Deep Belief Networks using discriminative features for phone recognition

• Published in: 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 5060 - 5063
• Main Authors: Mohamed, Abdel-rahman, Sainath, Tara N., Dahl, George, Ramabhadran, Bhuvana, Hinton, Geoffrey E., Picheny, Michael A.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.05.2011
• Subjects: Artificial neural networks; Decoding; Deep belief networks; Discriminative feature transformation; Error analysis; Hidden Markov models; Mel frequency cepstral coefficient; Phone recognition; Speech; Training
• ISBN: 9781457705380; 1457705389
• ISSN: 1520-6149
• DOI: 10.1109/ICASSP.2011.5947494

Deep Belief Networks (DBNs) are multi-layer generative models. They can be trained to model windows of coefficients extracted from speech and they discover multiple layers of features that capture the higher-order statistical structure of the data. These features can be used to initialize the hidden...