Predicting the Acoustic Confusability between Words for a Speech Recognition System using Levenshtein Distance
Keywords: Acoustic modeling, automatic speech recognition, human computer interaction, Levenshtein distance
AbstractThis paper proposes a new method for calculating acoustic confusability between words for automatic speech recognition. Acoustic confusability is one of the key elements influencing speech recognition accuracy. The proposed method is based on Levenshtein distance, calculated on phonetic transcriptions from the speech recognizer’s vocabulary. The method was evaluated in an indirect way. The experiments were carried out on four different sets of context-dependent acoustic models. The proposed method successfully predicted the acoustic confusability between words from the speech recognizer’s vocabulary.
SYSTEM ENGINEERING, COMPUTER TECHNOLOGY
Copyright terms are indicated in the Republic of Lithuania Law on Copyright and Related Rights, Articles 4-37.