Zobrazeno 1 - 10
of 107
pro vyhledávání: '"Li, Chia‐Yu"'
Autor:
Li, Chia-Yu, Vu, Ngoc Thang
Training a semi-supervised end-to-end speech recognition system using noisy student training has significantly improved performance. However, this approach requires a substantial amount of paired speech-text and unlabeled speech, which is costly for
Externí odkaz:
http://arxiv.org/abs/2407.21061
This paper presents our latest investigation on modeling backchannel in conversations. Motivated by a proactive backchanneling theory, we aim at developing a system which acts as a proactive listener by inserting backchannels, such as continuers and
Externí odkaz:
http://arxiv.org/abs/2304.04478
Autor:
Li, Chia-Yu, Vu, Ngoc Thang
We propose a novel method that combines CycleGAN and inter-domain losses for semi-supervised end-to-end automatic speech recognition. Inter-domain loss targets the extraction of an intermediate shared representation of speech and text inputs using a
Externí odkaz:
http://arxiv.org/abs/2210.11642
Integrating Knowledge in End-to-End Automatic Speech Recognition for Mandarin-English Code-Switching
Autor:
Li, Chia-Yu, Vu, Ngoc Thang
Code-Switching (CS) is a common linguistic phenomenon in multilingual communities that consists of switching between languages while speaking. This paper presents our investigations on end-to-end speech recognition for Mandarin-English CS speech. We
Externí odkaz:
http://arxiv.org/abs/2112.10202
Autor:
Li, Chia Yu, Vu, Ngoc Thang
We investigate densely connected convolutional networks (DenseNets) and their extension with domain adversarial training for noise robust speech recognition. DenseNets are very deep, compact convolutional neural networks which have demonstrated incre
Externí odkaz:
http://arxiv.org/abs/2112.10108
Autor:
Li, Chia-Yu, Vu, Ngoc Thang
This paper presents our latest effort on improving Code-switching language models that suffer from data scarcity. We investigate methods to augment Code-switching training text data by artificially generating them. Concretely, we propose a cycle-cons
Externí odkaz:
http://arxiv.org/abs/2112.06327
Autor:
Li, Chia-Yu, Vu, Ngoc Thang
This paper presents our latest investigations on improving automatic speech recognition for noisy speech via speech enhancement. We propose a novel method named Multi-discriminators CycleGAN to reduce noise of input speech and therefore improve the a
Externí odkaz:
http://arxiv.org/abs/2112.06309
Autor:
Hamed, Injy, Denisov, Pavel, Li, Chia-Yu, Elmahdy, Mohamed, Abdennadher, Slim, Vu, Ngoc Thang
Code-switching (CS), defined as the mixing of languages in conversations, has become a worldwide phenomenon. The prevalence of CS has been recently met with a growing demand and interest to build CS ASR systems. In this paper, we present our work on
Externí odkaz:
http://arxiv.org/abs/2108.12881
Autor:
Li, Chia-Yu, Ortega, Daniel, Väth, Dirk, Lux, Florian, Vanderlyn, Lindsey, Schmidt, Maximilian, Neumann, Michael, Völkel, Moritz, Denisov, Pavel, Jenne, Sabrina, Kacarevic, Zorica, Vu, Ngoc Thang
We present ADVISER - an open-source, multi-domain dialog system toolkit that enables the development of multi-modal (incorporating speech, text and vision), socially-engaged (e.g. emotion recognition, engagement level prediction and backchanneling) c
Externí odkaz:
http://arxiv.org/abs/2005.01777
Autor:
LI, CHIA-YU, 李佳俞
106
Background: Chronic kidney disease patients have many physical symptoms. In recent years, research into positive mental health has suggested that a spiritual well-being approach is effective for patients with chronic kidney disease. However,
Background: Chronic kidney disease patients have many physical symptoms. In recent years, research into positive mental health has suggested that a spiritual well-being approach is effective for patients with chronic kidney disease. However,
Externí odkaz:
http://ndltd.ncl.edu.tw/handle/madwfw