This paper presents a new method to generate a codebook that best represents the mapping between articulatory and acoustic domains. Existing codebook generation methods are relatively inefficient because of the non-linearities between the two domains. In our method the articulatory space is considered as composed of several hypercubes where the mapping is linear. The advantages of such a representation are the lower number of vectors which compose the codebook and the hierarchical organization of the codebook in a manner that respects the structure of the two domains.
Cite as: Laprie, S.O.A.Y. (1999) Design of hypercube codebooks for the acoustic-to-articulatory inversion respecting the non-linearities of the articulatory-to-acoustic mapping. Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999), 141-144, doi: 10.21437/Eurospeech.1999-39
@inproceedings{laprie99_eurospeech,
author={Slim Ouni And Yves Laprie},
title={{Design of hypercube codebooks for the acoustic-to-articulatory inversion respecting the non-linearities of the articulatory-to-acoustic mapping}},
year=1999,
booktitle={Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999)},
pages={141--144},
doi={10.21437/Eurospeech.1999-39}
}