| 臺大學術典藏 |
2021-09-02T00:05:16Z |
VQVC+: One-shot voice conversion by vector quantization and U-Net architecture
|
Wu D.-Y;Chen Y.-H;Lee H.-Y.; Wu D.-Y; Chen Y.-H; Lee H.-Y.; HUNG-YI LEE |
| 臺大學術典藏 |
2021-09-02T00:05:16Z |
WG-WaveNet: Real-time high-fidelity speech synthesis without GPU
|
Hsu P.-C;Lee H.-Y.; Hsu P.-C; Lee H.-Y.; HUNG-YI LEE |
| 臺大學術典藏 |
2021-09-02T00:05:16Z |
Understanding self-attention of self-supervised audio transformers
|
Yang S.-W;Liu A.T;Lee H.-Y.; Yang S.-W; Liu A.T; Lee H.-Y.; HUNG-YI LEE |
| 臺大學術典藏 |
2021-09-02T00:05:15Z |
Personalized dialogue response generation learned from monologues
|
Su F.-G;Hsu A.R;Tuan Y.-L;Lee H.-Y.; Su F.-G; Hsu A.R; Tuan Y.-L; Lee H.-Y.; HUNG-YI LEE |
| 臺大學術典藏 |
2021-09-02T00:05:15Z |
Self-Supervised Deep Learning for Fisheye Image Rectification
|
Chao C.-H;Hsu P.-L;Lee H.-Y;Wang Y.-C.F.; Chao C.-H; Hsu P.-L; Lee H.-Y; Wang Y.-C.F.; HUNG-YI LEE |
| 臺大學術典藏 |
2021-09-02T00:05:15Z |
SpeechBERT: An audio-and-text jointly learned language model for end-to-end spoken question answering
|
Chuang Y.-S;Liu C.-L;Lee H.-Y;Lee L.-S.; Chuang Y.-S; Liu C.-L; Lee H.-Y; Lee L.-S.; HUNG-YI LEE |
| 臺大學術典藏 |
2021-09-02T00:05:15Z |
Semi-supervised learning for multi-speaker text-to-speech synthesis using discrete speech representation
|
Tu T;Chen Y.-J;Liu A.H;Lee H.-Y.; Tu T; Chen Y.-J; Liu A.H; Lee H.-Y.; HUNG-YI LEE |
| 臺大學術典藏 |
2021-09-02T00:05:14Z |
How Far Are We from Robust Voice Conversion: A Survey
|
Huang T.-H;Lin J.-H;Lee H.-Y.; Huang T.-H; Lin J.-H; Lee H.-Y.; HUNG-YI LEE |
| 臺大學術典藏 |
2021-09-02T00:05:14Z |
Improving automatic speech recognition and speech translation via word embedding prediction
|
Chuang S.-P;Liu A.H;Sung T.-W;Lee H.-Y.; Chuang S.-P; Liu A.H; Sung T.-W; Lee H.-Y.; HUNG-YI LEE |
| 臺大學術典藏 |
2021-09-02T00:05:14Z |
Order-free learning alleviating exposure bias in multi-label classification
|
Tsai C.-P;Lee H.-Y.; Tsai C.-P; Lee H.-Y.; HUNG-YI LEE |
| 臺大學術典藏 |
2021-09-02T00:05:14Z |
End-to-End Whispered Speech Recognition with Frequency-Weighted Approaches and Pseudo Whisper Pre-training
|
Chang H.-J;Liu A.H;Lee H.-Y;Lee L.-S.; Chang H.-J; Liu A.H; Lee H.-Y; Lee L.-S.; HUNG-YI LEE |
| 臺大學術典藏 |
2021-09-02T00:05:14Z |
Hierarchical Prosody Modeling for Non-Autoregressive Speech Synthesis
|
Chien C.-M;Lee H.-Y.; Chien C.-M; Lee H.-Y.; HUNG-YI LEE |
| 臺大學術典藏 |
2021-09-02T00:05:13Z |
Defending Your Voice: Adversarial Attack on Voice Conversion
|
Huang C.-Y;Lin Y.Y;Lee H.-Y;Lee L.-S.; Huang C.-Y; Lin Y.Y; Lee H.-Y; Lee L.-S.; HUNG-YI LEE |
| 臺大學術典藏 |
2021-09-02T00:05:13Z |
Defense Against Adversarial Attacks on Spoofing Countermeasures of ASV
|
Wu H;Liu S;Meng H;Lee H.-Y.; Wu H; Liu S; Meng H; Lee H.-Y.; HUNG-YI LEE |
| 臺大學術典藏 |
2021-09-02T00:05:13Z |
Defense for black-box attacks on anti-spoofing models by self-supervised learning
|
Wu H;Liu A.T;Lee H.-Y.; Wu H; Liu A.T; Lee H.-Y.; HUNG-YI LEE |
| 臺大學術典藏 |
2021-09-02T00:05:13Z |
DARTS-ASR: Differentiable architecture search for multilingual speech recognition and adaptation
|
Chen Y.-C;Hsu J.-Y;Lee C.-K;Lee H.-Y.; Chen Y.-C; Hsu J.-Y; Lee C.-K; Lee H.-Y.; HUNG-YI LEE |
| 臺大學術典藏 |
2021-09-02T00:05:12Z |
Adversarial Attacks on Spoofing Countermeasures of Automatic Speaker Verification
|
Liu S;Wu H;Lee H.-Y;Meng H.; Liu S; Wu H; Lee H.-Y; Meng H.; HUNG-YI LEE |
| 臺大學術典藏 |
2021-09-02T00:05:12Z |
Audio Albert: A Lite Bert for Self-Supervised Learning of Audio Representation
|
Chi P.-H;Chung P.-H;Wu T.-H;Hsieh C.-C;Chen Y.-H;Li S.-W;Lee H.-Y.; Chi P.-H; Chung P.-H; Wu T.-H; Hsieh C.-C; Chen Y.-H; Li S.-W; Lee H.-Y.; HUNG-YI LEE |
| 臺大學術典藏 |
2021-05-21T11:41:01Z |
End-to-End Whispered Speech Recognition with Frequency-Weighted Approaches and Pseudo Whisper Pre-training
|
Chang, Heng Jui; Liu, Alexander H.; HUNG-YI LEE; LIN-SHAN LEE |
| 臺大學術典藏 |
2021-05-21T11:41:01Z |
Audio Albert: A Lite Bert for Self-Supervised Learning of Audio Representation
|
Chi, Po Han; Chung, Pei Hung; Wu, Tsung Han; Hsieh, Chun Cheng; Chen, Yen Hao; Li, Shang Wen; HUNG-YI LEE |
| 臺大學術典藏 |
2021-05-21T11:41:00Z |
Hierarchical Prosody Modeling for Non-Autoregressive Speech Synthesis
|
Chien, Chung Ming; HUNG-YI LEE |
| 臺大學術典藏 |
2021-05-21T11:41:00Z |
How Far Are We from Robust Voice Conversion: A Survey
|
Huang, Tzu Hsien; Lin, Jheng Hao; HUNG-YI LEE |
| 臺大學術典藏 |
2021-05-21T11:41:00Z |
Defending Your Voice: Adversarial Attack on Voice Conversion
|
Huang, Chien Yu; Lin, Yist Y.; HUNG-YI LEE; LIN-SHAN LEE |
| 臺大學術典藏 |
2021-05-05T02:43:11Z |
Dykgchat: Benchmarking dialogue generation grounding on dynamic knowledge graphs
|
Tuan, Y.-L.; Chen, Y.-N.; Lee, H.-Y.; HUNG-YI LEE |
| 臺大學術典藏 |
2021-01-18T09:12:24Z |
Semi-supervised learning for multi-speaker text-to-speech synthesis using discrete speech representation
|
Tu, Tao; Chen, Yuan Jui; Liu, Alexander H.; HUNG-YI LEE |
| 臺大學術典藏 |
2021-01-18T09:12:23Z |
WG-WaveNet: Real-time high-fidelity speech synthesis without GPU
|
Hsu, Po Chun; HUNG-YI LEE |
| 臺大學術典藏 |
2021-01-18T09:12:23Z |
Understanding self-attention of self-supervised audio transformers
|
Yang, Shu Wen; Liu, Andy T.; HUNG-YI LEE |
| 臺大學術典藏 |
2021-01-18T09:12:23Z |
SpeechBERT: An audio-and-text jointly learned language model for end-to-end spoken question answering
|
Chuang, Yung Sung; Liu, Chi Liang; HUNG-YI LEE; LIN-SHAN LEE |
| 臺大學術典藏 |
2021-01-18T09:12:23Z |
Defense for black-box attacks on anti-spoofing models by self-supervised learning
|
Wu, Haibin; Liu, Andy T.; HUNG-YI LEE |
| 臺大學術典藏 |
2021-01-18T09:12:23Z |
VQVC+: One-shot voice conversion by vector quantization and U-Net architecture
|
Wu, Da Yi; Chen, Yen Hao; HUNG-YI LEE |
| 臺大學術典藏 |
2020-06-11T06:18:29Z |
Neural attention models for sequence classification: Analysis and application to key term extraction and dialogue act detection
|
Shen, S.-S.;Lee, H.-Y.; Shen, S.-S.; Lee, H.-Y.; HUNG-YI LEE |
| 臺大學術典藏 |
2020-06-11T06:18:29Z |
Order-preserving abstractive summarization for spoken content based on connectionist temporal classification
|
Lu, B.-R.;Shyu, F.;Chen, Y.-N.;Lee, H.-Y.;Lee, L.-S.; Lu, B.-R.; Shyu, F.; Chen, Y.-N.; Lee, H.-Y.; Lee, L.-S.; HUNG-YI LEE |
| 臺大學術典藏 |
2020-06-11T06:18:28Z |
Audio Word2vec: Sequence-to-Sequence Autoencoding for Unsupervised Learning of Audio Segmentation and Representation
|
Chen, Y.-C.;Huang, S.-F.;Lee, H.-Y.;Wang, Y.-H.;Shen, C.-H.; Chen, Y.-C.; Huang, S.-F.; Lee, H.-Y.; Wang, Y.-H.; Shen, C.-H.; HUNG-YI LEE |
| 臺大學術典藏 |
2020-06-11T06:18:28Z |
Machine Comprehension of Spoken Content: TOEFL Listening Test and Spoken SQuAD
|
Lee, C.-H.; Lee, H.-Y.; Wu, S.-L.; Liu, C.-L.; Fang, W.; Hsu, J.-Y.; Tseng, B.-H.; HUNG-YI LEE; Lee, C.-H.;Lee, H.-Y.;Wu, S.-L.;Liu, C.-L.;Fang, W.;Hsu, J.-Y.;Tseng, B.-H. |
| 臺大學術典藏 |
2020-06-11T06:18:28Z |
Interactive spoken content retrieval by deep reinforcement learning
|
Wu, Y.-C.;Lin, T.-H.;Chen, Y.-D.;Lee, H.-Y.;Lee, L.-S.; Wu, Y.-C.; Lin, T.-H.; Chen, Y.-D.; Lee, H.-Y.; Lee, L.-S.; HUNG-YI LEE |
| 臺大學術典藏 |
2020-06-11T06:18:27Z |
Phonetic-and-Semantic Embedding of Spoken words with Applications in Spoken Content Retrieval
|
Chen, Y.-C.;Huang, S.-F.;Shen, C.-H.;Lee, H.-Y.;Lee, L.-S.; Chen, Y.-C.; Huang, S.-F.; Shen, C.-H.; Lee, H.-Y.; Lee, L.-S.; HUNG-YI LEE |
| 臺大學術典藏 |
2020-06-11T06:18:27Z |
Rhythm-Flexible Voice Conversion Without Parallel Data Using Cycle-GAN over Phoneme Posteriorgram Sequences
|
Yeh, C.-C.;Hsu, P.-C.;Chou, J.-C.;Lee, H.-Y.;Lee, L.-S.; Yeh, C.-C.; Hsu, P.-C.; Chou, J.-C.; Lee, H.-Y.; Lee, L.-S.; HUNG-YI LEE |
| 臺大學術典藏 |
2020-06-11T06:18:27Z |
Enhanced Spoken Term Detection Using Support Vector Machines and Weighted Pseudo Examples
|
Lee, Hung-yi;Lee, Lin-shan; Lee, Hung-yi; Lee, Lin-shan; HUNG-YI LEE |
| 臺大學術典藏 |
2020-06-11T06:18:26Z |
Towards Audio to Scene Image Synthesis Using Generative Adversarial Network
|
Wan, C.-H.;Chuang, S.-P.;Lee, H.-Y.; Wan, C.-H.; Chuang, S.-P.; Lee, H.-Y.; HUNG-YI LEE |
| 臺大學術典藏 |
2020-06-11T06:18:26Z |
Adversarial Training of End-to-end Speech Recognition Using a Criticizing Language Model
|
Liu, A.H.;Lee, H.-Y.;Lee, L.-S.; Liu, A.H.; Lee, H.-Y.; Lee, L.-S.; HUNG-YI LEE |
| 臺大學術典藏 |
2020-06-11T06:18:26Z |
Using Deep-Q Network to Select Candidates from N-best Speech Recognition Hypotheses for Enhancing Dialogue State Tracking
|
Tsai, R.T.-H.;Chen, C.-H.;Wu, C.-K.;Hsiao, Y.-C.;Lee, H.-Y.; Tsai, R.T.-H.; Chen, C.-H.; Wu, C.-K.; Hsiao, Y.-C.; Lee, H.-Y.; HUNG-YI LEE |
| 臺大學術典藏 |
2020-06-11T06:18:26Z |
Adversarial Learning of Label Dependency: A Novel Framework for Multi-class Classification
|
Tsai, C.-P.;Lee, H.-Y.; Tsai, C.-P.; Lee, H.-Y.; HUNG-YI LEE |
| 臺大學術典藏 |
2020-06-11T06:18:26Z |
Towards End-to-end Speech-to-text Translation with Two-pass Decoding
|
Sung, T.-W.;Liu, J.-Y.;Lee, H.-Y.;Lee, L.-S.; Sung, T.-W.; Liu, J.-Y.; Lee, H.-Y.; Lee, L.-S.; HUNG-YI LEE |
| 臺大學術典藏 |
2020-06-11T06:18:25Z |
Recurrent Neural Network based language modeling with controllable external Memory
|
Ko, W.-J.;Tseng, B.-H.;Lee, H.-Y.; Ko, W.-J.; Tseng, B.-H.; Lee, H.-Y.; HUNG-YI LEE |
| 臺大學術典藏 |
2020-06-11T06:18:24Z |
Personalized word representations carrying personalized semantics learned from social network posts
|
Lin, Z.-W.;Sung, T.-W.;Lee, H.-Y.;Lee, L.-S.; Lin, Z.-W.; Sung, T.-W.; Lee, H.-Y.; Lee, L.-S.; HUNG-YI LEE |
| 臺大學術典藏 |
2020-06-11T06:18:24Z |
Personalized acoustic modeling by weakly supervised multi-task deep learning using acoustic tokens discovered from unlabeled data
|
Wei, C.-K.;Chung, C.-T.;Lee, H.-Y.;Lee, L.-S.; Wei, C.-K.; Chung, C.-T.; Lee, H.-Y.; Lee, L.-S.; HUNG-YI LEE |
| 臺大學術典藏 |
2020-06-11T06:18:23Z |
Temporal pattern attention for multivariate time series forecasting
|
Shih, S.-Y.;Sun, F.-K.;Lee, H.-Y.; Shih, S.-Y.; Sun, F.-K.; Lee, H.-Y.; HUNG-YI LEE |
| 臺大學術典藏 |
2020-06-11T06:18:23Z |
Towards structured deep neural network for automatic speech recognition
|
Liao, Y.-H.;Lee, H.-Y.;Lee, L.-S.; Liao, Y.-H.; Lee, H.-Y.; Lee, L.-S.; HUNG-YI LEE |
| 臺大學術典藏 |
2020-06-11T06:18:23Z |
An iterative deep learning framework for unsupervised discovery of speech features and linguistic units with applications on spoken term detection
|
Chung, C.-T.;Tsai, C.-Y.;Lu, H.-H.;Liu, C.-H.;Lee, H.-Y.;Lee, L.-S.; Chung, C.-T.; Tsai, C.-Y.; Lu, H.-H.; Liu, C.-H.; Lee, H.-Y.; Lee, L.-S.; HUNG-YI LEE |
| 臺大學術典藏 |
2020-06-11T06:18:23Z |
Personalizing universal recurrent neural network language model with user characteristic features by social network crowdsourcing.
|
Tseng, Bo-Hsiang;Lee, Hung-yi;Lee, Lin-Shan; Tseng, Bo-Hsiang; Lee, Hung-yi; Lee, Lin-Shan; HUNG-YI LEE |
