Neural networks and the bias/variance dilemma
Neural Computation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Subband architecture for automatic speaker recognition
Signal Processing - Special issue on emerging techniques for communication terminals
Discrete Time Processing of Speech Signals
Discrete Time Processing of Speech Signals
Subband Approach for Automatic Speaker Recognition: Optimal Division of the Frequency Domain
AVBPA '97 Proceedings of the First International Conference on Audio- and Video-Based Biometric Person Authentication
Sub-Band Based Recognition of Noisy Speech
ICASSP '97 Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '97)-Volume 2 - Volume 2
Hi-index | 0.00 |
This paper contributes to the growing literature confirming the effectiveness of subband processing for speaker recognition. Specifically, we investigate speaker identification from noisy test speech modelled using linear prediction and hidden Markov models (HMMs). After filtering the wideband signal into subbands, the output time trajectory of each is represented by 12 pseudo-cepstral coefficients which are used to train and test individual HMMs. During recognition, the HMM outputs are combined to produce an overall score for each test utterance. We find that, for particular numbers of filters, subband processing outperforms traditional wideband techniques.