Integration of asynchronous knowledge sources in a novel speech recognition framework
Hugo Van hamme · Lirias · 2008
Hidden Markov Models have been essential in obtaining today’s successes in speech recognition. However, some limitations of HMMs become clear: for example it is difficult to successfully exploit features that are measured at different time scales than the centisecond scale at which the spectral features are measured. Little success has been achieved in integrating utterance level information such as prosody, segmental information and finer detail such as voice onset times. In this paper, we apply latent semantic analysis (LSA) techniques known from the text processing field to histograms of acoustic event co-occurrence (HAC) to propose a novel speech recognition framework. We show that the HACmethod can deal with correlated information and exploit knowledge sources that are asynchronous. Index Terms: speech recognition, information discovery, information integration, latent semantic analysis, cooccurrence statistics. 1.