Performance estimation of noisy speech recognition considering recognition task complexity

  title={Performance estimation of noisy speech recognition considering recognition task complexity},
  author={Takeshi Yamada and Tomohiro Nakajima and Nobuhiko Kitawaki and Shoji Makino},
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… CONTINUE READING

From This Paper

Figures, tables, and topics from this paper.


Publications referenced by this paper.
Showing 1-9 of 9 references

Investigations into the relationship between measurable speech quality and speech recognition rate for telephony speech

2004 IEEE International Conference on Acoustics, Speech, and Signal Processing • 2004
View 1 Excerpt

Predicting the degradation of speech recognition performance from sub-band dynamic ranges

M. Kondo, K. Takeda, F. Itakura
IPSJ Journal, Vol. 43, No. 7, pp. 2242–2248, July 2002. • 2002
View 1 Excerpt

Perceptual evaluation of speech quality (PESQ): An objective method for end-to-end speech quality assessment of narrow-band telephone networks and speech codecs

ITU-T Rec. P.862
Feb. 2001. • 2001
View 1 Excerpt

JNAS: Japanese speech corpus for large vocabulary continuous speech recognition research

K. Itou, M. Yamamoto, +5 authors S. Itahashi
The Journal of the Acoustical Society of Japan, Vol. 20, No. 3, pp. 199–206, May 1999. • 1999
View 1 Excerpt

A new measure of task complexity for continuous speech recognition

S. Nakagawa, M. Ida
The Transactions of the IEICE, Vol. J81-D-2, No. 7, pp. 1491–1500, July 1998. (in Japanese) • 1998
View 1 Excerpt

Tohoku University and Matsushita isolated spoken word database

S. Makino, N. Niyada, Y. Mafune, K. Kido
Journal of the Acoustical Society of Japan, Vol. 48, No. 12, pp. 899–905, 1992. • 1992
View 1 Excerpt

Similar Papers

Loading similar papers…