Speaker identification based on a modified Kohonen network

Vieira, Karane; Wilamowski, Bogdan M.; Kubichek, Robert F.

doi:10.1109/icnn.1997.614229

Cited by 4 publications

(3 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The neural network architecture, as shown in Fig. 16, has 15 inputs, and number of hidden neurons is equal to number of authorized spcxch patterns. The output neuron performs the OR operation.…”

Section: Neural Network Architecturementioning

confidence: 99%

“…In a previous paper [15], we presented a robust speaker identification system based on a modified Kohonen algorithm. This algorithm has several advantages for classification tasks, including better performance and reduced training time.…”

mentioning

confidence: 99%

“…The basic techniques used in [15] for training the were implemented in this system, however, the following improvements were introduced:…”

mentioning

confidence: 99%

See 2 more Smart Citations

Speaker verification for security systems using artificial neural networks

Vieira

Wilamowski²,

Kubichek³

Proceedings of the IECON'97 23rd International Conference on Industrial Electronics, Control, and Instrumentation (Cat. No.97CH

Self Cite

View full text Add to dashboard Cite

h a m i e , W Y 82071 I Abstruct --This paper investigates automatic speaker recognition systems, which can be used for security purposes. The speech signal is compressed using linear prediction analysis and recognized by neural networks. This neural network technique is presented for the task of speech recognition and speaker verification. This technique first uses pattern recognition to identify the speech, then it is used to distinguish each user from all other speakers (impostors). With this method, unknown speech can be accurately classified as user or impostor speech. The approach used is based on the following steps: extraction of spectral features; training of an initial neural network to identify the speech; extraction of LPCreflection coefficients for each user, training of a secondary neural-network to identify the user; and classification of unknown speech as either user or impostor.

show abstract

Section: Neural Network Architecturementioning

confidence: 99%

mentioning

confidence: 99%