The effect of spectro-temporal integration in a probabilistic model for robust acoustic localization

Forfattere

  • Tobias May Eindhoven University of Technology, Department of Human Technology Interaction, P.O. Box 513, NL-5600 MB Eindhoven, The Netherlands
  • Steven van de Par Philips Research, High Tech Campus 36, NL-5656 AE Eindhoven, The Netherlands
  • Armin Kohlrausch Eindhoven University of Technology, Department of Human Technology Interaction, P.O. Box 513, NL-5600 MB Eindhoven, The Netherlands; Philips Research, High Tech Campus 36, NL-5656 AE Eindhoven, The Netherlands

Resumé

A robust acoustic localization model will be presented, which is based on the supervised learning of azimuth-dependent binaural feature maps consisting of interaural time differences (ITD) and interaural level differences (ILD). Motivated by the robust localization performance of the human auditory system, the associated peripheral stage is used in this study as a front-end for binaural cue extraction. Multi-conditional training is performed to take into account the variability of the binaural features which results from the combination of multiple sources, the effect of reverberation and changes in the source/receiver con guration. One way of accumulating evidence of possible sound source locations is to combine information across auditory channels. Alternatively, integrating evidence across groups of time-frequency (T-F) units, so called fragments, which are believed to belong to a single source, was reported to signi cantly improve ITD-based localization performance [Christensen et al., Proc. of Interspeech, 2769-2772 (2007)]. Instead of accumulating the localization cue directly, the proposed model combines likelihoods, taking into account the uncertainty which is associated with the azimuth estimate of a particular T-F unit. Various procedures of controlling the spectro-temporal integration will be discussed and the in uence on sound source localization will be presented.

Referencer

Bregman, A. S. (1990). Auditory Scene Analysis (MIT Press, Cambridge, MA).

Campbell, D. R., Palomäki, K. J., and Brown, G. (2005). “A MATLAB simulation of ”shoebox” room acoustics for use in research and teaching,” Computing and Information Systems 9, 48 – 51.

Christensen, H., Ma, N., Wrigley, S. N., and Barker, J. (2007). “Integrating pitch and localisation cues at a speech fragment level,” Proc. Interspeech , 2769–2772.

Christensen, H., Ma, N., Wrigley, S. N., and Barker, J. (2008). “Improving source localisation in multi-source, reverberant conditions: exploiting local spectro-temporal location cues,” J. Acoust. Soc. Am. 123, 3294 (A).

Christensen, H., Ma, N., Wrigley, S. N., and Barker, J. (2009). “A speech fragment approach to localising multiple speakers in reverberant environments,” IEEE Proc. ICASSP, 4593–4596.

Darwin, C. J. (2008). “Spatial Hearing and Perceiving Sources,” in Auditory perception of sound sources, edited by W. A. Yost, R. R. Fay, and A. N. Popper (Springer Verlag), pp. 215–232.

Garofolo, J. S., Lamel, L. F., Fisher, W. M., Fiscus, J. G., Pallett, D. S., Dahlgren, N. L., and Zue, V. (1993). “TIMIT Acoustic-Phonetic Continuous Speech Corpus,” Technical report NISTIR 4930. National Institute of Standards and Technology, Gaithersburg, MD.

Hu, G. and Wang, D. L. (2007). “Auditory Segmentation Based on Onset and Offset Analysis,” IEEE Trans. Audio, Speech, Lang. Process. 15, 396–405.

May, T., van de Par, S., and Kohlrausch, A. (2009a). “A Probabilistic Model for Robust Acoustic Localization based on an Auditory Front-end,” NAG/DAGA , 254 (A).

May, T., van de Par, S., and Kohlrausch, A. (2009b). “A Probabilistic Model for Robust Localization based on a Binaural Auditory Front-end,” submitted to IEEE Trans. Audio, Speech, Lang. Process. .

Roman, N., Wang, D. L., and Brown, G. J. (2003). “Speech segregation based on sound localization,” J. Acoust. Soc. Am. 114, 2236–2252.

Tomasi, C. and Manduchi, R. (1998). “Bilateral Filtering for Gray and Color Images,” Proc. ICCV , 839 – 846.

Wang, D. L. (2005). “On ideal binary masks as the computational goal of auditory scene analysis,” in Speech Separation by Humans and Machines, edited by P. Divenyi (Kluwer Academic), pp. 181–197.

Yderligere filer

Publiceret

2009-12-15

Citation/Eksport

May, T., van de Par, S., & Kohlrausch, A. (2009). The effect of spectro-temporal integration in a probabilistic model for robust acoustic localization. Proceedings of the International Symposium on Auditory and Audiological Research, 2, 125–134. Hentet fra https://proceedings.isaar.eu/index.php/isaarproc/article/view/2009-13

Nummer

Årg. 2 (2009): Binaural Processing and Spatial Hearing

Sektion

2009/2. Perceptual measures and models of spatial hearing

Licens

Authors who publish with this journal agree to the following terms:

a. Authors retain copyright* and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.

b. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.

c. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).

*From the 2017 issue onward. The Danavox Jubilee Foundation owns the copyright of all articles published in the 1969-2015 issues. However, authors are still allowed to share the work with an acknowledgement of the work's authorship and initial publication in this journal.