Art

J-GLOBAL ID：201102280180664540   Reference number：11A1154906

VLSI Architecture of GMM Processing and Viterbi Decoder for 60,000-Word Real-Time Continuous Speech Recognition

60000語実時間連続会話認識のためのGMM処理とViterbi復号器のVLSIアーキテクチャ

Author (6)： NOGUCHI Hiroki (Kobe Univ.) ,  MIURA Kazuo (Kobe Univ.) ,  FUJINAGA Tsuyoshi (Kobe Univ.) ,  SUGAHARA Takanobu (Kobe Univ.) ,  KAWAGUCHI Hiroshi (Kobe Univ.) ,  YOSHIMOTO Masahiko (Kobe Univ.)
Material： IEICE Transactions on Electronics (Institute of Electronics, Information and Communication Engineers)  (IEICE Trans Electron (Inst Electron Inf Commun Eng))
Volume： E94-C  Issue： 4  Page： 458-467 (J-STAGE)  Publication year： 2011 
JST Material Number： L1370A  ISSN： 0916-8524  Document type： Article
Article type： 原著論文  Country of issue： Japan (JPN)  Language： ENGLISH (EN)

Thesaurus term： *speech recognition ,  Time ,  *continuous analysis ,  Gaussian model ,  Viterbi decoding ,  cache memory ,  VLSI
Semi thesaurus term： Gaussian mixture model ,  *Viterbi decoding ,  *VLSI ,  cache memory ,  speech recognition ,  *actual time

JST classification (2)： Code theory  (ND02030R) ,  Semiconductor integrated circuit  (NC03162T)

Reference (9)：

• [1] K. Miura, H. Noguchi, H. Kawaguchi, and M. Yoshimoto, “A low memory bandwidth Gaussian mixture model (GMM) processor for 20,000-word real-time speech recognition FPGA system,” Proc. IEEE Intl. Conf. on Field-Programmable Technology (FPT), pp.341-344, Dec. 2008.
• [2] T. Fujinaga, K. Miura, H. Noguchi, H. Kawaguchi, and M. Yoshimoto, “Parallelized Viterbi processor for 5,000-word large-vocabulary real-time continuous speech recognition FPGA system,” Proc. ISCA Annual Conf. of Intl. Speech Communication Association (Interspeech), pp.1483-1486, Sept. 2009.
• [3] A. Lee, T. Kawahara, and K. Shikano, “Julius — An open source real-time large vocabulary recognition engine,” Proc. European Conf. on Speech Communication and Technology (EUROSPEECH), pp.1691-1694, Sept. 2001.
• [4] E.C. Lin, K. Yu, R.A. Rutenbar, and T. Chen, “A 1000-word vocabulary, speaker-independent, continuous live-mode speech recognizer implemented in a single FPGA,” Proc. 2007 ACM/SIGDA 15th Intl. Symposium on Field Programmable Gate Arrays (FPGA), pp.60-68, Feb. 2007.
• [5] E.C. Lin and R.A. Rutenbar, “A multi-FPGA 10x-real-time high-speed search engine for a 5000-word vocabulary speech recognizer,” Proc. ACM/SIGDA Intl. Symposium on Field Programmable Gate Arrays (FPGA), pp.83-92, Feb. 2009.

Terms in the title (5)： 実時間 ,  会話認識 ,  GMM ,  復号器 ,  VLSIアーキテクチャ