Pitch-based non-intrusive objective intelligibility prediction

Charlotte Sorensen; Angeliki Xenaki; Jesper B. Boldt; Mads G. Christensen

doi:10.1109/ICASSP.2017.7952183

Pitch-based non-intrusive objective intelligibility prediction

Charlotte Sorensen^*, Angeliki Xenaki, Jesper B. Boldt, Mads G. Christensen

^*Corresponding author for this work

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

10 Citations (Scopus)

74 Downloads (Pure)

Abstract

Automatic adjustment of the hearing aid according to the intelligibility for the user in the environment could be beneficial. While most intelligibility metrics require a clean speech reference, i.e. intrusive methods, this is rarely available in real-life. This paper proposes a non-intrusive intelligibility metric in which a reconstruction of the clean speech is used in the established intrusive short-time objective intelligibility (STOI) metric. The reconstruction of the clean speech is based on pitch-features of the desired source using a spatio-temporal harmonic model. This model takes advantage of both the spatial and spectral separation of the desired source and interferers to reconstruct the clean signal. The simulations show a high correlation between the proposed pitch-based STOI (PB-STOI) and the original intrusive STOI and hence is promising for online processing of intelligibility.

Original language	English
Title of host publication	2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings
Number of pages	5
Publisher	IEEE
Publication date	16 Jun 2017
Pages	386-390
Article number	7952183
ISBN (Electronic)	9781509041176
DOIs	https://doi.org/10.1109/ICASSP.2017.7952183
Publication status	Published - 16 Jun 2017
Event	2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - New Orleans, United States Duration: 5 Mar 2017 → 9 Mar 2017

Conference

Conference	2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017
Country/Territory	United States
City	New Orleans
Period	05/03/2017 → 09/03/2017
Sponsor	The Institute of Electrical and Electronics Engineers Signal Processing Society

Keywords

hearing aids
non-intrusive objective intelligibility prediction
Pitch estimation

Access to Document

10.1109/ICASSP.2017.7952183

sorensenSubmitted manuscript, 3.47 MB

AUB Link

Search for the material in Aalborg University Library's search engine

Cite this

@inproceedings{1f8a087efd8940be9c971e8de03099a5,

title = "Pitch-based non-intrusive objective intelligibility prediction",

abstract = "Automatic adjustment of the hearing aid according to the intelligibility for the user in the environment could be beneficial. While most intelligibility metrics require a clean speech reference, i.e. intrusive methods, this is rarely available in real-life. This paper proposes a non-intrusive intelligibility metric in which a reconstruction of the clean speech is used in the established intrusive short-time objective intelligibility (STOI) metric. The reconstruction of the clean speech is based on pitch-features of the desired source using a spatio-temporal harmonic model. This model takes advantage of both the spatial and spectral separation of the desired source and interferers to reconstruct the clean signal. The simulations show a high correlation between the proposed pitch-based STOI (PB-STOI) and the original intrusive STOI and hence is promising for online processing of intelligibility.",

keywords = "hearing aids, non-intrusive objective intelligibility prediction, Pitch estimation",

author = "Charlotte Sorensen and Angeliki Xenaki and Boldt, {Jesper B.} and Christensen, {Mads G.}",

year = "2017",

month = jun,

day = "16",

doi = "10.1109/ICASSP.2017.7952183",

language = "English",

pages = "386--390",

booktitle = "2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings",

publisher = "IEEE",

address = "United States",

note = "2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 ; Conference date: 05-03-2017 Through 09-03-2017",

}

Sorensen, C, Xenaki, A, Boldt, JB & Christensen, MG 2017, Pitch-based non-intrusive objective intelligibility prediction. in 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings., 7952183, IEEE, pp. 386-390, 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017, New Orleans, United States, 05/03/2017. https://doi.org/10.1109/ICASSP.2017.7952183

Pitch-based non-intrusive objective intelligibility prediction. / Sorensen, Charlotte; Xenaki, Angeliki; Boldt, Jesper B. et al.
2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings. IEEE, 2017. p. 386-390 7952183.

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

TY - GEN

T1 - Pitch-based non-intrusive objective intelligibility prediction

AU - Sorensen, Charlotte

AU - Xenaki, Angeliki

AU - Boldt, Jesper B.

AU - Christensen, Mads G.

PY - 2017/6/16

Y1 - 2017/6/16

N2 - Automatic adjustment of the hearing aid according to the intelligibility for the user in the environment could be beneficial. While most intelligibility metrics require a clean speech reference, i.e. intrusive methods, this is rarely available in real-life. This paper proposes a non-intrusive intelligibility metric in which a reconstruction of the clean speech is used in the established intrusive short-time objective intelligibility (STOI) metric. The reconstruction of the clean speech is based on pitch-features of the desired source using a spatio-temporal harmonic model. This model takes advantage of both the spatial and spectral separation of the desired source and interferers to reconstruct the clean signal. The simulations show a high correlation between the proposed pitch-based STOI (PB-STOI) and the original intrusive STOI and hence is promising for online processing of intelligibility.

AB - Automatic adjustment of the hearing aid according to the intelligibility for the user in the environment could be beneficial. While most intelligibility metrics require a clean speech reference, i.e. intrusive methods, this is rarely available in real-life. This paper proposes a non-intrusive intelligibility metric in which a reconstruction of the clean speech is used in the established intrusive short-time objective intelligibility (STOI) metric. The reconstruction of the clean speech is based on pitch-features of the desired source using a spatio-temporal harmonic model. This model takes advantage of both the spatial and spectral separation of the desired source and interferers to reconstruct the clean signal. The simulations show a high correlation between the proposed pitch-based STOI (PB-STOI) and the original intrusive STOI and hence is promising for online processing of intelligibility.

KW - hearing aids

KW - non-intrusive objective intelligibility prediction

KW - Pitch estimation

UR - http://www.scopus.com/inward/record.url?scp=85023742656&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2017.7952183

DO - 10.1109/ICASSP.2017.7952183

M3 - Article in proceeding

AN - SCOPUS:85023742656

SP - 386

EP - 390

BT - 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings

PB - IEEE

T2 - 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017

Y2 - 5 March 2017 through 9 March 2017

ER -

Pitch-based non-intrusive objective intelligibility prediction

Abstract

Conference

Keywords

Access to Document

AUB Link

Other files and links

Fingerprint

Cite this