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
OA 2106.05627.pdf 295.97 KB
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
Access Level
OA Open Access
Last Uploaded
2023-11-15T15:29:32Z


Link(s) to Main File(s)
Access Level
Restricted Closed Access

Export

Marked Publications

Open Data LibreCat

Sources

arXiv 2106.05627

Search this title in

Google Scholar