Direct-to-Reverberant ratio estimation on the ACE corpus using a Two-channel beamformer
File(s)1510.07546v1.pdf (545.77 KB)
Accepted version
Author(s)
Eaton, J
Naylor, PA
Type
Conference Paper
Abstract
Direct-to-Reverberant Ratio (DRR) is an important measure for characterizing the properties of a room. The recently proposed DRR Estimation using a Null-Steered Beamformer (DENBE) algorithm was originally tested on simulated data where noise was artificially added to the speech after convolution with impulse responses simulated using the image-source method. This paper evaluates the performance of this algorithm on speech convolved with measured impulse responses and noise using the Acoustic Characterization of Environments (ACE) Evaluation corpus. The fullband DRR estimation performance of the DENBE algorithm exceeds that of the baselines in all Signal-to-Noise Ratios (SNRs) and noise types. In addition, estimation of the DRR in one third-octave ISO frequency bands is demonstrated.
Date Issued
2015-10-18
Date Acceptance
2015-07-02
Citation
Proc. ACE Challenge Workshop, a satellite event of IEEE-WASPAA, 2015
Publisher
arXiv
Journal / Book Title
Proc. ACE Challenge Workshop, a satellite event of IEEE-WASPAA
Copyright Statement
© 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Identifier
http://arxiv.org/abs/1510.07546
Source
ACE Challenge Workshop, a satellite event of IEEE-WASPAA
Subjects
Direct-to-Reverberant ratio
speech processing
room impulse response
Place of Publication
arXiv
Publication Status
Published
Start Date
2015-10-18
Finish Date
2015-10-21
Coverage Spatial
New Paltz, New York