BROWSE
Detail
Registered APPARATUS AND METHOD FOR LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION
- 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