Spoken Term Detection Using Spoken Document Index Based on Keywords Collected from Automatic Speech Recognition Result
Kentaro Domoto 1, Takehito Utsuro 1,
Naoki Sawada 2, and
Hiromitsu Nishizaki 2
1. Graduate School of Systems and Information Engineering, University of Tsukuba, Tsukuba, Japan
2. Department of Education, Interdisplinary Graduate School of Medicine and Engineering, University of Yamanashi, Kofu, Japan
2. Department of Education, Interdisplinary Graduate School of Medicine and Engineering, University of Yamanashi, Kofu, Japan
Abstract—This paper presents a novel spoken document indexing framework for Spoken Term Detection (STD). Our proposed method utilizes an STD method for making an index from keywords collected from outputs from automatic speech recognition systems. The STD method is conducted for all the keywords as query terms; then, the detection result, a set of each keyword and its detection intervals in the spoken document, is obtained. For the keywords that have competitive intervals, we rank them based on the matching cost of STD and select the best one with the longest duration among competitive detections. This is the final output of STD process and serves as an index word for the spoken document. The proposed framework was evaluated on real lecture speeches as spoken documents in an STD task. The results show that our framework was quite effective for preventing false detection errors and in annotating keyword indices to spoken documents.
Index Terms—keyword collection, spoken document indexing, spoken term detection
Cite: Kentaro Domoto, Takehito Utsuro, Naoki Sawada, and Hiromitsu Nishizaki, "Spoken Term Detection Using Spoken Document Index Based on Keywords Collected from Automatic Speech Recognition Result," International Journal of Signal Processing Systems, Vol. 4, No. 4, pp. 282-288, August 2016. doi: 10.18178/ijsps.4.4.282-288
Cite: Kentaro Domoto, Takehito Utsuro, Naoki Sawada, and Hiromitsu Nishizaki, "Spoken Term Detection Using Spoken Document Index Based on Keywords Collected from Automatic Speech Recognition Result," International Journal of Signal Processing Systems, Vol. 4, No. 4, pp. 282-288, August 2016. doi: 10.18178/ijsps.4.4.282-288