A Comparison and Combination of Unsupervised Blind Source Separation Techniques
C. Boeddeker, F. Rautenberg, R. Haeb-Umbach, in: ITG Conference on Speech Communication, 2021.
Download
2106.05627.pdf
295.97 KB
Download (ext.)
Conference Paper
| English
Abstract
Unsupervised blind source separation methods do not require a training phase
and thus cannot suffer from a train-test mismatch, which is a common concern in
neural network based source separation. The unsupervised techniques can be
categorized in two classes, those building upon the sparsity of speech in the
Short-Time Fourier transform domain and those exploiting non-Gaussianity or
non-stationarity of the source signals. In this contribution, spatial mixture
models which fall in the first category and independent vector analysis (IVA)
as a representative of the second category are compared w.r.t. their separation
performance and the performance of a downstream speech recognizer on a
reverberant dataset of reasonable size. Furthermore, we introduce a serial
concatenation of the two, where the result of the mixture model serves as
initialization of IVA, which achieves significantly better WER performance than
each algorithm individually and even approaches the performance of a much more
complex neural network based technique.
Publishing Year
Proceedings Title
ITG Conference on Speech Communication
Conference
ITG Conference on Speech Communication
Conference Location
Kiel
LibreCat-ID
Cite this
Boeddeker C, Rautenberg F, Haeb-Umbach R. A Comparison and Combination of Unsupervised Blind Source Separation Techniques. In: ITG Conference on Speech Communication. ; 2021.
Boeddeker, C., Rautenberg, F., & Haeb-Umbach, R. (2021). A Comparison and Combination of Unsupervised Blind Source Separation Techniques. ITG Conference on Speech Communication. ITG Conference on Speech Communication, Kiel.
@inproceedings{Boeddeker_Rautenberg_Haeb-Umbach_2021, title={A Comparison and Combination of Unsupervised Blind Source Separation Techniques}, booktitle={ITG Conference on Speech Communication}, author={Boeddeker, Christoph and Rautenberg, Frederik and Haeb-Umbach, Reinhold}, year={2021} }
Boeddeker, Christoph, Frederik Rautenberg, and Reinhold Haeb-Umbach. “A Comparison and Combination of Unsupervised Blind Source Separation Techniques.” In ITG Conference on Speech Communication, 2021.
C. Boeddeker, F. Rautenberg, and R. Haeb-Umbach, “A Comparison and Combination of Unsupervised Blind Source Separation Techniques,” presented at the ITG Conference on Speech Communication, Kiel, 2021.
Boeddeker, Christoph, et al. “A Comparison and Combination of Unsupervised Blind Source Separation Techniques.” ITG Conference on Speech Communication, 2021.
All files available under the following license(s):
Copyright Statement:
This Item is protected by copyright and/or related rights. [...]
Main File(s)
File Name
2106.05627.pdf
295.97 KB
Access Level
Open Access
Last Uploaded
2023-11-15T15:29:32Z
Link(s) to Main File(s)
Access Level
Closed Access