Abstract
In this paper, a way to classify and edit lengthy speech material in sound scene, including various sounds such as TV/radio or meeting and discussion speech, is discussed on the premise of no prior information hypothesis. The proposed method is comprised of two technical parts. One is voice clustering, based on the vector quantization (VQ) distortion as the criterion, and the other is automatic adaptive threshold estimation. This application is, especially, convenient and fast for creating the speech database or speech searching using the audio data. The experimental results show the F-measure value of 94.13% on the conversation speech 1.67 hours, and a clustering rate of 84.1% on speaker sound of the 30 minutes from phone calling voice including various noises. Without a training model and a short utterance, we conformed that the VQ distortion measure and the dynamic threshold estimating approach are easy to implement and convenient to one-set recording sound scene (category) clustering.
This research is supported by funds NNSFC (No.61063024, 61163030) and NSFXJT(No.2011211A012).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Delacour, P., et al.: Based Segmentation for Audio Data Indexing, TU dalacour@eurecom.frUT
Kawahara, T., Akita, Y.: Unsupervised Speaker Indexing of Discussions Using Anchor Models. IEICE Trans. Inf. Syst. (D-II) J87-d-II(2), 495–503 (2004)
Liu, D., Kubala, F.: Fast speaker change detection for broadcast news transcription and indexing. In: Proc. Eurospeech, pp. 1031–1034 (1999)
Solomonoff, A., Mielke, A., et al.: Clustering speakers by their voice Pro. In: ICASSP, vol. 2, pp. 757–760 (1998)
Nakagawa, S., Mori, K.: Speaker Change detection and Speaker Clustering Using VQ Distortion Measure. System and Computer in Japan 34(13) (2003)
Herbert, et al.: Segregation of Speaker for Speech Recognition and Speaker Identification, CH2977-7/0000-0873 $1.00©. IEEE (1991)
Kawahara, T., et al.: Sharable software repository for Japanese large vocabulary continues speech recognition. In: Proc. ICSLP, pp. 3257–3260
Dawa, I.: Wushour Silamu: Free calling Speaker Recognition System Based on GMM Using LPC Plus Pitch Components. Journal of Chinese Information Processing 25(4), 114–148 (2010)
Taguma, R., Furui, S., et al.: A study on sound sequence segmentation and evaluation methods. ASJ Meeting, 1-Q-2, 0 (2000)
Dawa, L.I., Silamu, W.: A Speaker Recognition System based on GMM-UBM/SVM. J. Computer Applicatin and Software 29(1), 45–49 (2011)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Yidemucao, D., Zhao, Z., Silamu, W.s. (2012). Sound Scene Clustering without Prior Knowledge. In: Liu, CL., Zhang, C., Wang, L. (eds) Pattern Recognition. CCPR 2012. Communications in Computer and Information Science, vol 321. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33506-8_75
Download citation
DOI: https://doi.org/10.1007/978-3-642-33506-8_75
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-33505-1
Online ISBN: 978-3-642-33506-8
eBook Packages: Computer ScienceComputer Science (R0)