Title :
Hybrid HMM-NN architectures for connected digit recognition
Author_Institution :
Ist. di Fonetica e Dialettologia, CNR, Padova, Italy
Abstract :
This paper deals with the more recent results obtained by the application of the CSLU Toolkit frame-based hybrid HMM/ANN architecture on the connected digit recognition task for the Italian language. The hybrid architecture for speaker independent recognition is described and the last obtained results are introduced in detail
Keywords :
hidden Markov models; neural net architecture; speech recognition; CSLU Toolkit frame-based hybrid HMM/ANN architecture; Italian language; connected digit recognition; speaker independent recognition; Computer architecture; Electronic mail; Hidden Markov models; Loudspeakers; Materials testing; Neural networks; Speech synthesis; Telephony; Vocabulary; World Wide Web;
Conference_Titel :
Neural Networks, 2000. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on
Conference_Location :
Como
Print_ISBN :
0-7695-0619-4
DOI :
10.1109/IJCNN.2000.861439
