Sixth International Conference on Spoken Language Processing
The use of heterogeneous features in automatic speech recognition has been shown to increase clean speech performance. This paper focuses on the noise robustness of systems with heterogeneous features. In particular a system where different features are extracted for different sets of phonemes. The employed features are computed by applying a linear transformation, estimated in a data-driven fashion, to standard feature processing methods. The transformed features are tested in a set of experiments employing different system configurations. Overall the experiments suggests that employing more phoneme specific features can improve speech recognition. When testing the system on noisy speech with added car or factory noise, this tendency is maintained.
Bibliographic reference. Christensen, Heidi / Lindberg, Borge / Andersen, Ove (2000): "Noise robustness of heterogeneous features employing minimum classification error feature space transformations", In ICSLP-2000, vol.3, 534-537.