상세정보
학술대회
Hypo and Hyperarticulated Speech Data Augmentation for Spontaneous Speech Recognition
- 발행일
- 201809
- 출처
- European Signal Processing Conference (EUSIPCO) 2018, pp.2094-2098
- 협약과제
- 18HS3700, 언어학습을 위한 자유발화형 음성대화처리 원천기술 개발, 이윤근
- 초록
- Among many challenges in spontaneous speech recognition, we focus on the variability of speech depending on the degree of articulation such as hypo and hyperarticulation. In this paper, we investigate the feasibility of the past acoustic-phonetic studies on the variability of speech in terms of the data augmentation of a spontaneous speech recognition system. To do so, we develop data augmentation approaches to reflect the acoustic-phonetic characteristics of hypo and hyperarticulated speech. Since our approaches are based on signal processing methods they do not require a model learned from supervised or unsupervised data. A series of speech recognition tests are conducted across various speech styles. The results show that we are able to achieve meaningful performance gain by using our approaches. It also indicates that the past acoustic-phonetic knowledge of the variability of speech is useful for improving the recognition performance of spontaneous speech including hypo and hyper-articulated speech.
- KSP 제안 키워드
- Data Augmentation, Performance gain, Processing Method, Signal Processing, Speech recognition system, recognition performance, spontaneous speech