Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox
Picture for Hung-yi Lee

Hung-yi Lee

Few-Shot Cross-Lingual TTS Using Transferable Phoneme Embedding



Wei-Ping Huang , Po-Chun Chen , Sung-Feng Huang , Hung-yi Lee

* Submitted to Interspeech 2022 
   Access Paper or Ask Questions

Tackling Spoofing-Aware Speaker Verification with Multi-Model Fusion



Haibin Wu , Jiawen Kang , Lingwei Meng , Yang Zhang , Xixin Wu , Zhiyong Wu , Hung-yi Lee , Helen Meng

Figure 1 for Tackling Spoofing-Aware Speaker Verification with Multi-Model Fusion
Figure 2 for Tackling Spoofing-Aware Speaker Verification with Multi-Model Fusion
Figure 3 for Tackling Spoofing-Aware Speaker Verification with Multi-Model Fusion
Figure 4 for Tackling Spoofing-Aware Speaker Verification with Multi-Model Fusion
* Accepted by Odyssey 2022 
   Access Paper or Ask Questions

Few-shot Prompting Towards Controllable Response Generation



Hsuan Su , Pohan Chi , Shih-Cheng Huang , Chung Ho Lam , Saurav Sahay , Shang-Tse Chen , Hung-yi Lee

Figure 1 for Few-shot Prompting Towards Controllable Response Generation
Figure 2 for Few-shot Prompting Towards Controllable Response Generation
Figure 3 for Few-shot Prompting Towards Controllable Response Generation
Figure 4 for Few-shot Prompting Towards Controllable Response Generation

   Access Paper or Ask Questions

Searching for the Essence of Adversarial Perturbations



Dennis Y. Menn , Hung-yi Lee

Figure 1 for Searching for the Essence of Adversarial Perturbations
Figure 2 for Searching for the Essence of Adversarial Perturbations
Figure 3 for Searching for the Essence of Adversarial Perturbations
Figure 4 for Searching for the Essence of Adversarial Perturbations

   Access Paper or Ask Questions

Structured Prompt Tuning



Chi-Liang Liu , Hung-yi Lee , Wen-tau Yih

Figure 1 for Structured Prompt Tuning
Figure 2 for Structured Prompt Tuning
Figure 3 for Structured Prompt Tuning
Figure 4 for Structured Prompt Tuning

   Access Paper or Ask Questions

Self-Supervised Speech Representation Learning: A Review



Abdelrahman Mohamed , Hung-yi Lee , Lasse Borgholt , Jakob D. Havtorn , Joakim Edin , Christian Igel , Katrin Kirchhoff , Shang-Wen Li , Karen Livescu , Lars Maaløe , Tara N. Sainath , Shinji Watanabe

Figure 1 for Self-Supervised Speech Representation Learning: A Review
Figure 2 for Self-Supervised Speech Representation Learning: A Review
Figure 3 for Self-Supervised Speech Representation Learning: A Review
Figure 4 for Self-Supervised Speech Representation Learning: A Review

   Access Paper or Ask Questions

Silence is Sweeter Than Speech: Self-Supervised Model Using Silence to Store Speaker Information



Chi-Luen Feng , Po-chun Hsu , Hung-yi Lee

Figure 1 for Silence is Sweeter Than Speech: Self-Supervised Model Using Silence to Store Speaker Information
Figure 2 for Silence is Sweeter Than Speech: Self-Supervised Model Using Silence to Store Speaker Information
Figure 3 for Silence is Sweeter Than Speech: Self-Supervised Model Using Silence to Store Speaker Information
Figure 4 for Silence is Sweeter Than Speech: Self-Supervised Model Using Silence to Store Speaker Information

   Access Paper or Ask Questions

Meta Learning for Natural Language Processing: A Survey



Hung-yi Lee , Shang-Wen Li , Ngoc Thang Vu

Figure 1 for Meta Learning for Natural Language Processing: A Survey
Figure 2 for Meta Learning for Natural Language Processing: A Survey
Figure 3 for Meta Learning for Natural Language Processing: A Survey
Figure 4 for Meta Learning for Natural Language Processing: A Survey
* Accepted by NAACL 2022 
   Access Paper or Ask Questions

AdapterBias: Parameter-efficient Token-dependent Representation Shift for Adapters in NLP Tasks



Chin-Lun Fu , Zih-Ching Chen , Yun-Ru Lee , Hung-yi Lee

Figure 1 for AdapterBias: Parameter-efficient Token-dependent Representation Shift for Adapters in NLP Tasks
Figure 2 for AdapterBias: Parameter-efficient Token-dependent Representation Shift for Adapters in NLP Tasks
Figure 3 for AdapterBias: Parameter-efficient Token-dependent Representation Shift for Adapters in NLP Tasks
Figure 4 for AdapterBias: Parameter-efficient Token-dependent Representation Shift for Adapters in NLP Tasks
* The first two authors contributed equally. This paper will be published in Findings of NAACL 2022 
   Access Paper or Ask Questions

XDBERT: Distilling Visual Information to BERT from Cross-Modal Systems to Improve Language Understanding



Chan-Jan Hsu , Hung-yi Lee , Yu Tsao

Figure 1 for XDBERT: Distilling Visual Information to BERT from Cross-Modal Systems to Improve Language Understanding
Figure 2 for XDBERT: Distilling Visual Information to BERT from Cross-Modal Systems to Improve Language Understanding
Figure 3 for XDBERT: Distilling Visual Information to BERT from Cross-Modal Systems to Improve Language Understanding
Figure 4 for XDBERT: Distilling Visual Information to BERT from Cross-Modal Systems to Improve Language Understanding
* ACL 2022 
   Access Paper or Ask Questions
1
2
3
4
5
6
7
>>