Speech recognition on an FPA using discrete and continuous hidden Markov models

被引：0

作者：

Melnikoff, SJ ^{[1
]}

Quigley, SF ^{[1
]}

Russell, MJ ^{[1
]}

机构：

[1] Univ Birmingham, Birmingham B15 2TT, W Midlands, England

来源：

FIELD-PROGRAMMABLE LOGIC AND APPLICATIONS, PROCEEDINGS: RECONFIGURABLE COMPUTING IS GOING MAINSTREAM | 2002年 / 2438卷

关键词：

D O I：

暂无

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

Speech recognition is a computationally demanding task, particularly the stage which uses Viterbi decoding for converting pre-processed speech data into words or sub-word units. Any device that can reduce the load on, for example, a PC's processor, is advantageous. Hence we present FPGA implementations of the decoder based alternately on discrete and continuous hidden Markov models (HMMs) representing monophones, and demonstrate that the discrete version can process speech nearly 5,000 times real time, using just 12% of the slices of a Xilinx Virtex XCV1000, but with a lower recognition rate than the continuous implementation, which, is 75 times faster than real time, and occupies 45% of the same device.

引用

页码：202 / 211

页数：10

共 11 条

[1] A single chip phoneme based HMM speech recognition system for consumer applications [J].

Burchard, B ;

Römer, R ;

Fox, O .

IEEE TRANSACTIONS ON CONSUMER ELECTRONICS, 2000, 46 (03) :914-919

[2] How may I help you? [J].

Gorin, AL ;

Riccardi, G ;

Wright, JH .

SPEECH COMMUNICATION, 1997, 23 (1-2) :113-127

[3]

HOLME JN, 2001, SPEECH SYNTHESIS REC

[4]

Melnikoff S. J., 2000, Field-Programmable Logic and Applications. Roadmap to Reconfigurable Computing. 10th International Conference, FPL 2000. Proceedings (Lecture Notes in Computer Science Vol.1896), P495

[5]

MELNIKOFF SJ, 2001, LNCS, V2147, P81

[6]

Nakamura K, 2001, PROCEEDINGS OF THE ASP-DAC 2001: ASIA AND SOUTH PACIFIC DESIGN AUTOMATION CONFERENCE 2001, P396, DOI 10.1109/ASPDAC.2001.913339

[7] A TUTORIAL ON HIDDEN MARKOV-MODELS AND SELECTED APPLICATIONS IN SPEECH RECOGNITION [J].

RABINER, LR .

PROCEEDINGS OF THE IEEE, 1989, 77 (02) :257-286

[8] Single-chip speech recognition system based on 8051 microcontroller core [J].

Shi, YY ;

Liu, J ;

Liu, RS .

IEEE TRANSACTIONS ON CONSUMER ELECTRONICS, 2001, 47 (01) :149-153

[9] Speech interface VLSI for car applications [J].

Shozakai, M .

ICASSP '99: 1999 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, PROCEEDINGS VOLS I-VI, 1999, :141-144

[10] A configurable logic based architecture for real-time continuous speech recognition using hidden Markov models [J].

Stogiannos, P ;

Dollas, A ;

Digalakis, V .

JOURNAL OF VLSI SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY, 2000, 24 (2-3) :223-240

← 1 2 →