Speaker Identification from emotional and noisy speech data using learned voice segregation and Speech VGG

TL;DR

This paper introduces a novel speaker identification method that effectively segregates speech signals from emotional and noisy environments using a pre-trained DNN mask and Speech VGG, achieving high accuracy across multiple datasets.

Contribution

It presents a new approach combining a pre-trained DNN mask with Speech VGG for robust speaker identification in adverse conditions, outperforming recent methods.

Findings

Achieved over 85% accuracy on multiple emotional and noisy speech datasets.

Outperformed recent literature in speaker identification under challenging conditions.

Effective in both English and Arabic speech data.

Abstract

Speech signals are subjected to more acoustic interference and emotional factors than other signals. Noisy emotion-riddled speech data is a challenge for real-time speech processing applications. It is essential to find an effective way to segregate the dominant signal from other external influences. An ideal system should have the capacity to accurately recognize required auditory events from a complex scene taken in an unfavorable situation. This paper proposes a novel approach to speaker identification in unfavorable conditions such as emotion and interference using a pre-trained Deep Neural Network mask and speech VGG. The proposed model obtained superior performance over the recent literature in English and Arabic emotional speech data and reported an average speaker identification rate of 85.2\%, 87.0\%, and 86.6\% using the Ryerson audio-visual dataset (RAVDESS), speech under simulated and actual stress (SUSAS) dataset and Emirati-accented Speech dataset (ESD) respectively.