Error Analysis of Field Trial Results of a Spoken Dialogue System for Telecommunications Applications

Shingo KUROIWA; Kazuya TAKEDA; Masaki NAITO; Naomi INOUE; Seiichi YAMAMOTO

Error Analysis of Field Trial Results of a Spoken Dialogue System for Telecommunications Applications

Shingo KUROIWA, Kazuya TAKEDA, Masaki NAITO, Naomi INOUE, Seiichi YAMAMOTO

Full Text Views

0

Cite this

Summary :

We carried out a one year field trial of a voice-activated automatic telephone exchange service at KDD Laboratories which has about 200 branch phones. This system has DSP-based continuous speech recognition hardware which can process incoming calls in real time using a vocabulary of 300 words. The recognition accuracy was found to be 92.5% for speech read from a written text under laboratory conditions independent of the speaker. In this paper, we describe the performance of the system obtained as a result of the field trial. Apart from recognition accuracy, there was about 20% error due to out-of-vocabulary input and incorrect detection of speech endpoints which had not been allowed for in the laboratory experiments. Also, we found that the recognition accuracy for actual speech was about 18% lower than for speech read from text even if there were no out-of-vocabulary words. In this paper, we examine error variations for individual data in order to try and pinpoint the cause of incorrect recognition. It was found from experiments on the collected data that the pause model used, filled pause grammar and differences of channel frequency response seriously affected recognition accuracy. With the help of simple techniques to overcome these problems, we finally obtained a recognition accuracy of 88.7% for real data.

Publication: IEICE TRANSACTIONS on Information Vol.E78-D No.6 pp.636-641

Publication Date: 1995/06/25

Publicized

Online ISSN

DOI

Type of Manuscript: Special Section PAPER (Special Issue on Spoken Language Processing)

Category

Cite this

Copy

Shingo KUROIWA, Kazuya TAKEDA, Masaki NAITO, Naomi INOUE, Seiichi YAMAMOTO, "Error Analysis of Field Trial Results of a Spoken Dialogue System for Telecommunications Applications" in IEICE TRANSACTIONS on Information, vol. E78-D, no. 6, pp. 636-641, June 1995, doi: .
Abstract: We carried out a one year field trial of a voice-activated automatic telephone exchange service at KDD Laboratories which has about 200 branch phones. This system has DSP-based continuous speech recognition hardware which can process incoming calls in real time using a vocabulary of 300 words. The recognition accuracy was found to be 92.5% for speech read from a written text under laboratory conditions independent of the speaker. In this paper, we describe the performance of the system obtained as a result of the field trial. Apart from recognition accuracy, there was about 20% error due to out-of-vocabulary input and incorrect detection of speech endpoints which had not been allowed for in the laboratory experiments. Also, we found that the recognition accuracy for actual speech was about 18% lower than for speech read from text even if there were no out-of-vocabulary words. In this paper, we examine error variations for individual data in order to try and pinpoint the cause of incorrect recognition. It was found from experiments on the collected data that the pause model used, filled pause grammar and differences of channel frequency response seriously affected recognition accuracy. With the help of simple techniques to overcome these problems, we finally obtained a recognition accuracy of 88.7% for real data.
URL: https://global.ieice.org/en_transactions/information/10.1587/e78-d_6_636/_p

Copy

@ARTICLE{e78-d_6_636,
author={Shingo KUROIWA, Kazuya TAKEDA, Masaki NAITO, Naomi INOUE, Seiichi YAMAMOTO, },
journal={IEICE TRANSACTIONS on Information},
title={Error Analysis of Field Trial Results of a Spoken Dialogue System for Telecommunications Applications},
year={1995},
volume={E78-D},
number={6},
pages={636-641},
abstract={We carried out a one year field trial of a voice-activated automatic telephone exchange service at KDD Laboratories which has about 200 branch phones. This system has DSP-based continuous speech recognition hardware which can process incoming calls in real time using a vocabulary of 300 words. The recognition accuracy was found to be 92.5% for speech read from a written text under laboratory conditions independent of the speaker. In this paper, we describe the performance of the system obtained as a result of the field trial. Apart from recognition accuracy, there was about 20% error due to out-of-vocabulary input and incorrect detection of speech endpoints which had not been allowed for in the laboratory experiments. Also, we found that the recognition accuracy for actual speech was about 18% lower than for speech read from text even if there were no out-of-vocabulary words. In this paper, we examine error variations for individual data in order to try and pinpoint the cause of incorrect recognition. It was found from experiments on the collected data that the pause model used, filled pause grammar and differences of channel frequency response seriously affected recognition accuracy. With the help of simple techniques to overcome these problems, we finally obtained a recognition accuracy of 88.7% for real data.},
keywords={},
doi={},
ISSN={},
month={June},}

Copy

TY - JOUR
TI - Error Analysis of Field Trial Results of a Spoken Dialogue System for Telecommunications Applications
T2 - IEICE TRANSACTIONS on Information
SP - 636
EP - 641
AU - Shingo KUROIWA
AU - Kazuya TAKEDA
AU - Masaki NAITO
AU - Naomi INOUE
AU - Seiichi YAMAMOTO
PY - 1995
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E78-D
IS - 6
JA - IEICE TRANSACTIONS on Information
Y1 - June 1995
AB - We carried out a one year field trial of a voice-activated automatic telephone exchange service at KDD Laboratories which has about 200 branch phones. This system has DSP-based continuous speech recognition hardware which can process incoming calls in real time using a vocabulary of 300 words. The recognition accuracy was found to be 92.5% for speech read from a written text under laboratory conditions independent of the speaker. In this paper, we describe the performance of the system obtained as a result of the field trial. Apart from recognition accuracy, there was about 20% error due to out-of-vocabulary input and incorrect detection of speech endpoints which had not been allowed for in the laboratory experiments. Also, we found that the recognition accuracy for actual speech was about 18% lower than for speech read from text even if there were no out-of-vocabulary words. In this paper, we examine error variations for individual data in order to try and pinpoint the cause of incorrect recognition. It was found from experiments on the collected data that the pause model used, filled pause grammar and differences of channel frequency response seriously affected recognition accuracy. With the help of simple techniques to overcome these problems, we finally obtained a recognition accuracy of 88.7% for real data.
ER -