14th International Congress of Phonetic Sciences (ICPhS-14)San Francisco, CA, USA |
We describe a new model of CASA labelling which assigns to each time-frequency region a probability "clean" enough to feed a multistream recogniser only adapted to clean data. This labelling process is based on the harmonicity of the speech. The probability is evaluated according to a SNR-feature mapping and the choice of a SNR decision threshold. This allows an extension of a previous method [1] based on the binary detection of noisy time-frequency regions, followed by partial recognition of clean regions. The labelling process i s adapted to a new multistream recognition approach [2], since the previous probabilities serve to weight the streams' posteriors.
Bibliographic reference. Berthommier, Frédéric / Glotin, Hervé (1999): "A new SNR-feature mapping for robust multistream speech recognition", In ICPhS-14, 711-714.