Spontaneous Thai speech recognition

This paper expands previous work on Thai speech recognition, investigating pronunciation changes such as syllable and phoneme elisions as well as phoneme shifts in Thai spontaneous speech. We compare several approaches to model these effects in large vocabulary continuous speech recognition across multiple domains. This work includes experiments on two new speech databases that significantly alleviate the data sparseness problem of earlier publications. We found that given sufficient training data, a fully data driven approach using an allophone cluster tree yields the best results. Explicit modeling of pronunciation changes does not improve performance across domains. Index Terms: Thai, speech recognition, spontaneous speech, pronunciation modeling, acoustic model sharing