Neural Network Based Speaker Classification and Verification Systems with Enhanced Features

TL;DR

This paper introduces a neural network framework with enhanced features for speaker recognition, achieving high accuracy and low error rates through optimized features, training, and score normalization techniques.

Contribution

It presents a novel neural network-based speaker recognition system with optimized features, training methods, and normalization techniques that improve performance over previous approaches.

Findings

Achieved 100% classification rate on TIMIT dataset.

Less than 6% Equal Error Rate in speaker verification.

Enhanced features and normalization significantly improve system performance.

Abstract

This work presents a novel framework based on feed-forward neural network for text-independent speaker classification and verification, two related systems of speaker recognition. With optimized features and model training, it achieves 100% classification rate in classification and less than 6% Equal Error Rate (ERR), using merely about 1 second and 5 seconds of data respectively. Features with stricter Voice Active Detection (VAD) than the regular one for speech recognition ensure extracting stronger voiced portion for speaker recognition, speaker-level mean and variance normalization helps to eliminate the discrepancy between samples from the same speaker. Both are proven to improve the system performance. In building the neural network speaker classifier, the network structure parameters are optimized with grid search and dynamically reduced regularization parameters are used to avoid training terminated in local minimum. It enables the training goes further with lower cost. In speaker verification, performance is improved with prediction score normalization, which rewards the speaker identity indices with distinct peaks and penalizes the weak ones with high scores but more competitors, and speaker-specific thresholding, which significantly reduces ERR in the ROC curve. TIMIT corpus with 8K sampling rate is used here. First 200 male speakers are used to train and test the classification performance. The testing files of them are used as in-domain registered speakers, while data from the remaining 126 male speakers are used as out-of-domain speakers, i.e. imposters in speaker verification.