A robust speech recognition system against the ego noise of a robot

Gökhan Ince; Kazuhiro Nakadai; Tobias Rodemann; Hiroshi Tsujino; Jun Ichi Imura

A robust speech recognition system against the ego noise of a robot

Gökhan Ince^*, Kazuhiro Nakadai, Tobias Rodemann, Hiroshi Tsujino, Jun Ichi Imura

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Citation (Scopus)

Abstract

This paper presents a speech recognition system for a mobile robot that attains a high recognition performance, even if the robot generates ego-motion noise. We investigate noise suppression and speech enhancement methods that are based on prediction of ego-motion and its noise. The estimation of egomotion is used for superimposing white noise in a selective manner based on the ego-motion type. Moreover, instantaneous prediction of ego-motion noise is the core concept to establish the following techniques: ego-motion noise suppression by template subtraction and missing feature theory based masking of noisy speech features. We evaluate the proposed technique on a robot using speech recognition results. Adaptive superimposition of white noise achieves up to 20% improvement of word correct rates (WCR) and the spectrographic mask attains an additional improvement of up to 10% compared to the single channel recognition.

Original language	English
Title of host publication	Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010
Publisher	International Speech Communication Association
Pages	2070-2073
Number of pages	4
Publication status	Published - 2010
Externally published	Yes

Publication series

Name	Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010

Keywords

ASR
Noise reduction
Speech enhancement

Cite this

Ince, G., Nakadai, K., Rodemann, T., Tsujino, H., & Imura, J. I. (2010). A robust speech recognition system against the ego noise of a robot. In Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010 (pp. 2070-2073). (Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010). International Speech Communication Association.

Ince, Gökhan ; Nakadai, Kazuhiro ; Rodemann, Tobias et al. / A robust speech recognition system against the ego noise of a robot. Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010. International Speech Communication Association, 2010. pp. 2070-2073 (Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010).

@inproceedings{5f5bd9f5a7d3406688a34a42b32bb530,

title = "A robust speech recognition system against the ego noise of a robot",

abstract = "This paper presents a speech recognition system for a mobile robot that attains a high recognition performance, even if the robot generates ego-motion noise. We investigate noise suppression and speech enhancement methods that are based on prediction of ego-motion and its noise. The estimation of egomotion is used for superimposing white noise in a selective manner based on the ego-motion type. Moreover, instantaneous prediction of ego-motion noise is the core concept to establish the following techniques: ego-motion noise suppression by template subtraction and missing feature theory based masking of noisy speech features. We evaluate the proposed technique on a robot using speech recognition results. Adaptive superimposition of white noise achieves up to 20% improvement of word correct rates (WCR) and the spectrographic mask attains an additional improvement of up to 10% compared to the single channel recognition.",

keywords = "ASR, Noise reduction, Speech enhancement",

author = "G{\"o}khan Ince and Kazuhiro Nakadai and Tobias Rodemann and Hiroshi Tsujino and Imura, {Jun Ichi}",

year = "2010",

language = "English",

series = "Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010",

publisher = "International Speech Communication Association",

pages = "2070--2073",

booktitle = "Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010",

}

Ince, G, Nakadai, K, Rodemann, T, Tsujino, H & Imura, JI 2010, A robust speech recognition system against the ego noise of a robot. in Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010. Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010, International Speech Communication Association, pp. 2070-2073.

A robust speech recognition system against the ego noise of a robot. / Ince, Gökhan; Nakadai, Kazuhiro; Rodemann, Tobias et al.
Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010. International Speech Communication Association, 2010. p. 2070-2073 (Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A robust speech recognition system against the ego noise of a robot

AU - Ince, Gökhan

AU - Nakadai, Kazuhiro

AU - Rodemann, Tobias

AU - Tsujino, Hiroshi

AU - Imura, Jun Ichi

PY - 2010

Y1 - 2010

N2 - This paper presents a speech recognition system for a mobile robot that attains a high recognition performance, even if the robot generates ego-motion noise. We investigate noise suppression and speech enhancement methods that are based on prediction of ego-motion and its noise. The estimation of egomotion is used for superimposing white noise in a selective manner based on the ego-motion type. Moreover, instantaneous prediction of ego-motion noise is the core concept to establish the following techniques: ego-motion noise suppression by template subtraction and missing feature theory based masking of noisy speech features. We evaluate the proposed technique on a robot using speech recognition results. Adaptive superimposition of white noise achieves up to 20% improvement of word correct rates (WCR) and the spectrographic mask attains an additional improvement of up to 10% compared to the single channel recognition.

AB - This paper presents a speech recognition system for a mobile robot that attains a high recognition performance, even if the robot generates ego-motion noise. We investigate noise suppression and speech enhancement methods that are based on prediction of ego-motion and its noise. The estimation of egomotion is used for superimposing white noise in a selective manner based on the ego-motion type. Moreover, instantaneous prediction of ego-motion noise is the core concept to establish the following techniques: ego-motion noise suppression by template subtraction and missing feature theory based masking of noisy speech features. We evaluate the proposed technique on a robot using speech recognition results. Adaptive superimposition of white noise achieves up to 20% improvement of word correct rates (WCR) and the spectrographic mask attains an additional improvement of up to 10% compared to the single channel recognition.

KW - ASR

KW - Noise reduction

KW - Speech enhancement

UR - http://www.scopus.com/inward/record.url?scp=79959849492&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:79959849492

T3 - Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010

SP - 2070

EP - 2073

BT - Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010

PB - International Speech Communication Association

ER -

Ince G, Nakadai K, Rodemann T, Tsujino H, Imura JI. A robust speech recognition system against the ego noise of a robot. In Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010. International Speech Communication Association. 2010. p. 2070-2073. (Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010).

A robust speech recognition system against the ego noise of a robot

Abstract

Publication series

Keywords

Other files and links

Fingerprint

Cite this