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

^*Bu çalışma için yazışmadan sorumlu yazar

Honda Motor Co., Ltd.
Tokyo Inst. Technol., 2-12-1 O.

Araştırma sonucu: Kitap/Rapor/Konferans Bildirisinde Bölüm › Konferans katkısı › bilirkişi

1 Atıf (Scopus)

Özet

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.

Orijinal dil	İngilizce
Ana bilgisayar yayını başlığı	Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010
Yayınlayan	International Speech Communication Association
Sayfalar	2070-2073
Sayfa sayısı	4
Yayın durumu	Yayınlandı - 2010
Harici olarak yayınlandı	Evet

Yayın serisi

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

Diğer Dosyalar ve Linkler

Link to publication in Scopus

Alıntı Yap

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).

Araştırma sonucu: Kitap/Rapor/Konferans Bildirisinde Bölüm › Konferans katkısı › bilirkişi

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 - https://www.scopus.com/pages/publications/79959849492

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

Özet

Yayın serisi

Diğer Dosyalar ve Linkler

Parmak izi

Alıntı Yap