The DSP32C: AT&amp;Ts second generation floating point digital signal processor

Fuccio, M.L.; Gadenz, R.; Garen, C.J.; Huser, J.M.; Ng, Benjamin K.; Pekarich, S.P.; Ulery, K.D.

doi:10.1109/40.16779

Cited by 20 publications

(4 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The DSP32C from AT&T [14] is an improved version of its predecessor the DSP32. It can perform either 24 bit integer operations or 32 bit floating point operations at a rate of 25 million per second.…”

Section: C) Third Generation Dspsmentioning

confidence: 99%

Digital Signal Processors

2008

Applied Signal Processing

View full text Add to dashboard Cite

show abstract

Section: C) Third Generation Dspsmentioning

confidence: 99%

Digital Signal Processors

2008

Applied Signal Processing

View full text Add to dashboard Cite

show abstract

“…AT&T is a leaderin DSPS, with powerful floating-point signal processors such as the WE® DSP-32C and fast, cost-effective fixed-point processors likethe WEDSP-16. 5 These fast, flexible DSP chips enable advanced research algorithms to be implemented on real-time, cost-effective hardware for integration intocommercial applications.…”

Section: Introductionmentioning

confidence: 99%

Speech Recognition: From the Laboratory to the Real World

Wilpon

Mikkilineni

Roe

et al. 1990

At&T Technical Journal

View full text Add to dashboard Cite

The art and science ofspeech recognition research have advanced to the point where it is now possible to communicate reliably with a machine via telephone to carry outsimple tasks. However, the creation ofrobust algorithms is only partofthe overall process ofmaking speech recognition technology a commercial reality. In this paper, we present a brief overview ofspeech recognition technology and discuss the implementation ofthe algorithms with digital signal processing chips. In addition, we will show how theory and practice come together in real-world conditions bydescribing a telephone network trial ofautomatic credit card verification using speech recognition technology.

show abstract

“…With a 160 ns cycle time, a total system performance of 50 Mflops/s is achieved. A change from the DSP32 to its successor, the DSP32C [6], can easily be done, which would increase the system throughput to about 100 Mflops/s.…”

Section: Analog Interfacementioning

confidence: 99%

Multi signal processor systems for acoustical echo control

Fleischmann

Frenzel

Hatty

et al.

IEEE International Symposium on Circuits and Systems

View full text Add to dashboard Cite

Two multi digital signal processor systems for high speed signal processing are presented. Both systems can be configured with a variable number of processor units. Thus, there is sufficient computational power for real-time implementations of high order adaptive filter algorithms as required for echo cancellation, e.g., in hands-free telephone equipment. One system is based on the DSP32 floating-point DSP from AT&T. Monitoring and debugging is done with a standard PC system. The second system uses Fujitsu's MB8764 fixed-point DSP. It is controlled by an '80186 AMs-M-Bus' microcomputer board. The architectures are designed to support efficient parallel implementations of high order adaptive algorithms and of multirate systems for echo compensation in frequency subbands (i.e., block processing).

show abstract

The DSP32C: AT&Ts second generation floating point digital signal processor

Cited by 20 publications

References 7 publications

Digital Signal Processors

Digital Signal Processors

Speech Recognition: From the Laboratory to the Real World

Multi signal processor systems for acoustical echo control

Contact Info

Product

Resources

About