Speaker Verification Using Acoustic and Prosodic Features

Abstract

In this paper we report the experiment carried out on recently collected speaker recognition database namely Arunachali Language Speech Database (ALS-DB)to make a comparative study on the performance of acoustic and prosodic features for speaker verification task.The speech database consists of speech data recorded from 200 speakers with Arunachali languages of NorthEast India as mother tongue. The collected database is evaluated using Gaussian mixture model-Universal Background Model (GMM-UBM) based speaker verification system. The acoustic feature considered in the present study is Mel-Frequency Cepstral Coefficients (MFCC) along with its derivatives.The performance of the system has been evaluated for both acoustic feature and prosodic feature individually as well as in combination.It has been observed that acoustic feature, when considered individually, provide better performance compared to prosodic features. However, if prosodic features are combined with acoustic feature, performance of the system outperforms both the systems where the features are considered individually. There is a nearly 5% improvement in recognition accuracy with respect to the system where acoustic features are considered individually and nearly 20% improvement with respect to the system where only prosodic features are considered.

A Critical Review on Automatic Speaker Recognition

“…For Vector Quantization (VQ) the LBG (Linde, Buzo and Gray) algorithm and the k-means algorithm are the most familiar algorithms. Also some other methods was proposed for speaker modeling such as neural networks (NN) and stochastic models that uses probability distribution for example Hidden Markov Model (HMM) and Gaussian Mixture Model (GMM) etc [11] [13] [16].The following methods for speaker recognition will be aimed specifically at text-independent speaker identification system. The system involves following steps:…”

“…Speaker verification systems are use to verify whether an input speech signal matches to the claimed identity where as speaker identification objective to identify an input speech by selecting one speaker model from a set of enrolled speakers models. Sometimes speaker verification will follow speaker identification in order to validate the identification results [11].…”