상세정보
학술지
원어민 및 외국인 화자의 음성 인식을 위한 심층 신경망 기반 음향 모델링
- 저자
- 강병옥, 권오욱
- 발행일
- 201706
- 출처
- 말소리와 음성과학, v.9 no.2, pp.95-101
- ISSN
- 2005-8063
- 협약과제
- 17HS5700, 언어학습을 위한 자유발화형 음성대화처리 원천기술 개발, 이윤근
- 초록
- This paper proposes a new method to train Deep Neural Network (DNN)-based acoustic models for speech recognition of native and foreign speakers. The proposed method consists of determining multi-set state clusters with various acoustic properties, training a DNN-based acoustic model, and recognizing speech based on the model. In the proposed method, hidden nodes of DNN are shared, but output nodes are separated to accommodate different acoustic properties for native and foreign speech. In an English speech recognition task for speakers of Korean and English respectively, the proposed method is shown to slightly improve recognition accuracy compared to the conventional multi-condition training method.
- KSP 제안 키워드
- Acoustic properties, DNN-based acoustic model, Deep neural network(DNN), Foreign speech, Hidden nodes, Multi-condition training, Recognition Accuracy, multi-set, new method, speech recognition, training method