A brand-new floating-point digital speech signal processor (DSSP) VLSI, intended for a wide range of applications in speech processing, has been developed. For speech applications, a wide-dynamic-range vector operation that includes FFT and complex arithmetic is necessary in executing a highly-complicated coding algorithm that treats a large amount of windowed data collectively. It is shown at length how the floating-point data format and hardware architecture meet this requirement. The DSSP, which is fabricated using 2. 5 mu m CMOS technology, completes almost all the floating-point operations within a 150-ns machine-cycle.
|Number of pages
|ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
|Published - 1985
ASJC Scopus subject areas
- Signal Processing
- Electrical and Electronic Engineering