Please use this identifier to cite or link to this item:
https://www.um.edu.mt/library/oar/handle/123456789/17795
Title: | Phoneme classification in hardware implemented neural networks |
Authors: | Gatt, Edward Micallef, Joseph Micallef, Paul Chilton, Edward |
Keywords: | Neural networks (Computer science) Self-organizing maps Hidden Markov models Integrated circuits -- Very large scale integration Automatic speech recognition Analog CMOS integrated circuits |
Issue Date: | 2001 |
Publisher: | Institute of Electrical and Electronics Engineers Inc. |
Citation: | Gatt, E., Micallef, J., Micallef, P., & Chilton, E. (2001). Phoneme classification in hardware implemented neural networks. 8th IEEE International Conference on Electronics, Circuits and Systems, Malta. 481-484. |
Abstract: | Among speech researchers, it is widely believed that Hidden Markov Models (HMMs) are the most successful modelling approaches for acoustic events in speech recognition. However, common assumptions limit the classification abilities of HMMs and these can been relaxed by introducing neural networks in the HMM framework. With today's advances in VLSI technology, artificial neural networks (ANNs) can be integrated into a single chip offering adequate circuit complexity required to attain both a high recognition accuracy and an improved learning time. Analogue implementations are considered due to the high processing speeds. The relative performance of different speech coding parameters for use with two different ANN architectures that lend themselves to analogue hardware implementations are investigated. In this case, the dynamic ranges of the different coefficients need to be taken into consideration since they will affect the performance of the analogue chip due to the scaling of the coefficients to voltage signals. The hardware requirements for implementing the two architectures are then discussed. |
URI: | https://www.um.edu.mt/library/oar//handle/123456789/17795 |
Appears in Collections: | Scholarly Works - FacICTMN |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Phoneme Classification in Hardware Implemented Neural Networks.pdf Restricted Access | Phoneme classification in hardware implemented neural networks | 623.46 kB | Adobe PDF | View/Open Request a copy |
Items in OAR@UM are protected by copyright, with all rights reserved, unless otherwise indicated.