Please use this identifier to cite or link to this item:
|Title:||A 1000-word vocabulary, speaker-independent, continuous live-mode speech recognizer implemented in a single FPGA||Authors:||Lin E.C.
In silico vox
|Issue Date:||2007||Citation:||Lin E.C., Yu K., Rutenbar R.A., Chen T. (2007). A 1000-word vocabulary, speaker-independent, continuous live-mode speech recognizer implemented in a single FPGA. ACM/SIGDA International Symposium on Field Programmable Gate Arrays - FPGA : 60-68. ScholarBank@NUS Repository. https://doi.org/10.1145/1216919.1216928||Abstract:||The Carnegie Mellon In Silico Vox project seeks to move best-quality speech recognition technology from its current software-only form into a range of efficient all-hardware implementations. The central thesis is that, like graphics chips, the application is simply too performance hungry, and too power sensitive, to stay as a large software application. As a first step in this direction, we describe the design and implementation of a fully functional speech-to-text recognizer on a single Xilinx XUP platform. The design recognizes a 1000 word vocabulary, is speaker-independent, recognizes continuous (connected) speech, and is a "live mode" engine, wherein recognition can start as soon as speech input appears. To the best of our knowledge, this is the most complex recognizer architecture ever fully committed to a hardware-only form. The implementation is extraordinarily small, and achieves the same accuracy as state-of-the-art software recognizers, while running at a fraction of the clock speed. Copyright 2007 ACM.||Source Title:||ACM/SIGDA International Symposium on Field Programmable Gate Arrays - FPGA||URI:||http://scholarbank.nus.edu.sg/handle/10635/146269||ISBN:||1595936009
|Appears in Collections:||Staff Publications|
Show full item record
Files in This Item:
There are no files associated with this item.
checked on Oct 12, 2021
checked on Oct 14, 2021
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.