Quality assessment for listening-room compensation algorithms

S. Goetze; E. Albertin; M. Kallinger; A. Mertins; K. Kammeyer

doi:10.1109/ICASSP.2010.5496301

Quality assessment for listening-room compensation algorithms

S. Goetze, E. Albertin, M. Kallinger, A. Mertins, K. Kammeyer

Institute of Signal Processing

Abstract

In this contribution various objective measures that can be used to evaluate speech dereverberation algorithms by means of listening-room compensation (LRC) are compared to subjective listening tests. It is shown that technical measures describing the impulse responses are suitable for evaluation of such algorithms. Most signal-based objective measures fail to judge the specific distortions that may be introduced by LRC algorithms like late reverberation since these artifacts are small in amplitude but perceptually relevant due to the loss of masking of the room impulse response. Only one signal-based measure, the so-called perceptual similarity measure (PSM), showed high correlation with subjective rating for the given test setup.

Original language	English
Title of host publication	2010 IEEE International Conference on Acoustics, Speech and Signal Processing
Number of pages	4
Place of Publication	Dallas, TX, USA
Publisher	IEEE
Publication date	01.03.2010
Pages	2450-2453
Article number	5496301
ISBN (Print)	978-1-4244-4295-9
ISBN (Electronic)	978-1-4244-4296-6
DOIs	https://doi.org/10.1109/ICASSP.2010.5496301
Publication status	Published - 01.03.2010
Event	2010 IEEE International Conference on Acoustics, Speech, and Signal Processing - Dallas, United States Duration: 14.03.2010 → 19.03.2010 Conference number: 81981

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/ICASSP.2010.5496301

Cite this

Goetze, S., Albertin, E., Kallinger, M., Mertins, A., & Kammeyer, K. (2010). Quality assessment for listening-room compensation algorithms. In 2010 IEEE International Conference on Acoustics, Speech and Signal Processing (pp. 2450-2453). Article 5496301 (IEEE International Conference on Acoustics, Speech and Signal Processing). IEEE. https://doi.org/10.1109/ICASSP.2010.5496301

@inproceedings{7feb389f678d40a3996999a08b517c0d,

title = "Quality assessment for listening-room compensation algorithms",

abstract = "In this contribution various objective measures that can be used to evaluate speech dereverberation algorithms by means of listening-room compensation (LRC) are compared to subjective listening tests. It is shown that technical measures describing the impulse responses are suitable for evaluation of such algorithms. Most signal-based objective measures fail to judge the specific distortions that may be introduced by LRC algorithms like late reverberation since these artifacts are small in amplitude but perceptually relevant due to the loss of masking of the room impulse response. Only one signal-based measure, the so-called perceptual similarity measure (PSM), showed high correlation with subjective rating for the given test setup.",

author = "S. Goetze and E. Albertin and M. Kallinger and A. Mertins and K. Kammeyer",

year = "2010",

month = mar,

day = "1",

doi = "10.1109/ICASSP.2010.5496301",

language = "English",

isbn = "978-1-4244-4295-9 ",

series = "IEEE International Conference on Acoustics, Speech and Signal Processing",

publisher = "IEEE",

pages = "2450--2453",

booktitle = "2010 IEEE International Conference on Acoustics, Speech and Signal Processing",

note = "2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010 ; Conference date: 14-03-2010 Through 19-03-2010",

}

Goetze, S, Albertin, E, Kallinger, M, Mertins, A & Kammeyer, K 2010, Quality assessment for listening-room compensation algorithms. in 2010 IEEE International Conference on Acoustics, Speech and Signal Processing., 5496301, IEEE International Conference on Acoustics, Speech and Signal Processing, IEEE, Dallas, TX, USA , pp. 2450-2453, 2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, Dallas, Texas, United States, 14.03.10. https://doi.org/10.1109/ICASSP.2010.5496301

Quality assessment for listening-room compensation algorithms. / Goetze, S.; Albertin, E.; Kallinger, M. et al.
2010 IEEE International Conference on Acoustics, Speech and Signal Processing. Dallas, TX, USA : IEEE, 2010. p. 2450-2453 5496301 (IEEE International Conference on Acoustics, Speech and Signal Processing).

Research output: Chapters in Books/Reports/Conference Proceedings › Conference contribution › peer-review

TY - GEN

T1 - Quality assessment for listening-room compensation algorithms

AU - Goetze, S.

AU - Albertin, E.

AU - Kallinger, M.

AU - Mertins, A.

AU - Kammeyer, K.

N1 - Conference code: 81981

PY - 2010/3/1

Y1 - 2010/3/1

N2 - In this contribution various objective measures that can be used to evaluate speech dereverberation algorithms by means of listening-room compensation (LRC) are compared to subjective listening tests. It is shown that technical measures describing the impulse responses are suitable for evaluation of such algorithms. Most signal-based objective measures fail to judge the specific distortions that may be introduced by LRC algorithms like late reverberation since these artifacts are small in amplitude but perceptually relevant due to the loss of masking of the room impulse response. Only one signal-based measure, the so-called perceptual similarity measure (PSM), showed high correlation with subjective rating for the given test setup.

AB - In this contribution various objective measures that can be used to evaluate speech dereverberation algorithms by means of listening-room compensation (LRC) are compared to subjective listening tests. It is shown that technical measures describing the impulse responses are suitable for evaluation of such algorithms. Most signal-based objective measures fail to judge the specific distortions that may be introduced by LRC algorithms like late reverberation since these artifacts are small in amplitude but perceptually relevant due to the loss of masking of the room impulse response. Only one signal-based measure, the so-called perceptual similarity measure (PSM), showed high correlation with subjective rating for the given test setup.

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-78049368127&origin=inward&txGid=cc8505197b8c5a9146d74485caebf220

U2 - 10.1109/ICASSP.2010.5496301

DO - 10.1109/ICASSP.2010.5496301

M3 - Conference contribution

SN - 978-1-4244-4295-9

T3 - IEEE International Conference on Acoustics, Speech and Signal Processing

SP - 2450

EP - 2453

BT - 2010 IEEE International Conference on Acoustics, Speech and Signal Processing

PB - IEEE

CY - Dallas, TX, USA

T2 - 2010 IEEE International Conference on Acoustics, Speech, and Signal Processing

Y2 - 14 March 2010 through 19 March 2010

ER -

Quality assessment for listening-room compensation algorithms

Abstract

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this