Development of vad evaluation framework censrec-1-c and investigation of relationship between vad and speech recognition performance

2007 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2007, Proceedings

Volumn , Issue , 2007, Pages 607-612

  Kitaoka, Norihide ^a   Yamamoto, Kazumasa ^b   Kusamizu, Tomohiro ^b   Nakagawa, Seiichi ^b   Yamada, Takeshi ^c   Tsuge, Satoru ^d   Miyajima, Chiyomi ^a   Nishiura, Takanobu ^e   Nakayama, Masato ^e   Denda, Yuki ^e   Fujimoto, Masakiyo ^f   Takiguchi, Tetsuya ^g   Tamura, Satoshi ^h   Kuroiwa, Shingo ^d   Takeda, Kazuya ^a   Nakamura, Satoshi ⁱ  

^a NAGOYA UNIVERSITY   (Japan)

^b TOYOHASHI UNIVERSITY OF TECHNOLOGY   (Japan)

^c UNIVERSITY OF TSUKUBA   (Japan)

^d UNIVERSITY OF TOKUSHIMA   (Japan)

^e RITSUMEIKAN UNIVERSITY   (Japan)

^f NTT CORPORATION   (Japan)

^g KOBE UNIVERSITY   (Japan)

^h GIFU UNIVERSITY   (Japan)

ⁱ NiCT

Author keywords

Evaluation framework; Noisy speech recognition; Voice activity detection

Indexed keywords

AUTOMATIC SPEECH RECOGNITION (ASR); BALANCE (WEIGHTING); DETECTION PERFORMANCES; EVALUATION FRAMEWORK; EVALUATION MEASURES; EVALUATION RESULTS; EVALUATION TOOLS; EXPERIMENTAL SIMULATIONS; NOISY ENVIRONMENTS; NOISY SPEECH RECOGNITION; SPEECH FRAMES; SPEECH RECOGNITION PERFORMANCE; SPEECH RECOGNIZERS; SPEECH SEGMENTS; VOICE ACTIVITY DETECTION (VAD);

MICROFLUIDICS; MULTITASKING; PROGRAMMING THEORY; SIGNAL DETECTION; SPEECH ANALYSIS; SPEECH CODING; SPEECH ENHANCEMENT; SPEECH PROCESSING; SPEECH RECOGNITION; WIRELESS LOCAL AREA NETWORKS (WLAN);

SPEECH;

EID: 44849110632     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (9)

1. http://elazar.itd.nrl.navy.mil/spine/
2. H. G. Hirsh, D. Pearce, "The AURORA experimental framework for the performance evaluations of speech recognition systems under noisy conditions," ISCAITRW ASR2000, September, 2000
3. Aurora document no. AU/345/01, "Large vocabulary evaluation of front-ends- baseline recognition system description," Mississippi State University, Aug. 2001.
4. AURORA-J/CENSREC Web site: http://sp.shinshu-u.ac.jp/CENSREC/
5. S. Nakamura et al., "AURORA-2J: An Evaluation Framework for Japanese Noisy Speech Recognition," IEICE Transactions on Information and Systems, Vol. E88-D, No. 3, pp. 535-544, 2005.
6. S. Nakamura, M. Fujimoto, and K. Takeda, "CENSREC2: Corpus and Evaluation Environments for In Car Continuous Digit Speech Recognition," Proc. ICSLP '06, pp. 2330-2333, Sept. 2006.
7. M. Fujimoto, K. Takeda, and S. Nakamura, "CENSREC-3: An Evaluation Framework for Japanese Speech Recognition in Real Driving-Car Environments," IEICE Transactions on Information and Systems, (accepted).
8. N. Otsu, "A threshold selection method from gray-level histograms," IEEE Trans. Sys., Man, and Cybernetics, Vol. SMC-9, No. 1, pp. 62-66, 1979.
9. N. Kitaoka and S. Nakagawa. "Evaluation of spectral subtraction with smoothing of time direction on the AURORA 2 task", ICSLP-2002, pp. 465-468, 2002.