Parallel Viterbi search algorithm for speech recognition

The Viterbi search is an important, but computationally expensive, algorithm for speech recognition. Even with the substantial advances expected in processor technology , the massive computational resources required will remain prohibitive for operation of a speech recognition system in real time. This problem motivates the development of a parallel Viterbi search algorithm. A software implementation of a Viterbi search algorithm was written for NuMesh, a network of programmable communications routers supporting a set of digital signal processors with local memory. Communication between the processors occurs in the logical pattern of a binary tree, embedded in the physical topology of a two-dimensional Cartesian mesh. Despite the limited architecture of the routers, eecient merging and broadcasting of data were achieved by simple protocols for pipelined communication. Experimental results were collected in evaluation of an analytical model, which projects excellent scaling of performance with the number of processors.