Inventors

Sung Joo Lee, Park Jeon Gue, Kang Byung Ok, Chung Hoon, Lee Yunkeun

Application No.

15042309 (2016.02.12)

Publication No.

20160240190 (2016.08.18)

Registration No.

9805716 (2017.10.31)

Country

UNITED STATES

Project Code

14MS1500, Development of dialog-based spontaneous speech interface technology on mobile platform , Lee Yunkeun

Abstract

Provided is an apparatus for large vocabulary continuous speech recognition (LVCSR) based on a context-dependent deep neural network hidden Markov model (CD-DNN-HMM) algorithm. The apparatus may include an extractor configured to extract acoustic model-state level information corresponding to an input speech signal from a training data model set using at least one of a first feature vector based on a gammatone filterbank signal analysis algorithm and a second feature vector based on a bottleneck algorithm, and a speech recognizer configured to provide a result of recognizing the input speech signal based on the extracted acoustic model-state level information.

KSP Keywords

CD-DNN-HMM, Continuous Speech, Continuous Speech Recognition, DNN-HMM, Data Model, Deep neural network(DNN), Feature Vector, Gammatone filterbank, Hidden Markov, Hidden markov model(HMM), Large vocabulary, Markov model, Model set, Signal analysis, Speech Signals, Vector based, acoustic model, context-dependent, large vocabulary continuous speech recognition(LVCSR), neural network(NN), signal based, speech recognition, state level, training data