Towards more efficient and accurate methods for Mandarin LVCSR discriminative training

Discriminative training of Mandarin large vocabulary continuous speech recognition (LVCSR) has been remarkably improved in speech community recent years. However, much work still needs further investigating. In this work, we focus on improvements to two aspects of discriminative training method, in particular related to minimum phone error (MPE) training method in Mandarin speech recognition. One is to use syllable, not multi-character word, as speech recognition unit (SRU) to generate phone lattice to train models. The other is to investigate better objective functions related to MPE with comparisons on recent proposed methods. Experimental results showed that the proposed methods improved both efficiency and accuracy for discriminative training in Mandarin speech recognition.