Correlated Bigram LSA for Unsupervised Language Model Adaptation (2009)
We present a correlated bigram LSA approach for unsupervised LM adaptation for automatic speech recognition. The model is trained using efficient variational EM and smoothed using the proposed...
Bilingual-LSA Based LM Adaptation for Spoken Language Translation (2009)
Yik-cheung Tam, Ian Lane, Tanja Schultz
We propose a novel approach to crosslingual language model (LM) adaptation based on bilingual Latent Semantic Analysis (bLSA). A bLSA model is introduced which enables latent topic distributions to...
Bilingual-LSA Based LM Adaptation for Spoken Language Translation (2008)
Yik-cheung Tam, Ian Lane, Tanja Schultz
We propose a novel approach to crosslingual language model (LM) adaptation based on bilingual Latent Semantic Analysis (bLSA). A bLSA model is introduced which enables latent topic distributions to...
Sebastian Stüker, Christian Fügen, Roger Hsiao, Shajith Ikbal, Qin Jin, Florian Kraft, ...
The project Technology and Corpora for Speech to Speech Translation (TC-STAR) aims at making a break-through in speech-to-speech translation research, significantly reducing the gap between the...
Bilingual-LSA Based LM Adaptation for Spoken Language Translation (2008)
Yik-cheung Tam, Ian Lane, Tanja Schultz
We propose a novel approach to crosslingual language model (LM) adaptation based on bilingual Latent Semantic Analysis (bLSA). A bLSA model is introduced which enables latent topic distributions to...
Unsupervised language model adaptation using latent semantic marginals (2006)
We integrated the Latent Dirichlet Allocation (LDA) approach, a latent semantic analysis model, into unsupervised language model adaptation framework. We adapted a background language model by...
The ISL RT04 Mandarin Broadcast News Evaluation System (2004)
Hua Yu, Yik-Cheung Tam, Schaaf, Thomas, Stüker, Sebastian, Qin Jin, Noamany, Mohamed, ...
The ISL RT04 Mandarin Broadcast News Evaluation System. (2004)
Hua Yu, Yik-Cheung Tam, Schaaf, Thomas, Stüker, Sebastian, Qin Jin, Noamany, Mohamed, ...
The Isl Rt04 Mandarin Broadcast News Evaluation System (2004)
Hua Yu, Yik-cheung Tam, Thomas Schaaf, Sebastian Stüker, Qin Jin, ...
This paper describes our effort in developing a Mandarin Broadcast News system for the RT-04f (Rich Transcription) evaluation. Starting from a legacy system, we revisited all the issues including...
The isl rt04 mandarin broadcast news evaluation system (2004)
Hua Yu, Yik-cheung Tam, Thomas Schaaf, Sebastian Stüker, Qin Jin, Mohamed Noamany, ...
This paper describes our effort in developing a Mandarin Broadcast News system for the RT-04f (Rich Transcription) evaluation. Starting from a legacy system, we revisited all the issues including...
PLASER: Pronunciation Learning via Automatic Speech Recognition (2003)
Brian Mak, Manhung Siu, Mimi Ng, Yik-cheung Tam, Yu-chung Chan, Kin-wah Chan, ...
PLASER is a multimedia tool with instant feedback designed to teach English pronunciation for high-school students of Hong Kong whose mother tongue is Cantonese Chinese. The objective is to teach...
Training a Confidence Measure for a Reading Tutor that Listens (2003)
Yik-cheung Tam, Jack Mostow, Joseph Beck, Satanjeev Banerjee
One issue in a Reading Tutor that listens is to determine which words the student read correctly. We describe a confidence measure that uses a variety of features to estimate the probability that a...
Training a Confidence Measure for a Reading Tutor that Listens (2003)
Yik-cheung Tam, Jack Mostow, Joseph Beck, Satanjeev Banerjee
One issue in a Reading Tutor that listens is to determine which words the student read correctly. We describe a confidence measure that uses a variety of features to estimate the probability that a...
Discriminative Auditory Features for Robust Speech Recognition (2002)
Recently, Li et al. proposed a new auditory feature for robust speech recognition in noise environments. The new feature was derived by mimicking closely the function of human auditory process....
During minimum-classification-error (MCE) training, competing hypotheses against the correct one are commonly derived by the N-best algorithm. One problem with the N-best algorithm is that, in...
Development of an asynchronous multi-band system for continuous speech recognition / (2001)
Thesis (M. Phil.)--Hong Kong University of Science and Technology, 2001.
Development of an asynchronous multi-band system for continuous speech recognition (2001)
Recently, multi-band automatic speech recognition (MBASR) is proposed to combat environmental noises. In this paper, we describe the two major efforts in the development of our asynchronous MBASR...
Development of an asynchronous multi-band system for continuous speech recognition (2001)
Thesis (M.Phil.)--Hong Kong University of Science and Technology, 2001
Recently multi-band speech recognition has been proposed to improve robustness under environmental noises. One important issue is how to combine decisions from individual sub-band recognizers to...
One of the central themes in multi-band automatic speech recognition (ASR) is to devise a strategy for recombining sub-band information. This in turn raises two questions: (1) at what phonetic unit...