Search Results - "Chong, Tze Yuang"

Cancelable Biometrics Realization With Multispace Random Projections by Beng Jin Teoh, A., Chong Tze Yuang

“…Biometric characteristics cannot be changed; therefore, the loss of privacy is permanent if they are ever compromised. This paper presents a two-factor…”
Get full text

Decoupling Word-Pair Distance and Co-occurrence Information for Effective Long History Context Language Modeling by Tze Yuang Chong, Banchs, Rafael E., Eng Siong Chng, Haizhou Li

“…In this paper, we propose the use of distance and co-occurrence information of word-pairs to improve language modeling. We have empirically shown that, for…”
Get full text

Improving language modeling by using distance and co-occurrence information of word-pairs and its application to LVCSR by Tze Yuang Chong, Banchs, Rafael E., Eng Siong Chng, Haizhou Li

“…This paper reports our study in exploiting the distance and co-occurrence information of word-pairs to improve the n-gram language model. We used these two…”
Get full text

Extending Multilingual ASR to New Languages Using Supplementary Encoder and Decoder Components by Khassanov, Yerbolat, Chen, Zhipeng, Chen, Tianfeng, Chong, Tze Yuang, Li, Wei, Lu, Lu, Ma, Zejun

“…Extending multilingual automatic speech recognition (mASR) systems to new languages poses challenges, particularly when training data for existing languages is…”
Get full text

Collection and annotation of Malay conversational speech corpus by Tze Yuang Chong, Xiong Xiao, Tien-Ping Tan, Eng Siong Chng, Haizhou Li

“…We report the development of a Malay conversational speech corpus as part of our research in spontaneous conversational speech LVCSR. This corpus development…”
Get full text

The development and analysis of a Malay broadcasr news corpus by Tze Yuang Chong, Xiong Xiao, Haihua Xu, Tien-Ping Tan, Pham Chau-Khoa, Dau-Cheng Lyu, Eng Siong Chng, Haizhou Li

“…This paper presents our effort in collecting a Malay broadcast news (BN) speech corpus to support our research in Malay LVCSR. The 53 hours corpus is recorded…”
Get full text

Dual-Pipeline with Low-Rank Adaptation for New Language Integration in Multilingual ASR by Khassanov, Yerbolat, Chen, Zhipeng, Chen, Tianfeng, Chong, Tze Yuang, Li, Wei, Zhang, Jun, Lu, Lu, Wang, Yuxuan

“…This paper addresses challenges in integrating new languages into a pre-trained multilingual automatic speech recognition (mASR) system, particularly in…”
Get full text

TransfoRNN: Capturing the Sequential Information in Self-Attention Representations for Language Modeling by Chong, Tze Yuang, Wang, Xuyang, Yang, Lin, Wang, Junjie

“…In this paper, we describe the use of recurrent neural networks to capture sequential information from the self-attention representations to improve the…”
Get full text

Improving N-gram language modeling for code-switching speech recognition by Zeng, Zhiping, Xu, Haihua, Chong, Tze Yuang, Chng, Eng-Siong, Li, Haizhou

“…Code-switching language modeling is challenging due to statistics of each individual language, as well as statistics of cross-lingual language are…”
Get full text

Random Utterance Concatenation Based Data Augmentation for Improving Short-video Speech Recognition by Lin, Yist Y, Han, Tao, Xu, Haihua, Pham, Van Tung, Khassanov, Yerbolat, Chong, Tze Yuang, He, Yi, Lu, Lu, Ma, Zejun

“…One of limitations in end-to-end automatic speech recognition (ASR) framework is its performance would be compromised if train-test utterance lengths are…”
Get full text

On the study of very low-resource language keyword search by Van Tung, Pham, Xu, Haihua, Van Hai, Do, Chong, Tze Yuang, Xiao, Xiong, Chng, Eng Siong, Li, Haizhou

“…In this paper we report our approaches to accomplishing the very limited resource keyword search (KWS) task in the NIST Open Keyword Search 2015 (OpenKWS15)…”
Get full text