This is a report of our lessons learned building acoustic models from 1 Million hours of
unlabeled speech, while labeled speech is restricted to 7,000 hours. We employ …

We propose a new technique for training deep neural networks (DNNs) as data-driven
feature front-ends for large vocabulary continuous speech recognition (LVCSR) in low …

This paper investigates unsupervised language model adaptation, from ASR transcripts. N-
gram counts from these transcripts can be used either to adapt an existing n-gram model or …

Since the introduction of hidden Markov modelling there has been an increasing emphasis
on data-driven approaches to automatic speech recognition. This derives from the fact that …

This paper investigates adapting a lexicalized probabilistic context-free grammar (PCFG) to
a novel domain, using maximum a posteriori (MAP) estimation. The MAP framework is …

A significant cost in obtaining acoustic training data is the generation of accurate
transcriptions. When no transcription is available, unsupervised training techniques must be …

We present our study on semi-supervised Gaussian mixture model (GMM) hidden Markov
model (HMM) and deep neural network (DNN) HMM acoustic model training. We analyze …

Typical supervised acoustic model training relies on strong top-down constraints provided
by dynamic programming alignment of the input observations to phonetic sequences …

This paper investigates supervised and unsupervised adaptation of stochastic grammars,
including n-gram language models and probabilistic context-free grammars (PCFGs), to a …

We present a method for cross-lingual training an ASR system using absolutely no
transcribed training data from the target language, and with no phonetic knowledge of the …