E-LIB Suche - Ergebnisse für: Lo, Tien-Hong

1

3M: An Effective Multi-view, Multi-granularity, and Multi-a..:

, In: 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC),

Chao, Fu-An ; Lo, Tien-Hong ; Wu, Tzu-I.. - p. 575-582 , 2022

Link: https://doi.org/10.23919..

2

An Effective Contextual Language Modeling Framework for Spe..:

, In: 2020 28th European Signal Processing Conference (EUSIPCO),

Weng, Shi-Yan ; Lo, Tien-Hong ; Chen, Berlin - p. 316-320 , 2021

Link: https://doi.org/10.23919..

3

Spoken Document Retrieval Leveraging Bert-Based Modeling an..:

, In: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP),

Fan-Jiang, Shao-Wei ; Lo, Tien-Hong ; Chen, Berlin - p. 8144-8148 , 2020

Link: https://doi.org/10.1109/..

4

Semi-supervised Training of Acoustic Models Leveraging Know..:

, In: 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC),

Lo, Tien-Hong ; Chen, Berlin - p. 1400-1404 , 2019

Link: https://doi.org/10.1109/..

5

Enhanced Bert-Based Ranking Models for Spoken Document Retr..:

, In: 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU),

Lin, Hsiao-Yun ; Lo, Tien-Hong ; Chen, Berlin - p. 601-606 , 2019

Link: https://doi.org/10.1109/..

6

A Hierarchical Context-aware Modeling Approach for Multi-as..:

Chao, Fu-An ; Lo, Tien-Hong ; Wu, Tzu-I..
http://arxiv.org/abs/2305.18146. , 2023

Link: http://arxiv.org/abs/230..

7

3M: An Effective Multi-view, Multi-granularity, and Multi-a..:

Chao, Fu-An ; Lo, Tien-Hong ; Wu, Tzu-I..
http://arxiv.org/abs/2208.09110. , 2022

Link: http://arxiv.org/abs/220..

8

Cross-utterance Reranking Models with BERT and Graph Convol..:

Chiu, Shih-Hsuan ; Lo, Tien-Hong ; Chao, Fu-An.
http://arxiv.org/abs/2106.06922. , 2021

Link: http://arxiv.org/abs/210..

9

Towards Robust Mispronunciation Detection and Diagnosis for..:

Jiang, Shao-Wei Fan ; Yan, Bi-Cheng ; Lo, Tien-Hong..
http://arxiv.org/abs/2108.11627. , 2021

Link: http://arxiv.org/abs/210..

10

Improving End-To-End Modeling for Mispronunciation Detectio..:

Lo, Tien-Hong ; Sung, Yao-Ting ; Chen, Berlin
http://arxiv.org/abs/2110.08731. , 2021

Link: http://arxiv.org/abs/211..

11

The NTNU Taiwanese ASR System for Formosa Speech Recognitio..:

Chao, Fu-An ; Lo, Tien-Hong ; Weng, Shi-Yan...
http://arxiv.org/abs/2104.04221. , 2021

Link: http://arxiv.org/abs/210..

12

An Effective Contextual Language Modeling Framework for Spe..:

Weng, Shi-Yan ; Lo, Tien-Hong ; Chen, Berlin
http://arxiv.org/abs/2006.01189. , 2020

Link: http://arxiv.org/abs/200..

13

The NTNU System at the Interspeech 2020 Non-Native Children..:

Lo, Tien-Hong ; Chao, Fu-An ; Weng, Shi-Yan.
http://arxiv.org/abs/2005.08433. , 2020

Link: http://arxiv.org/abs/200..

14

Query Expansion System for the VoxCeleb Speaker Recognition..:

Cheng, Yu-Sen ; Shih, Chun-Liang ; Lo, Tien-Hong..
http://arxiv.org/abs/2011.02882. , 2020

Link: http://arxiv.org/abs/201..

15

An Effective End-to-End Modeling Approach for Mispronunciat..:

Lo, Tien-Hong ; Weng, Shi-Yan ; Chang, Hsiu-Jui.
http://arxiv.org/abs/2005.08440. , 2020

Link: http://arxiv.org/abs/200..