Improving Multiband Position-Pitch Algorithm for Localization and Tracking of Multiple Concurrent Speakers by Using a Frequency Selective Criterion

TitleImproving Multiband Position-Pitch Algorithm for Localization and Tracking of Multiple Concurrent Speakers by Using a Frequency Selective Criterion
Publication TypeConference Paper
Year of Publication2011
AuthorsHabib, T., & Romsdorfer H.
Conference NameInterspeech
Pages2897-2900
Date Published09/2011
Conference LocationFlorence, Italy
Abstract

 We present an auditory inspired frequency selective extension to the multiband position-pitch (MPoPi) algorithm and a new particle filtering algorithm for localization and tracking of an arbitrary number of concurrent speakers. In the particle filtering framework, we combine standard bootstrap with importance sampling techniques. The proposed algorithm was tested on real-world recordings using a 24 channel microphone array in a meeting room for different location and speaker combinations. The results show that using the frequency selective criterion outperforms state-of-the-art and our original algorithms.

 

Citation Key2213
Refereed DesignationRefereed
SPSC cross-references