Language, Dialect, and Speaker Recognition Using Gaussian Mixture Models on the Cell Processor.

摘要

Automatic recognition systems are commonly used in speech processing to classify observed utterances by the speaker's identity, dialect, and language. these problems often require high processing throughput, especially in applications involving multiple concurrent incoming speech streams, such as in datacenter-level processing. This paper addresses the implementation of the language, dialect, and speacker recognition on the Cell architecture.