speech - Sound Zones

Paper: Multizone Soundfield Reproduction With Privacy- and Quality-Based Speech Masking Filters

In this work, the authors present a comprehensive methodology for multizone sound field reproduction using specially designed speech masking filters. The masking filters are designed to maximise speech privacy and quality. Trade-offs between speech privacy and quality are shown to exist and parameters are provided in the methods to control those trade-offs. An accurate and precise formulation of grating lobes from spatial aliasing in multizone reproduction scenarios is provided and used to enhance the masking filters. The mathematical descriptions and thorough methodology are evaluated using simulations and a real world implementation of a multizone sound field reproduction system.

Continue reading Paper: Multizone Soundfield Reproduction With Privacy- and Quality-Based Speech Masking Filters

Paper: Blind Speaker Counting in Highly Reverberant Environments by Clustering Coherence Features

Using only two microphones, like those commonly found on mobile devices, we show in this work how to count the number of people talking in a meeting scenario. This paper has been presented at and published in the proceedings of the 2017 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) in Kuala Lumpur, Malaysia.

Continue reading Paper: Blind Speaker Counting in Highly Reverberant Environments by Clustering Coherence Features

An even faster, parallel, MATLAB executable (MEX) compilation of the PESQ measure

In a previous post of mine (which you should read now if you haven’t already) I explained how to create a MATLAB executable for the widely used PESQ algorithm. The main reason for wanting to do this was to save time when running a large amount of speech quality tests and the speed increases obtained from using a PESQ MEX function were amazing! At the time of writing that post, the MEX function was approximately 8 times faster than anything else online that I could find. In fact, it is still the fastest implementation I can find, however, I think there is room for improvement and I finally found some time to get it working. In this post, I will show step-by-step how you can compile the PESQ MEX function to accept audio vectors directly from MATLAB and, which, should give great speed increases when run on parallel cores.

Continue reading An even faster, parallel, MATLAB executable (MEX) compilation of the PESQ measure

Paper: Active Speech Control using Wave-Domain Processing with a Linear Wall of Dipole Secondary Sources

Ever wondered if you could cancel someones voice without the need for a physical wall or partition? In this work presented at ICASSP 2017 in New Orleans, USA, we investigate the possibilities of cancelling speech over a loudspeaker wall. The method is not limited to speech, in-fact, it works much better for periodic signals as the non-stationarity of speech degrades the performance.

Continue reading Paper: Active Speech Control using Wave-Domain Processing with a Linear Wall of Dipole Secondary Sources

Paper: Towards Real-Time Source Counting by Estimation of Coherent-to-Diffuse Ratios from Ad-Hoc Microphone Array Recordings

Blindly counting the number of speech sources (talkers) in a meeting room can be a difficult task. This paper was presented at HSCMA 2017 at the Google Offices in San Francisco and shows how using coherent-to-diffuse ratios could allow real-time source counting.

Continue reading Paper: Towards Real-Time Source Counting by Estimation of Coherent-to-Diffuse Ratios from Ad-Hoc Microphone Array Recordings