no code implementations • 14 Dec 2023 • Bobbi Aditya, Mahdin Rohmatillah, Liang-Hsuan Tai, Jen-Tzung Chien
The prevalence of the powerful multilingual models, such as Whisper, has significantly advanced the researches on speech recognition.
no code implementations • 23 Sep 2023 • Youzhi Tu, Man-Wai Mak, Jen-Tzung Chien
Contrastive speaker embedding assumes that the contrast between the positive and negative pairs of speech segments is attributed to speaker identity only.
no code implementations • 8 Sep 2023 • Chong-Xin Gan, Man-Wai Mak, Weiwei Lin, Jen-Tzung Chien
Contrastive self-supervised learning (CSL) for speaker verification (SV) has drawn increasing interest recently due to its ability to exploit unlabeled data.
1 code implementation • 18 May 2023 • Li-Jen Yang, Chao-Han Huck Yang, Jen-Tzung Chien
This paper presents a parameter-efficient learning (PEL) to develop a low-resource accent adaptation for text-to-speech (TTS).
no code implementations • 29 Sep 2021 • Jen-Tzung Chien, Yu-Han Huang
To strengthen the sequential learning representation, this paper presents a new disentangled mask attention in transformer where the redundant features are reduced and the semantic information is enriched.
no code implementations • 29 Sep 2021 • Jen-Tzung Chien, Hsiu-Wei Tien
One of the most important challenges in a visual dialog is to effectively extract the information from a given image and its historical conversation which are related to the current question.
no code implementations • ACL 2019 • Jen-Tzung Chien
The {``}distribution function{''} in discrete or continuous latent variable model for natural language may not be properly decomposed or estimated.
no code implementations • 8 Jul 2018 • Jiyang Xie, Zhanyu Ma, Guo-Qiang Zhang, Jing-Hao Xue, Jen-Tzung Chien, Zhiqing Lin, Jun Guo
In order to explicitly characterize the nonnegative L1-norm constraint of the parameters, we further approximate the true posterior distribution by a Dirichlet distribution.