Paper Info
Title
Multi-microphone speech enhancement informed by auditory scene analysis
Abstract
A multitude of multi-microphone speech enhancement methods is available. In this paper, we focus our attention to the well-known minimum variance distortionless response (MVDR) beamformer, due to its ability to preserve distortionless response towards the desired speaker while minimizing the output noise power. We explore two alternatives for constructing the steering vectors towards the desired speech source. One is only using the direct path of the speech propagation in the form of delay-only filters, while the other is using the entire room impulse response (RIR). All beamforming methods requires some control information to be able to accomplish the task of enhancing a desired speech signal. In this paper, an acoustic event detection method using biologically-inspired features is employed. It can interpret the auditory scene by detecting the presence of different auditory objects. This is employed to control the estimation procedures used by beamformer. The resulting system provides a blind method of speech enhancement that can improve intelligibility independently of any additional information. Experiments with real recordings show the practical applicability of the method. Significant gain in fwSNRseg is achieved. Compared to using the direct path only, the use of the entire RIR proves beneficial.
Year
DOI
Venue
2016
10.1109/SAM.2016.7569625
2016 IEEE Sensor Array and Multichannel Signal Processing Workshop (SAM)
Keywords
Field
DocType
microphone array,auditory scene analysis,blind beamformer for speech enhancement
Speech enhancement,Beamforming,Speech processing,Impulse response,Auditory scene analysis,Computer science,Voice activity detection,Speech recognition,Microphone,Intelligibility (communication)
Conference
ISBN
Citations 
PageRank 
978-1-5090-2104-8
1
0.35
References 
Authors
21
2
Name
Order
Citations
PageRank
Axel Plinge1727.47
Sharon Gannot21754130.51