A study on using word-level HMMs to improve ASR performance over state-of-the-art phone-level acoustic modeling for LVCSR
I-Fan Chen, Chin‐Hui Lee · 2012
In this paper, we propose word-level hidden Markov models (HMMs) to supplement state-of-the-art phone-based acoustic modeling in order to enhance the performance of automatic speech recognition (ASR) system. Each word in a vocabulary is initially modeled by well-trained triphone models. Maximum a posteriori adaptation is then applied to generate models for words with a large number of occurrences in the training set so that the acoustic distribution of the words can be modeled more precisely. Experimental results show that the proposed wordbased systems outperform phone-based systems on the TIMIT task with a small training corpus. While in tasks with plenty of training data, word-based systems still show improvements over phone-based systems, such as the WSJ task. Furthermore the word-based systems have a better discriminating ability on short words and homophones. They are also more robust to language model weight variation than conventional phone-based systems.