2015 | OriginalPaper | Buchkapitel
Improving Acoustic Model for Vietnamese Large Vocabulary Continuous Speech Recognition System Using Deep Bottleneck Features
verfasst von : Quoc Bao Nguyen, Tat Thang Vu, Chi Mai Luong
Erschienen in: Knowledge and Systems Engineering
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
In this paper, a method based on deep learning for extracting bottleneck features for Vietnamese large vocabulary speech recognition is presented. Deep bottleneck features (DBNFs) is able to achieve significant improvements over a number of base bottleneck features which was reported previously. The experiments are carried out on the dataset containing speeches on Voice of Vietnam channel (VOV). The results show that adding tonal feature as input feature of the network reached around 20% relative recognition performance. The DBNF extraction for Vietnamese recognition decrease the error rate by 51%, compared to the MFCC baseline.