:

Spoken LLM (v11).pdf

drive.google.com

8

35

193

Hung-yi Lee (李宏毅)

@HungyiLee2

3 years

Receive the YouTube Creator Silver Award for 100,000 subscribers. When I started uploading videos about DL to YouTube in the fall of 2016, I never imagined this achievement. Thanks to all subscribers. We learn together.

7

12

181

Hung-yi Lee (李宏毅)

@HungyiLee2

2 years

Two tutorials at INTERSPEECH'22. Self-Supervised Representation Learning for Speech Processing slides: Neural Speech Synthesis slides:

0

33

173

Hung-yi Lee (李宏毅)

@HungyiLee2

22 days

Congratulations to the SUPERB Team! Our work on the Speech Processing Universal PERformance Benchmark (SUPERB) has been ranked 7th among the most cited papers at INTERSPEECH over the past five years! A big round of applause to everyone involved.

4

18

171

Hung-yi Lee (李宏毅)

@HungyiLee2

2 months

The paper "Self-Supervised Speech Representation Learning: A Review" is a top 25 download in IEEE JSTSP! The authors will discuss the latest in speech foundation models. Time: 1:00 PM ET, 6 Aug 2024 Registration page:

0

19

135

Hung-yi Lee (李宏毅)

@HungyiLee2

7 months

Recent years have witnessed significant developments in audio codec models (an overview figure from ). We introduce Codec-SUPERB () to boost fair and comprehensive comparison. Leaderboard:

1

21

121

Hung-yi Lee (李宏毅)

@HungyiLee2

3 months

Launched "Intro to Generative AI" course with 1000+ students this spring! Thanks to @dcml0714 for being head TA. Using LLMs to evaluate assignments, inspired by his ACL paper (). Check what we learned:

Large Language Model as an Assignment Evaluator: Insights,...

Using large language models (LLMs) for automatic evaluation has become an important evaluation method in NLP research. However, it is unclear whether these LLM-based evaluators can be applied in...

arxiv.org

Cheng Han Chiang (姜成翰)

@dcml0714

3 months

❗ New Paper❗ 📄 In '23, we proposed LLM-as-judge for NLP research 🤔 Any real-world applications? 💯 Now, we use LLM as an automatic assignment evaluator in a course with 1000+ students at National Taiwan University, led by @HungyiLee2 with me as a TA 🔗

1

8

49

0

14

117

Hung-yi Lee (李宏毅)

@HungyiLee2

3 months

Exploring task vectors: Not just for text LLMs learning new languages (), but also helpful for speech models. Train with domain-specific synthetic data, then adapt using a task vector for real speech ().

2

20

114

Hung-yi Lee (李宏毅)

@HungyiLee2

1 year

Attending #ICASSP2023 in Rhodes, Greece? Don't miss the workshop on "Self-supervision in Audio, Speech & Beyond". Dive deep into the advancements in self-supervised learning. Catch me delivering the workshop keynote @ Jupiter Ballroom, 8:40 a.m. GMT+3.

ICASSP SASB 2023 - Program

The SASB 2023 workshop will be held on the 10th of June 2023 at the same venue from the ICASSP 2023 conference, at the Jupiter Ballroom. Detailed poster session information can be found at the end of...

sites.google.com

2

17

96

Hung-yi Lee (李宏毅)

@HungyiLee2

4 months

What's the best token unit for speech in LLMs? Dive into this question at the Codec-SUPERB Challenge at SLT 2024! We're now accepting submissions. For more information, please visit the challenge's webpage:

0

6

91

Hung-yi Lee (李宏毅)

@HungyiLee2

2 years

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.

Tutorials

NAACL 2022 Tutorials

2022.naacl.org

0

15

87

Hung-yi Lee (李宏毅)

@HungyiLee2

10 months

Excited to speak at #ASRU2023 tomorrow (December 20) at 11:30 AM (GMT+8) on "The Journey of Advancements in Speech Foundation Models"! We'll explore the evolution of speech foundation models. Below, please find the slides:

SpeechLLM ASRU 2023 (v9).pdf

drive.google.com

2

23

78

Hung-yi Lee (李宏毅)

@HungyiLee2

5 months

Watched OpenAI's demo, amazed by GPT-4's speech understanding & interaction. Dynamic-SUPERB is collecting speech tasks to challenge foundation models. Submit your innovative tasks to advance speech processing! More info:

GitHub - dynamic-superb/dynamic-superb: The official repository of Dynamic-SUPERB.

The official repository of Dynamic-SUPERB. Contribute to dynamic-superb/dynamic-superb development by creating an account on GitHub.

github.com

3

13

80

Hung-yi Lee (李宏毅)

@HungyiLee2

5 months

Join us for the Dynamic-SUPERB call-for-tasks event. Submit your innovative task to challenge the speech foundation models that can understand task instruction. Let's push the boundaries of what speech foundation models can do!

1

19

75

Hung-yi Lee (李宏毅)

@HungyiLee2

2 months

Congratulations to Cheng Han Chiang ( @dcml0714 ) for winning the Best Paper Award at the ACL24 Knowledgeable LMs workshop! This paper tackles the issue I mentioned in my course () — combining correct facts can sometimes result in an incorrect response.

Cheng Han Chiang (姜成翰)

@dcml0714

2 months

🎉 Very honored and flattered to receive best paper award at the KnowledgeableLM workshop at #ACL2024 It means A LOT to be granted an award by community members who work on knowledge and LMs. I'll keep working on topics in this direction! Great collaboration with @HungyiLee2

5

6

65

4

70

Hung-yi Lee (李宏毅)

@HungyiLee2

3 years

Self-Supervised Learning for Speech and Audio Processing Workshop @ AAAI 2022 ===== Website: Submission Deadline: November 15th, 2021 (Anywhere on Earth) -> Less than 24 hours! Submission website: Contact: sas.aaai.2022 @gmail .com

0

18

64

Hung-yi Lee (李宏毅)

@HungyiLee2

1 year

If you're participating in ICML 2023, do not miss the workshop "What's Left to TEACH (Trustworthy, Enhanced, Adaptable, Capable, and Human-centric) Chatbots?" It's happening today in Room 303. #ICML2023

TEACH @ ICML-23

Arvind's Talk is uploaded!

sites.google.com

0

9

60

Hung-yi Lee (李宏毅)

@HungyiLee2

3 years

Workshop on Self-supervised Learning for Audio and Speech Processing @ AAAI 2022 starts at 8:50 a.m., EST (9:50 p.m. GMT+8), February 28. If you want to hear about exciting new advances in self-supervised learning, don't miss it.

1

8

54

Hung-yi Lee (李宏毅)

@HungyiLee2

1 year

Join us for ASRU's satellite event - the Workshop on Speech Foundation Models & Performance Benchmarks (SPARKS), on Dec 16th, 2023, in Taiwan. 📌 Paper Submission: Oct 19th 🔗 Webpage: Tip: When registering for ASRU, tick the SPARKS option. #ASRU

SPARKS Workshop

sites.google.com

0

18

54

Hung-yi Lee (李宏毅)

@HungyiLee2

5 months

Join the Webinar Series for Advancements in Audio, Speech and Language Technology. Next up: "End-to-End Automatic Speech Recognition" by Dr. Jinyu Li from Microsoft on May 10 @ 1:00 pm EDT (May 11 @ 1:00 am Taiwan time) Register now:

0

9

53

Hung-yi Lee (李宏毅)

@HungyiLee2

2 years

There have been many new developments in pre-trained LM recently. I will give a tutorial on the latest advances in pretrained LMs with Cheng-Han Chiang @dcml0714 and @YungSungChuang at AACL-IJCNLP 2022 from 5:00 p.m. to 8:00 p.m. on Nov 20th (Taiwan time).

1

9

50

Hung-yi Lee (李宏毅)

@HungyiLee2

4 months

Webinar Series for Advancements in Audio, Speech, and Language Technology Next Webinar: Neural Target Speech and Sound Extraction: An Overview Speaker: Dr. Marc Delcroix Time: June 6, 2024, 7:30 PM (NY Time) Register:

This link will take you to a page that’s not on LinkedIn

lnkd.in

1

6

40

Hung-yi Lee (李宏毅)

@HungyiLee2

2 months

SPS SLTC/AASP TC Webinar Don't miss out on recent advances in speech separation, end-to-end modeling, speaker diarization, and more! Speaker: Dr. Takuya Yoshioka, Director of Research at Assembly AI Inc. Time: 1:00 PM ET, 23 July 2024 Register here:

Attend an Event

signalprocessingsociety.org

0

6

38

Hung-yi Lee (李宏毅)

@HungyiLee2

10 months

Join us for an enlightening afternoon with distinguished speech researchers, Dr. Andreas Stolcke and Prof. Torbjørn Svendsen. Their talks will take place at Barry Lam Hall (博理館) (), R101 (Auditorium), NTU, on December 21st, starting at 2:20PM. #ASRU2023

0

6

32

Hung-yi Lee (李宏毅)

@HungyiLee2

26 days

Excited to speak at CHIME 2024, collocated with INTERSPEECH! Join me on Sept 6th, 14:00-15:00, for "Teaching New Skills to Foundation Models: Insights and Experiences." Learn why fine-tuning is more challenging than it seems! Workshop link:

CHiME 2024 Workshop

September 6, 2024, Kos International Convention Centre (KICC), Kos Island, Greece

www.chimechallenge.org

0

4

31

Hung-yi Lee (李宏毅)

@HungyiLee2

3 years

Three years ago, when we first tried to use GAN to realize unsupervised ASR (), I thought the idea was sci-fi. But a few days ago, Facebook AI pushed the idea of using GAN for unsupervised ASR to 5.9% WER on Librispeech ().

wav2vec Unsupervised: Speech recognition without supervision

To enable speech recognition technology for many more languages spoken around the globe, Facebook AI is releasing wav2vec Unsupervised, a new method to train models with no supervision whatsoever....

ai.meta.com

0

10

28

Hung-yi Lee (李宏毅)

@HungyiLee2

2 years

AlphaTensor Explained:

AlphaTensor: 用增強式學習 (Reinforcement Learning) 找出更有效率的矩陣相乘演算法 (線性代數...

slides: https://drive.google.com/file/d/1MtNUrZrIbzJmR1WaimBesvEsnDImOyAv/view?usp=sharingPaper link: https://www.nature.com/articles/s41586-022-05172-4

www.youtube.com

1

12

29

Hung-yi Lee (李宏毅)

@HungyiLee2

3 years

HuBERT achieves surprisingly good performance on the speech version of GLUE, that is, SUPERB (). As we all know, SuperGLUE is constructed after the pre-trained LMs achieve superhuman performance on GLUE. Maybe we have to consider SuperSUPERB now.

AI at Meta

@AIatMeta

3 years

We are releasing pretrained HuBERT speech representation models and code for recognition and generation. By alternating clustering and prediction steps, HuBERT learns to invent discrete tokens representing continuous spoken input. Learn more:

3

85

286

0

2

4