| Presentation | 2013-10-07 A 2.4x-Real-Time VLSI Processor for 60-kWord Continuous Speech Recognition Guangji HE, Yuki MIYAMOTO, IZUMI Shintaro /, Hiroshi KAWAGUCHI, Masahiko YOSHIMOTO, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | This paper describes a low-power VLSI chip for speaker-independent 60-kWord continuous speech recognition based on a context-dependent Hidden Markov Model (HMM). We implement parallel and pipelined architecture for GMM computation and Viterbi processing. It includes a 8-path Viterbi transition architecture to maximize the processing speed and adopts tri-gram language model to improve the recognition accuracy. A two-level cache architecture is implemented for the demo system. The test chip, fabricated in 40 nm CMOS technology, occupies 1.77 mm × 2.18 mm containing 2.98 M transistors for logic and 4.29 Mbit on-chip memory. The measured results show that our implementation achieves 25% required frequency reduction (62.5 MHz) and 26% power consumption reduction (54.8 mW) for 60 k-Word real-time continuous speech recognition compared to the previous work. This chip can maximally process 3.02× and 2.25× times faster than real-time at 200 MHz using the bigram and trigram language models, respectively. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | 40nm VLSI / Hidden Markov Model (HMM) / large vocabulary continuous speech recognition (LVCSR) |
| Paper # | VLD2013-52,ICD2013-76,IE2013-52 |
| Date of Issue |
| Conference Information | |
| Committee | ICD |
|---|---|
| Conference Date | 2013/9/30(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | |
| Vice Chair | |
| Secretary | |
| Assistant | |
| Paper Information | |
| Registration To | Integrated Circuits and Devices (ICD) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | A 2.4x-Real-Time VLSI Processor for 60-kWord Continuous Speech Recognition |
| Sub Title (in English) | |
| Keyword(1) | 40nm VLSI |
| Keyword(2) | Hidden Markov Model (HMM) |
| Keyword(3) | large vocabulary continuous speech recognition (LVCSR) |
| 1st Author's Name | Guangji HE |
| 1st Author's Affiliation | Graduate School of System Informatics, Kobe University() |
| 2nd Author's Name | Yuki MIYAMOTO |
| 2nd Author's Affiliation | / |
| 3rd Author's Name | IZUMI Shintaro / |
| 3rd Author's Affiliation | / / |
| 4th Author's Name | Hiroshi KAWAGUCHI |
| 4th Author's Affiliation | |
| 5th Author's Name | Masahiko YOSHIMOTO |
| 5th Author's Affiliation | |
| Date | 2013-10-07 |
| Paper # | VLD2013-52,ICD2013-76,IE2013-52 |
| Volume (vol) | vol.113 |
| Number (no) | 236 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |