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 Lin-shan Lee

Towards Lifelong Learning of End-to-end ASR


Apr 04, 2021
Heng-Jui Chang, Hung-yi Lee, Lin-shan Lee

* Submitted to INTERSPEECH 2021 

  Access Paper or Ask Questions

FragmentVC: Any-to-Any Voice Conversion by End-to-End Extracting and Fusing Fine-Grained Voice Fragments With Attention


Oct 27, 2020
Yist Y. Lin, Chung-Ming Chien, Jheng-Hao Lin, Hung-yi Lee, Lin-shan Lee

* Submitted to ICASSP 2021, equal contribution from first two authors 

  Access Paper or Ask Questions

Defending Your Voice: Adversarial Attack on Voice Conversion


May 18, 2020
Chien-yu Huang, Yist Y. Lin, Hung-yi Lee, Lin-shan Lee

* Submitted to INTERSPEECH 2020 

  Access Paper or Ask Questions

End-to-end Whispered Speech Recognition with Frequency-weighted Approaches and Layer-wise Transfer Learning


May 05, 2020
Heng-Jui Chang, Alexander H. Liu, Hung-yi Lee, Lin-shan Lee

* submitted to INTERSPEECH 2020 

  Access Paper or Ask Questions

Sequence-to-sequence Automatic Speech Recognition with Word Embedding Regularization and Fused Decoding


Oct 28, 2019
Alexander H. Liu, Tzu-Wei Sung, Shun-Po Chuang, Hung-yi Lee, Lin-shan Lee

* under review ICASSP 2020 

  Access Paper or Ask Questions

Towards Unsupervised Speech Recognition and Synthesis with Quantized Speech Representation Learning


Oct 28, 2019
Alexander H. Liu, Tao Tu, Hung-yi Lee, Lin-shan Lee

* under review ICASSP 2020 

  Access Paper or Ask Questions

Interrupted and cascaded permutation invariant training for speech separation


Oct 28, 2019
Gene-Ping Yang, Szu-Lin Wu, Yao-Wen Mao, Hung-yi Lee, Lin-shan Lee


  Access Paper or Ask Questions

Improved Speech Separation with Time-and-Frequency Cross-domain Joint Embedding and Clustering


Apr 16, 2019
Gene-Ping Yang, Chao-I Tuan, Hung-Yi Lee, Lin-shan Lee

* Submitted to Interspeech 2019 

  Access Paper or Ask Questions

From Semi-supervised to Almost-unsupervised Speech Recognition with Very-low Resource by Jointly Learning Phonetic Structures from Audio and Text Embeddings


Apr 10, 2019
Yi-Chen Chen, Sung-Feng Huang, Hung-yi Lee, Lin-shan Lee


  Access Paper or Ask Questions

Completely Unsupervised Phoneme Recognition By A Generative Adversarial Network Harmonized With Iteratively Refined Hidden Markov Models


Apr 08, 2019
Kuan-Yu Chen, Che-Ping Tsai, Da-Rong Liu, Hung-Yi Lee, Lin-shan Lee


  Access Paper or Ask Questions

Improved Audio Embeddings by Adjacency-Based Clustering with Applications in Spoken Term Detection


Nov 07, 2018
Sung-Feng Huang, Yi-Chen Chen, Hung-yi Lee, Lin-shan Lee


  Access Paper or Ask Questions

Adversarial Training of End-to-end Speech Recognition Using a Criticizing Language Model


Nov 02, 2018
Alexander H. Liu, Hung-yi Lee, Lin-shan Lee

* under review ICASSP 2019 

  Access Paper or Ask Questions

Almost-unsupervised Speech Recognition with Close-to-zero Resource Based on Phonetic Structures Learned from Very Small Unpaired Speech and Text Data


Oct 30, 2018
Yi-Chen Chen, Chia-Hao Shen, Sung-Feng Huang, Hung-yi Lee, Lin-shan Lee


  Access Paper or Ask Questions

Phonetic-and-Semantic Embedding of Spoken Words with Applications in Spoken Content Retrieval


Sep 03, 2018
Yi-Chen Chen, Sung-Feng Huang, Chia-Hao Shen, Hung-yi Lee, Lin-shan Lee

* Accepted by SLT2018 

  Access Paper or Ask Questions

Segmental Audio Word2Vec: Representing Utterances as Sequences of Vectors with Applications in Spoken Term Detection


Aug 07, 2018
Yu-Hsuan Wang, Hung-yi Lee, Lin-shan Lee


  Access Paper or Ask Questions

Multi-target Voice Conversion without Parallel Data by Adversarially Learning Disentangled Audio Representations


Jun 24, 2018
Ju-chieh Chou, Cheng-chieh Yeh, Hung-yi Lee, Lin-shan Lee

* Accepted to Interspeech 2018 

  Access Paper or Ask Questions

Transcribing Lyrics From Commercial Song Audio: The First Step Towards Singing Content Processing


Apr 15, 2018
Che-Ping Tsai, Yi-Lin Tuan, Lin-shan Lee

* Accepted as a conference paper at ICASSP 2018 

  Access Paper or Ask Questions

Scalable Sentiment for Sequence-to-sequence Chatbot Response with Performance Analysis


Apr 07, 2018
Chih-Wei Lee, Yau-Shian Wang, Tsung-Yuan Hsu, Kuan-Yu Chen, Hung-Yi Lee, Lin-shan Lee


  Access Paper or Ask Questions

Completely Unsupervised Phoneme Recognition by Adversarially Learning Mapping Relationships from Audio Embeddings


Apr 01, 2018
Da-Rong Liu, Kuan-Yu Chen, Hung-Yi Lee, Lin-shan Lee


  Access Paper or Ask Questions

Order-Preserving Abstractive Summarization for Spoken Content Based on Connectionist Temporal Classification


Nov 16, 2017
Bo-Ru Lu, Frank Shyu, Yun-Nung Chen, Hung-Yi Lee, Lin-shan Lee

* Accepted by Interspeech 2017 

  Access Paper or Ask Questions

Abstractive Headline Generation for Spoken Content by Attentive Recurrent Neural Networks with ASR Error Modeling


Dec 26, 2016
Lang-Chi Yu, Hung-yi Lee, Lin-shan Lee


  Access Paper or Ask Questions

An Iterative Deep Learning Framework for Unsupervised Discovery of Speech Features and Linguistic Units with Applications on Spoken Term Detection


Feb 01, 2016
Cheng-Tao Chung, Cheng-Yu Tsai, Hsiang-Hung Lu, Chia-Hsiang Liu, Hung-yi Lee, Lin-shan Lee

* arXiv admin note: text overlap with arXiv:1506.02327 

  Access Paper or Ask Questions

Towards Structured Deep Neural Network for Automatic Speech Recognition


Nov 08, 2015
Yi-Hsiu Liao, Hung-yi Lee, Lin-shan Lee

* arXiv admin note: text overlap with arXiv:1506.01163 

  Access Paper or Ask Questions

Unsupervised Spoken Term Detection with Spoken Queries by Multi-level Acoustic Patterns with Varying Model Granularity


Sep 07, 2015
Cheng-Tao Chung, Chun-an Chan, Lin-shan Lee

* Accepted by ICASSP 2014 

  Access Paper or Ask Questions

Unsupervised Discovery of Linguistic Structure Including Two-level Acoustic Patterns Using Three Cascaded Stages of Iterative Optimization


Sep 07, 2015
Cheng-Tao Chung, Chun-an Chan, Lin-shan Lee

* Accepted by ICASSP 2013 

  Access Paper or Ask Questions

A Multi-layered Acoustic Tokenizing Deep Neural Network (MAT-DNN) for Unsupervised Discovery of Linguistic Units and Generation of High Quality Features


Jun 07, 2015
Cheng-Tao Chung, Cheng-Yu Tsai, Hsiang-Hung Lu, Yuan-ming Liou, Yen-Chen Wu, Yen-Ju Lu, Hung-yi Lee, Lin-shan Lee

* submitted to Interspeech 2015 

  Access Paper or Ask Questions