Analysis of recognition of acoustic events of stop consonants

Better discrimination of phonemic units still remains one of the most important problems in automatic speech recognition. Direct phoneme recognition in speaker independent automatic speech recognition systems is unable to provide good enough recognition results. There is made an assumption that better results could be achieved through the recognition of phoneme groups using group characteristic features: voiced/unvoiced, vowel/consonant, etc. This paper describes and statistically motivates features and rules for the detection of acoustic events of stop consonants using phonetically labeled data. Stop consonants recognition algorithm is presented. It was achieved 93.8% stop consonants recognition accuracy when testing the algorithm using utterances from LTDIGITS corpora.