Sixth International Conference on Spoken Language Processing
The development of a speaker independent connected ”°digits”± recognizer for Italian is described. The CSLU Speech Toolkit was used to develop and implement the system which is based on an hybrid ANN/HMM architecture. The recognizer is trained on contextdependent categories to account for coarticulatory variation. Various front-end processing was compared and, when the best features (MFCC with CMS + Δ) were considered, there was a 98.68% word recognition accuracy (90.76% sentence recognition accuracy) on a test set of the FIELD continuous digits recognition task.
Bibliographic reference. Cosi, Piero / Hosom, John-Paul / Tesser, Fabio (2000): "High performance Italian continuous "digit" recognition", In ICSLP-2000, vol.4, 242-245.