Learning task-dependent speech variability in discriminative acoustic model adaptation

We present a new discriminative method of acoustic model adaptation that deals with a task-dependent speaking style. We have focused on differences of expressions or speaking styles between tasks and set the objective of this method as improving the recognition accuracy of indistinctly pronounced phrases dependent on a speaking style. The adaptation appends subword models for frequently observable variants of subwords in the task. To find the task-dependent variants, low-confidence words are statistically selected from words with higher frequency in the task´s adaptation data by using their word lattices. Subword models dependent on the words are discriminatively trained by using linear transforms with a minimum phoneme error (MPE) criterion. For the MPE training, subword accuracy discriminating between the variants and the originals is also investigated. In speech recognition experiments, the proposed adaptation with the subword variants relatively reduced the word error rate by 4.4% in a Japanese conversational broadcast task.