Noise Robust Speaker-Independent Speech Recognition with Invariant-Integration Features Using Power-Bias Subtraction

Florian Müller; Alfred Mertins

Noise Robust Speaker-Independent Speech Recognition with Invariant-Integration Features Using Power-Bias Subtraction

Institute of Signal Processing

Abstract

This paper presents new results about the robustness of invariant-integration features (IIF) in noisy conditions. Furthermore, it is shown that a feature-enhancement method known as "powerbias subtraction: for noisy conditions can be combined with the IIF approach to improve its performance in noisy environments while keeping the robustness of the IIFs to mismatching vocal-tract length training-testing conditions. Results of experiments with training on clean speech only as well as experiments with matched-condition training are presented.

Original language	English
Title of host publication	Proc. Interspeech-2011
Number of pages	4
Place of Publication	Florence, Italy
Publisher	International Speech Communication Association (ISCA)
Publication date	01.08.2011
Pages	1677-1680
Publication status	Published - 01.08.2011
Event	12th Annual Conference of the International Speech Communication Association - Florence, Italy Duration: 27.08.2011 → 31.08.2011 Conference number: 92405

UN SDGs

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

Access to Document

https://www.isca-speech.org/archive/archive_papers/interspeech_2011/i11_1677.pdf

Cite this

Müller, F., & Mertins, A. (2011). Noise Robust Speaker-Independent Speech Recognition with Invariant-Integration Features Using Power-Bias Subtraction. In Proc. Interspeech-2011 (pp. 1677-1680). (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH). International Speech Communication Association (ISCA). https://www.isca-speech.org/archive/archive_papers/interspeech_2011/i11_1677.pdf

Müller, Florian ; Mertins, Alfred. / Noise Robust Speaker-Independent Speech Recognition with Invariant-Integration Features Using Power-Bias Subtraction. Proc. Interspeech-2011. Florence, Italy : International Speech Communication Association (ISCA), 2011. pp. 1677-1680 (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH).

@inproceedings{0f2053b758d94703ae7a490d4abfa55e,

title = "Noise Robust Speaker-Independent Speech Recognition with Invariant-Integration Features Using Power-Bias Subtraction",

abstract = "This paper presents new results about the robustness of invariant-integration features (IIF) in noisy conditions. Furthermore, it is shown that a feature-enhancement method known as {"}powerbias subtraction: for noisy conditions can be combined with the IIF approach to improve its performance in noisy environments while keeping the robustness of the IIFs to mismatching vocal-tract length training-testing conditions. Results of experiments with training on clean speech only as well as experiments with matched-condition training are presented. ",

author = "Florian M{\"u}ller and Alfred Mertins",

year = "2011",

month = aug,

day = "1",

language = "English",

series = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",

publisher = " International Speech Communication Association (ISCA)",

pages = "1677--1680",

booktitle = "Proc. Interspeech-2011",

note = "12th Annual Conference of the International Speech Communication Association, INTERSPEECH 2011 ; Conference date: 27-08-2011 Through 31-08-2011",

}

Müller, F & Mertins, A 2011, Noise Robust Speaker-Independent Speech Recognition with Invariant-Integration Features Using Power-Bias Subtraction. in Proc. Interspeech-2011. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, International Speech Communication Association (ISCA), Florence, Italy, pp. 1677-1680, 12th Annual Conference of the International Speech Communication Association, Florence, Italy, 27.08.11. <https://www.isca-speech.org/archive/archive_papers/interspeech_2011/i11_1677.pdf>

Noise Robust Speaker-Independent Speech Recognition with Invariant-Integration Features Using Power-Bias Subtraction. / Müller, Florian; Mertins, Alfred.
Proc. Interspeech-2011. Florence, Italy: International Speech Communication Association (ISCA), 2011. p. 1677-1680 (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH).

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

TY - GEN

T1 - Noise Robust Speaker-Independent Speech Recognition with Invariant-Integration Features Using Power-Bias Subtraction

AU - Müller, Florian

AU - Mertins, Alfred

N1 - Conference code: 92405

PY - 2011/8/1

Y1 - 2011/8/1

N2 - This paper presents new results about the robustness of invariant-integration features (IIF) in noisy conditions. Furthermore, it is shown that a feature-enhancement method known as "powerbias subtraction: for noisy conditions can be combined with the IIF approach to improve its performance in noisy environments while keeping the robustness of the IIFs to mismatching vocal-tract length training-testing conditions. Results of experiments with training on clean speech only as well as experiments with matched-condition training are presented.

AB - This paper presents new results about the robustness of invariant-integration features (IIF) in noisy conditions. Furthermore, it is shown that a feature-enhancement method known as "powerbias subtraction: for noisy conditions can be combined with the IIF approach to improve its performance in noisy environments while keeping the robustness of the IIFs to mismatching vocal-tract length training-testing conditions. Results of experiments with training on clean speech only as well as experiments with matched-condition training are presented.

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-84865744455&origin=inward&txGid=45d45d6cbacb3b55c34866d41a10d2ee

M3 - Conference contribution

T3 - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

SP - 1677

EP - 1680

BT - Proc. Interspeech-2011

PB - International Speech Communication Association (ISCA)

CY - Florence, Italy

T2 - 12th Annual Conference of the International Speech Communication Association

Y2 - 27 August 2011 through 31 August 2011

ER -

Noise Robust Speaker-Independent Speech Recognition with Invariant-Integration Features Using Power-Bias Subtraction

Abstract

UN SDGs

Access to Document

Other files and links

Fingerprint

Invariant features for automatic speech recognition based on complex models of speech production and auditory perception

Cite this

Noise Robust Speaker-Independent Speech Recognition with Invariant-Integration Features Using Power-Bias Subtraction

Abstract

UN SDGs

Access to Document

Other files and links

Fingerprint

Projects

Invariant features for automatic speech recognition based on complex models of speech production and auditory perception

Cite this