| Paper: | SLP-L8.3 | ||
| Session: | Efficient Techniques for LVCSR | ||
| Time: | Thursday, May 18, 14:40 - 15:00 | ||
| Presentation: | Lecture | ||
| Topic: | Speech and Spoken Language Processing: Resource constrained ASR for portable/mobile devices | ||
| Title: | Parallel LVCSR Algorithm for Cellphone-Oriented Multicore Processors | ||
| Authors: | Shin-ya Ishikawa, Kiyoshi Yamabana, Ryosuke Isotani, Akitoshi Okumura, NEC, Japan | ||
| Abstract: | A parallel Large Vocabulary Continuous Speech Recognition (LVCSR) algorithm for cellphone-oriented multicore processors is proposed. We introduce an acoustic look-ahead and blockwise computation to our compact LVCSR algorithm, in order to distribute its computational load to multiple CPU cores. We implement the proposed LVCSR algorithm on an evaluation board of a cellphone-oriented three CPU core chip, and show real-time proccessing of stand-alone LCVSR on cellphones can be achived with recognition vocabulary of about 50,000 words in a travel conversational task. We also implement a speech-input text retrieval system using the proposed LVCSR on the same evaluation board, and confirm the ability of the proposed LVCSR algorithm to provide comfortable responses to query sentences spoken to a cellphone, without requiring any outside resources. | ||
©2018 Conference Management Services, Inc. -||- email: webmaster@icassp2006.org -||- Last updated Friday, August 17, 2012