Highly parallel architectures and algorithms for speech analysis
- 24 March 2005
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 9, 331-334
- https://doi.org/10.1109/icassp.1984.1172513
Abstract
Highly parallel computer architectures and algorithms for speech analysis operations are surveyed. The classes of architectures considered include SIMD, skewed-SIMD, MIMD, and data flow machines, associative processors, and pipelined systolic and wavefront arrays. Parallel algorithms for digital filtering, FFTs, and linear predictive coding are summarized. System requirements are analyzed in terms of number and complexity of processors, memory requirements, and nature and complexity of inter-processor communications.Keywords
This publication has 29 references indexed in Scilit:
- A parallel processor for real-time speech signal processingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- A VLSI architecture for digital filters using complex number-theoretic transformsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Parallel processing for computationally intensive speech analysis operationsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Why systolic architectures?Computer, 1982
- Highly concurrent computing structures for matrix arithmetic and signal processingComputer, 1982
- The Multistage Cube: A Versatile Interconnection NetworkComputer, 1981
- The cube-connected cycles: a versatile network for parallel computationCommunications of the ACM, 1981
- A Model of SIMD Machines and a Comparison of Various Interconnection NetworksIEEE Transactions on Computers, 1979
- The Indirect Binary n-Cube Microprocessor ArrayIEEE Transactions on Computers, 1977
- An Adaptation of the Fast Fourier Transform for Parallel ProcessingJournal of the ACM, 1968