Skip to Main Content
A hybrid approach to speaker-dependent isolated word recognition is discussed. The approach merges speaker-specific information obtained from a single training utterance with multisection vector quantization codebooks that were designed for speaker-independent recognition. The approach provides easily trained, computationally efficient, and accurate isolated word recognition. On the digits, the approach achieved an error rate less than 1 percent.
Acoustics, Speech and Signal Processing, IEEE Transactions on (Volume:33 , Issue: 2 )
Date of Publication: Apr 1985