Acoustic Modeling in the Philips Hub - 4 Continuous - Speech Recognition

In this paper we describe some characteristics of the acoustic modeling used in the Philips continuous-speech recognition system for the DARPA Hub-4 1997 evaluation, which are related to robustness issues. We aimed at a conceptually simple system: We trained two model sets on 70 hours of the Hub-4 training data, one for within-word and one for crossword decoding. These model sets were used for both genders and all environmental conditions. In order to be able to do so, channel normalization (mean, variance normalization) and speaker normalization (vocal tract length normalization, realized by an appropriate shift of the center frequencies of the mel lter bank) have been applied, as well as adaptation techniques. MLLR-based unsupervised batch adaptation on clusters of segments was conducted both after a rst within-word decoding and a crossword decoding pass. The training strategy and the eeects of the various normalization and adaptation techniques will be discussed in the paper.