A New Text-Independent Speaker Identification Using Vector Quantization and Multi-layer Perceptron
In this paper, we propose a new text-independent speaker identification method using VQ and MLP. It consists of three parts: a new spectral peak analysis based feature extraction, speaker clustering and model selection using VQ, and MLP based speaker identification. The feature vector reflects the speaker specific characteristics and has a long-term feature for which makes it text-independent. The proposed method has a computational efficient for feature extraction and identification. To evaluate the proposed method, we calculated the correct identification ratio (CIR), the average CIR of the proposed and GMM method was 92.27% and 85.78% for 5 seconds segments in 15-speaker identification. Experimental results, we have achieved a performance comparable to GMM-method.
KeywordsGaussian Mixture Model Spectral Peak Vector Quantization Speaker Recognition Speaker Identification
Unable to display preview. Download preview PDF.
- Herbert, G., Michael, S.: Text-independent Speaker Identification. IEEE Signal Processing Magazine, 18–32 (1994)Google Scholar
- Narayanaswamy, B., Gangadharaiah, R.: Extracting Additional Information from Gaussian Mixture Model Probabilities for Improved Text-Independent Speaker Identification. In: IEEE International Conference on Acoustics Speech and Signal Processing, vol. 1, pp. 621–624 (2005)Google Scholar
- Hiroaki, H.: Text-Independent Speaker Recognition using Neural Networks. IEICE Trans. INF. & SYST. E76-D(3), 345–351 (1993)Google Scholar
- Keum, J.S., Lee, H.S.: Speaker Change Detection Based on Spectral Peak Track Analysis for Korean Broadcast News. In: The Fifth International Conference on Information Communications and Signal Processing, pp. 724–728 (2005)Google Scholar
- Mohamed, Q.: Vector Quantization, http://www.geocities.com/mohamedqasem/vectorquantization/vq.html