DOI QR코드

DOI QR Code

A Study of Automatic Evaluation Platform for Speech Recognition Engine in the Vehicle Environment

자동차 환경내의 음성인식 자동 평가 플랫폼 연구

  • 이성재 (서경대학교 전자공학과 Intelligent Human & Computer Interface 연구실) ;
  • 강선미 (서경대학교 전자공학과 Intelligent Human & Computer Interface 연구실)
  • Received : 2012.05.14
  • Accepted : 2012.06.27
  • Published : 2012.07.31

Abstract

The performance of the speech recognition engine is one of the most critical elements of the in-vehicle speech recognition interface. The objective of this paper is to develop an automated platform for running performance tests on the in-vehicle speech recognition engine. The developed platform comprise of main program, agent program, database management module, and statistical analysis module. A simulation environment for performance tests which mimics the real driving situations was constructed, and it was tested by applying pre-recorded driving noises and a speaker's voice as inputs. As a result, the validity of the results from the speech recognition tests was proved. The users will be able to perform the performance tests for the in-vehicle speech recognition engine effectively through the proposed platform.

주행 중 차량내의 음성인터페이스 에서 음성인식기의 성능은 가장 중요한 부분이다. 본 논문은 차량내 음성인식기의 성능 평가를 자동화하기 위한 플랫폼의 개발에 대한 것이다. 개발된 플랫폼은 주 프로그램, 중계 프로그램 데이터베이스 관리, 통계산출 모듈로 구성된다. 성능 평가에 있어 실제 차량의 주행 조건을 고려한 시뮬레이션 환경이 구축되었고, 미리 녹음된 주행 노이즈와 발화자의 목소리를 마이크를 통해 입력하여 실험하였다. 실험 결과 제안하는 플랫폼에서 얻어진 음성인식 결과의 유효성이 입증되었다. 제안한 플랫폼으로 사용자는 음성인식의 자동화와 인식결과의 효율적인 관리 및 통계산출을 함으로서 차량 음성인식기의 평가를 효과적으로 진행할 수 있다.

Keywords

References

  1. JinWoo Yang, SoonHyob Kim, "A study on Speech Recognition in a Running Automobile", The Journal of the Acoustical Society of Korea pp.3-8 ISSN 1225-4428, 2000.
  2. KwangHyun Lee, "Comparison of Speech Intelligibility & Performance of Speech Recognition in Real Driving Environments", The Joournal of Korean Society of Speech Sciences pp.99-110 ISSN 2005-8063, 2004.
  3. JongGeon Kim, YounSeok Choi, NaeYoung Lee, "Unbalanced ANOVA for Testing Shape Variability in Statistical Shape Analysis", The Korean Journal of Applied Statistics, p317-323, 2010. https://doi.org/10.5351/KJAS.2010.23.2.317
  4. 강성훈, "Head and Torso Simulator를 이용한 음 향측정 및 음장재생"(SeongHoon Kang, "Sound measurement and acoustic field playback using Head and Torso Simulator"), The Joournal of Korean Society of Speech Sciences pp.80-85 ISSN 1225-4428, 1992
  5. P.Damaske, "Head-related two channel stereophony with loudspeaker reproduction." J.Acoust. Soc. Am. 52.pp 1109-1115, 1971.
  6. Takeshi Yamadam, "Performance Estimation of Speech Recognition System Under Noise Conditions Using objective Quality Measures and Artificial Voice", IEEE TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, VOL. 14, NO.6, NOVEMBER 2006.
  7. CheolJun Hwang, DeokSoo Kim, HyunYeol Chung, "Performance Evaluation of Multimodal Speech Recognition System by On-Line Tests", The Journal of Korea Information and Communications Society, 1998.
  8. Nicolas Scheffer, Luciana Ferrer, "THE SRI NIST 2010 SPEAKER RECOGNITION EVALUATION SYSTEM", IEEE Conference on Acoustics, Speech, and Signal Processing (ICASSP), Prague, 2011.

Cited by

  1. Acoustic Driving Simulator Design for Evaluating an In-car Speech Recognizer vol.5, pp.2, 2013, https://doi.org/10.13064/KSSS.2013.5.2.093