Publications

Event Detection in Sensor Networks with Non-Linear Amplifiers via Mixture Series Expansion

Authors: 
Zhang Pengfei, Ido Nevat, Gareth W. Peters, Laurent Clavier
Publication: 
IEEE Sensors Journal (SEN)
Publication Date: 
15 Sep 2016
Strategic Thrust: 
Intelligence
Abstract: 
We develop a new algorithm for binary eventdetection in Wireless Sensor Networks where the sensing processexhibits non-linear behavior causing clipping of the signalsat random. We formulate the optimal event detection... Read more ›

Context Aware Mispronunciation Detection for Mandarin Pronunciation Training

Authors: 
Tong Rong, Nancy Chen, Ma Bin, Li Haizhou
Publication: 
INTERSPEECH - HLT TOP CONFERENCE
Publication Date: 
10 Sep 2016
Strategic Thrust: 
Intelligence
Abstract: 
Mispronunciation detection is an important component in a computer-assisted language learning (CALL) system. Many CALL systems only provide pronunciation correctness as the single feedback, which is not very informative for... Read more ›

Toward High-Performance Language-Independent Query-by-Example Spoken Term Detection for MediaEval 2015: Post-Evaluation Analysis

Authors: 
Leung Cheung Chi, Wang Lei, Haihua Xu, HOU Jingyong, Van Tung Pham, LV Hang, Xie Lei, Xiao Xiong, Ni Chongjia, Ma Bin, Chng Eng Siong, Li Haizhou
Publication: 
INTERSPEECH - HLT TOP CONFERENCE
Publication Date: 
8 Sep 2016
Strategic Thrust: 
Intelligence
Abstract: 
This paper documents the significant components of a state-of-the-art language-independent query-by-example spoken term detection system designed for the Query by Example Search on Speech Task (QUESST) in MediaEval 2015. We... Read more ›

Joint Speaker and Lexical Modeling for Short-Term Characterization of Speaker

Authors: 
Wang Guangsen, Lee Kong Aik, Nguyen Trung Hieu, Sun Hanwu, Ma Bin
Publication: 
INTERSPEECH - HLT TOP CONFERENCE
Publication Date: 
8 Sep 2016
Strategic Thrust: 
Intelligence
Abstract: 
For speech utterances of very short duration, speaker characterization has shown strong dependency on the lexical content. In this context, speaker verification is always performed by analyzing and matching speaker... Read more ›

The 2015 NIST Language Recognition Evaluation: the Shared View of I2R, Fantastic4 and SingaMS

Authors: 
Lee Kong Aik, Li Haizhou, Sun Hanwu, Nguyen Trung Hieu, Wang Guangsen, Ma Bin, Xiao Xiong, Deng Li, Rao Wei, Anthony Larcher, Aleksandr Sizov, Ville Hautamaki, Chen Jianshu, Ivan Kukanov, Amir Hossein Poorjam, Trung Ngo Trong, Cheng-Lin Xu, Hai-Hua Xu, Eng-Siong Chng, Sylvain Meignier
Publication: 
INTERSPEECH - HLT TOP CONFERENCE
Publication Date: 
8 Sep 2016
Strategic Thrust: 
Intelligence
Abstract: 
The series of language recognition evaluations (LRE's) conducted by the National Institute of Standards and Technology (NIST) have been one of the driving forces in advancing spoken language recognition technology... Read more ›

Twin model G-PLDA for duration mismatch compensation in text-independent speaker verification

Authors: 
Jianbo Ma, Vidhyasaharan Sethu, Eliathamby Ambikairajah, Lee Kong Aik
Publication: 
INTERSPEECH - HLT TOP CONFERENCE
Publication Date: 
8 Sep 2016
Strategic Thrust: 
Intelligence
Abstract: 
This paper proposes a novel method to compensate for duration mismatch for use in short duration speaker verification. This method modifies the standard Gaussian probabilistic linear discriminant analysis (G-PLDA) to... Read more ›

Automatic Correction of ASR Outputs by Using Machine Translation

Authors: 
Luis Fernando D'Haro Enriquez, Rafael E. Banchs
Publication: 
INTERSPEECH - HLT TOP CONFERENCE
Publication Date: 
8 Sep 2016
Strategic Thrust: 
Intelligence
Abstract: 
One of the main challenges when working with a domain-independent automatic speech recognizers (ASR) is to correctly transcribe rare or out-of-vocabulary words that are not included in the language model... Read more ›

SERAPHIM - A Wavetable Synthesis System with 3D Lip Animation for Real-time Speech and Singing Applications on Mobile Platforms

Authors: 
Paul Chan Yaozhu, Dong Ming Hui, Li Haizhou
Publication: 
INTERSPEECH - HLT TOP CONFERENCE
Publication Date: 
8 Sep 2016
Strategic Thrust: 
Media, Intelligence
Abstract: 
1) This paper is on a novel real-time singing synthesis technique that addresses issues unsolved by current competitors.2) State-of-the-art real-time singing synthesis systems employ static methods that either are only... Read more ›

Pages