CENSREC-1-C: An evaluation framework for voice activity detection under noisy environments

Acoustical Science and Technology

Norihide Kitaoka¹⁰  Yuki Denda³  Satoru Tsuge²  Takanobu Nishiura³  Masakiyo Fujimoto¹  Satoshi Nakamura^4,12  Tetsuya Takiguchi⁴  Masato Nakayama³  Takeshi Yamada^4,9  Chiyomi Miyajima¹⁰  Shigeki Matsuda⁸  Kazuya Takeda¹⁰  Shingo Kuroiwa¹¹  Kazumasa Yamamoto⁵  Satoshi Tamura⁶  Tetsuji Ogawa^4,7 

[1] NTT Communication Science Laboratories, NTT Corporation, “Keihanna Science City,”;The University of Tokushima;Ritsumeikan University;Kobe University;Toyohashi University of Technology;Gifu University;Waseda University;ATR Spoken Language Communication Research Labs. and National Institute of Information and Communications Technology, “Keihanna Science City,”;University of Tsukuba;Nagoya University;Chiba University and National Institute of Information and Communications Technology;National Institute of Information and Communications Technology, “Keihanna Science City,”

关键词: Voice activity detection;    Noisy speech processing;    Evaluation framework;   

DOI  :  10.1250/ast.30.363

学科分类：声学和超声波

来源: Acoustical Society of Japan

【 摘 要 】

References(16)Cited-By(5)Voice activity detection (VAD) plays an important role in speech processing including speech recognition, speech enhancement, and speech coding under noisy environments. We have developed an evaluation framework for VAD under noisy environments, named CENSREC-1-C. We designed this framework for simple isolated utterance detection and hence, this framework consists of noisy continuous digit utterances and evaluation tools for VAD results. We define two evaluation measures, one for frame-level detection performance and the other for utterance-level detection performance. We also provide the evaluation results of a power-based VAD method as a reference.

【 授权许可】

Unknown