A study of pronunciation verification in a speech therapy application

Techniques are presented for detecting phoneme level mispronunciations in utterances obtained from a population of impaired children speakers. The intended application of these approaches is to use the resulting confidence measures to provide feedback to patients concerning the quality of pronunciations in utterances arising within interactive speech therapy sessions. The pronunciation verification scenario involves presenting utterances of known words to a phonetic decoder and generating confusion networks from the resulting phone lattices. Confidence measures are derived from the posterior probabilities obtained from the confusion networks. An average phoneme level mispronunciation detection performance of 14.9 percent equal error rate is obtained after optimizing acoustic models and pronunciation models in the phonetic decoder and applying a nonlinear mapping to the confusion network posteriors.

• Type: Conference
• Year: 2009
• Where: ICASSP
• Authors: Shou-Chun Yin, Richard Rose, Oscar Saz, Eduardo Lleida
• Keywords: Confusion Network, ICASSP 2009, Phoneme Level Mispronunciation, Phonetic Decoder, Signal Processing