A Dynamic Time Warp VLSI Processor for Continuous Speech Recognition, Georges M. Quénot, Jean-Luc Gauvain, Jean-Jacques Gangolf and Joseph Mariani, IEEE International Conference on Accoustics, Speech and Signal Processing, Volume 3, pages 1549-1552 Tokyo, Japan, 7-11 April 1986.

We present a VLSI processor designed to compute dynamic time warping algorithms for speech recognition with extreme rapidity. This processor works as a coprocessor in a classical system including a standard microprocessor and a digital signal processor. It uses its own local memory for reference utterances and intermediate results. It has been designed to give maximum efficiency on continuous speech recognition applications with or without syntax constraints. Its flexiblility permits software optimization and its use in a large number of different applications. We use a sequential approach for DTW computation and work along the time axis. All the calculations are carried out on each frame of the unknown utterance as soon as it arrives from the DSP and DTW computations therefore take place in real time. Response time is in hundredth of seconds; intermediate results are obtained before the end of the sentence. A system using this chip will be able to carry out continuous speech recognition in real time on a vocabulary of 300 references. Many of those chips can be used in parallel on a single system.