EUROSPEECH 2001 Scandinavia
7th European Conference on Speech Communication and Technology
2nd INTERSPEECH Event

Aalborg, Denmark
September 3-7, 2001

                 

Introducing Phonetically Motivated Information into ASR

Heidi Christensenyz, BÝrge Lindbergy, Ove Anderseny

Aalborg University, Denmark

In this paper we present an approach to introducing more phonetically motivated information into automatic speech recognition in the form of a phonetic `expert'. To avoid the curse of dimensionality problem, the expert information is introduced at the level of the acoustic model. Two types of experts are used each providing discriminative information regarding groups of phonetically related phonemes. The phonetic expert is implemented using an MLP. A numbers recognition task shows that, when using the expert in conjunction with both a fullband and a multiband system speech recognition performances are increased.

Full Paper

Bibliographic reference.  Christensenyz, Heidi / Lindbergy, BÝrge / Anderseny, Ove (2001): "Introducing phonetically motivated information into ASR", In EUROSPEECH-2001, 2289-2292.