This paper introduces a common database, an evaluation framework, and its baseline recognition results for in-car speech recognition, CENSREC-3, as an outcome of the IPSJ-SIG SLP Noisy Speech Recognition Evaluation Working Group. CENSREC-3, which is a sequel to AURORA-2J, has been designed as the evaluation framework of isolated word recognition in real car-driving environments. Speech data were collected using two microphones, a close-talking microphone and a hands-free microphone, under 16 carefully controlled driving conditions, i.e., combinations of three car speeds and six car conditions. CENSREC-3 provides six evaluation environments designed using speech data collected in these conditions.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Masakiyo FUJIMOTO, Kazuya TAKEDA, Satoshi NAKAMURA, "CENSREC-3: An Evaluation Framework for Japanese Speech Recognition in Real Car-Driving Environments" in IEICE TRANSACTIONS on Information,
vol. E89-D, no. 11, pp. 2783-2793, November 2006, doi: 10.1093/ietisy/e89-d.11.2783.
Abstract: This paper introduces a common database, an evaluation framework, and its baseline recognition results for in-car speech recognition, CENSREC-3, as an outcome of the IPSJ-SIG SLP Noisy Speech Recognition Evaluation Working Group. CENSREC-3, which is a sequel to AURORA-2J, has been designed as the evaluation framework of isolated word recognition in real car-driving environments. Speech data were collected using two microphones, a close-talking microphone and a hands-free microphone, under 16 carefully controlled driving conditions, i.e., combinations of three car speeds and six car conditions. CENSREC-3 provides six evaluation environments designed using speech data collected in these conditions.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e89-d.11.2783/_p
Copy
@ARTICLE{e89-d_11_2783,
author={Masakiyo FUJIMOTO, Kazuya TAKEDA, Satoshi NAKAMURA, },
journal={IEICE TRANSACTIONS on Information},
title={CENSREC-3: An Evaluation Framework for Japanese Speech Recognition in Real Car-Driving Environments},
year={2006},
volume={E89-D},
number={11},
pages={2783-2793},
abstract={This paper introduces a common database, an evaluation framework, and its baseline recognition results for in-car speech recognition, CENSREC-3, as an outcome of the IPSJ-SIG SLP Noisy Speech Recognition Evaluation Working Group. CENSREC-3, which is a sequel to AURORA-2J, has been designed as the evaluation framework of isolated word recognition in real car-driving environments. Speech data were collected using two microphones, a close-talking microphone and a hands-free microphone, under 16 carefully controlled driving conditions, i.e., combinations of three car speeds and six car conditions. CENSREC-3 provides six evaluation environments designed using speech data collected in these conditions.},
keywords={},
doi={10.1093/ietisy/e89-d.11.2783},
ISSN={1745-1361},
month={November},}
Copy
TY - JOUR
TI - CENSREC-3: An Evaluation Framework for Japanese Speech Recognition in Real Car-Driving Environments
T2 - IEICE TRANSACTIONS on Information
SP - 2783
EP - 2793
AU - Masakiyo FUJIMOTO
AU - Kazuya TAKEDA
AU - Satoshi NAKAMURA
PY - 2006
DO - 10.1093/ietisy/e89-d.11.2783
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E89-D
IS - 11
JA - IEICE TRANSACTIONS on Information
Y1 - November 2006
AB - This paper introduces a common database, an evaluation framework, and its baseline recognition results for in-car speech recognition, CENSREC-3, as an outcome of the IPSJ-SIG SLP Noisy Speech Recognition Evaluation Working Group. CENSREC-3, which is a sequel to AURORA-2J, has been designed as the evaluation framework of isolated word recognition in real car-driving environments. Speech data were collected using two microphones, a close-talking microphone and a hands-free microphone, under 16 carefully controlled driving conditions, i.e., combinations of three car speeds and six car conditions. CENSREC-3 provides six evaluation environments designed using speech data collected in these conditions.
ER -