A complete overview of distant automatic speech recognition The performance of
conventional Automatic Speech Recognition (ASR) systems degrades dramatically as soon …

We propose an unsupervised dynamic language model (LM) adaptation framework using
long-distance latent topic mixtures. The framework employs the Latent Dirichlet Allocation …

Abstract We integrated the Latent Dirichlet Allocation (LDA) approach, a latent semantic
analysis model, into unsupervised language model adaptation framework. We adapted a …

This paper describes recent advances at LIMSI in Mandarin Chinese speech-to-text
transcription. A number of novel approaches were introduced in the different system …

Nowadays official documents have to be made available in many languages, like for
example in the EU with its 20 official languages. Therefore, the need for effective tools to aid …

This paper discusses the development of the CU-HTK Mandarin broadcast news (BN)
transcription system. The Mandarin BN task includes a significant amount of English data …

Cross-system adaptation and system combination methods, such as ROVER and confusion
network combination, are known to lower the word error rate of speech recognition systems …

We propose a latent Dirichlet-tree allocation (LDTA) model-a correlated latent semantic
model-for unsupervised language model adaptation. The LDTA model extends the latent …

This paper describes the 2006 lecture recognition system developed at the Interactive
Systems Laboratories (ISL), for individual head-microphone (IHM), single distant …

Transcription of broadcast news is an interesting and challenging application for large-
vocabulary continuous speech recognition (LVCSR). We present in detail the structure of a …