Performance estimation of noisy speech recognition considering recognition task complexity

Takeshi Yamada; Tomohiro Nakajima; Nobuhiko Kitawaki; Shoji Makino

Performance estimation of noisy speech recognition considering recognition task complexity

Takeshi Yamada^*, Tomohiro Nakajima, Nobuhiko Kitawaki, Shoji Makino

^*Corresponding author for this work

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

4 Citations (Scopus)

Abstract

To ensure a satisfactory QoE (Quality of Experience) and facilitate system design in speech recognition services, it is essential to establish a method that can be used to efficiently investigate recognition performance in different noise environments. Previously, we proposed a performance estimation method using a spectral distortion measure. However, there is the problem that recognition task complexity affects the relationship between the recognition performance and the distortion value. To solve this problem, this paper proposes a novel performance estimation method considering the recognition task complexity. We confirmed that the proposed method gives accurate estimates of the recognition performance for various recognition tasks by an experiment using noisy speech data recorded in a real room.

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	2042-2045
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

Noisy speech recognition
Performance estimation
Recognition task difficulty

ASJC Scopus subject areas

Language and Linguistics
Speech and Hearing
Human-Computer Interaction
Signal Processing
Software
Modelling and Simulation

Cite this

Yamada, T., Nakajima, T., Kitawaki, N., & Makino, S. (2010). Performance estimation of noisy speech recognition considering recognition task complexity. In Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010 (pp. 2042-2045). (Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010). International Speech Communication Association.

Performance estimation of noisy speech recognition considering recognition task complexity. / Yamada, Takeshi; Nakajima, Tomohiro; Kitawaki, Nobuhiko et al.
Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010. International Speech Communication Association, 2010. p. 2042-2045 (Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010).

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

Yamada, T, Nakajima, T, Kitawaki, N & Makino, S 2010, Performance estimation of noisy speech recognition considering recognition task complexity. 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. 2042-2045.

Yamada T, Nakajima T, Kitawaki N, Makino S. Performance estimation of noisy speech recognition considering recognition task complexity. In Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010. International Speech Communication Association. 2010. p. 2042-2045. (Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010).

Yamada, Takeshi ; Nakajima, Tomohiro ; Kitawaki, Nobuhiko et al. / Performance estimation of noisy speech recognition considering recognition task complexity. Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010. International Speech Communication Association, 2010. pp. 2042-2045 (Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010).

@inproceedings{b2a016530f1e4e0a999862ed4828fff7,

title = "Performance estimation of noisy speech recognition considering recognition task complexity",

abstract = "To ensure a satisfactory QoE (Quality of Experience) and facilitate system design in speech recognition services, it is essential to establish a method that can be used to efficiently investigate recognition performance in different noise environments. Previously, we proposed a performance estimation method using a spectral distortion measure. However, there is the problem that recognition task complexity affects the relationship between the recognition performance and the distortion value. To solve this problem, this paper proposes a novel performance estimation method considering the recognition task complexity. We confirmed that the proposed method gives accurate estimates of the recognition performance for various recognition tasks by an experiment using noisy speech data recorded in a real room.",

keywords = "Noisy speech recognition, Performance estimation, Recognition task difficulty",

author = "Takeshi Yamada and Tomohiro Nakajima and Nobuhiko Kitawaki and Shoji Makino",

note = "Funding Information: This work was supported in part by the Telecommunications Advancement Foundation.",

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 = "2042--2045",

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

}

TY - GEN

T1 - Performance estimation of noisy speech recognition considering recognition task complexity

AU - Yamada, Takeshi

AU - Nakajima, Tomohiro

AU - Kitawaki, Nobuhiko

AU - Makino, Shoji

N1 - Funding Information: This work was supported in part by the Telecommunications Advancement Foundation.

PY - 2010

Y1 - 2010

N2 - To ensure a satisfactory QoE (Quality of Experience) and facilitate system design in speech recognition services, it is essential to establish a method that can be used to efficiently investigate recognition performance in different noise environments. Previously, we proposed a performance estimation method using a spectral distortion measure. However, there is the problem that recognition task complexity affects the relationship between the recognition performance and the distortion value. To solve this problem, this paper proposes a novel performance estimation method considering the recognition task complexity. We confirmed that the proposed method gives accurate estimates of the recognition performance for various recognition tasks by an experiment using noisy speech data recorded in a real room.

AB - To ensure a satisfactory QoE (Quality of Experience) and facilitate system design in speech recognition services, it is essential to establish a method that can be used to efficiently investigate recognition performance in different noise environments. Previously, we proposed a performance estimation method using a spectral distortion measure. However, there is the problem that recognition task complexity affects the relationship between the recognition performance and the distortion value. To solve this problem, this paper proposes a novel performance estimation method considering the recognition task complexity. We confirmed that the proposed method gives accurate estimates of the recognition performance for various recognition tasks by an experiment using noisy speech data recorded in a real room.

KW - Noisy speech recognition

KW - Performance estimation

KW - Recognition task difficulty

UR - http://www.scopus.com/inward/record.url?scp=79959840360&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79959840360&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:79959840360

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

SP - 2042

EP - 2045

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

PB - International Speech Communication Association

ER -

Performance estimation of noisy speech recognition considering recognition task complexity

Abstract

Publication series

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this