Lin-shan Lee

National Taiwan University — Taiwan

Computer Science · Physical Sciences

31h-index4.4kcitations405works1.02yr avg
OpenAlex↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Speech Recognition and Synthesis(243), Natural Language Processing Techniques(135), Speech and Audio Processing(134), Music and Audio Processing(98), Topic Modeling(76)

Publications405 total

SpeechDPR: End-To-End Spoken Passage Retrieval For Open-Domain Spoken Question Answering
2024· 3 cited
REBORN: Reinforcement-Learned Boundary Segmentation with Iterative Training for Unsupervised ASR
arXiv (Cornell University)·2024Open Access
SpeechDPR: End-to-End Spoken Passage Retrieval for Open-Domain Spoken Question Answering
arXiv (Cornell University)·2024Open Access
REBORN: Reinforcement-Learned Boundary Segmentation with Iterative Training for Unsupervised ASR
2024· 1 cited
DUAL: Discrete Spoken Unit Adaptive Learning for Textless Spoken Question Answering
Interspeech 2022·2022· 13 cited
DUAL: Discrete Spoken Unit Adaptive Learning for Textless Spoken Question Answering
arXiv (Cornell University)·2022· 2 citedOpen Access
Globecom 2021 Advisory Committee
2021 IEEE Global Communications Conference (GLOBECOM)·2021Open Access
Towards Lifelong Learning of End-to-End ASR
2021· 1 citedOpen Access
Fragmentvc: Any-To-Any Voice Conversion by End-To-End Extracting and Fusing Fine-Grained Voice Fragments with Attention
2021· 4 citedOpen Access
Spoken content retrieval and understanding using deep learning
Impact·2021Open Access
Defending Your Voice: Adversarial Attack on Voice Conversion
2021· 44 cited
End-to-End Whispered Speech Recognition with Frequency-Weighted Approaches and Pseudo Whisper Pre-training
2021· 10 cited
FragmentVC: Any-to-Any Voice Conversion by End-to-End Extracting and\n Fusing Fine-Grained Voice Fragments With Attention
arXiv (Cornell University)·2020· 1 citedOpen Access
SpeechBERT: An Audio-and-Text Jointly Learned Language Model for End-to-End Spoken Question Answering
2020· 83 cited
Defending Your Voice: Adversarial Attack on Voice Conversion
arXiv (Cornell University)·2020· 5 citedOpen Access
End-to-end Whispered Speech Recognition with Frequency-weighted Approaches and Pseudo Whisper Pre-training
arXiv (Cornell University)·2020· 2 citedOpen Access
End-to-end Whispered Speech Recognition with Frequency-weighted Approaches and Layer-wise Transfer Learning
arXiv (Cornell University)·2020Open Access
Sequence-to-Sequence Automatic Speech Recognition with Word Embedding Regularization and Fused Decoding
2020Open Access
Interrupted and Cascaded Permutation Invariant Training for Speech Separation
2020Open Access
Towards Unsupervised Speech Recognition and Synthesis with Quantized Speech Representation Learning
2020· 2 citedOpen Access
page 1 of 21Next →

Frequent Co-authors

Hung-yi Lee(17), Chiu-yu Tseng(9), Hsin‐Min Wang(7), Jia-Lin Shen(3), Jeih-weih Hung(3), Chia-Hao Shen(3), Chun-an Chan(3), Fu-Chiang Chou(3), Yu-An Chung(2), Chao-Chung Wu(2), Ju-Chieh Chou(2), Cheng-chieh Yeh(2), Yung-Sung Chuang(2), Chi-Liang Liu(2), Hung‐Yan Gu(2), Aaron Heidel(2), Berlin Chen(2), Yow-Bang Wang(2), Bo-Ren Bai(2), Chang-Wen Hsu(2)