Speaker Recognition under Stress Conditions

Abstract

Speaker Recognition systems exhibit a decrease in performance when the input speech is not in optimal circumstances, for example when the user is under emotional or stress conditions. The objective of this paper is measuring the effects of stress on speech to ultimately try to mitigate its consequences on a speaker recognition task. On this paper, we develop a stress-robust speaker identification system using data selection and augmentation by means of the manipulation of the original speech utterances. An extensive experimentation has been carried out for assessing the effectiveness of the proposed techniques. First, we concluded that the best performance is always obtained when naturally stressed samples are included in the training set, and second, when these are not available, their substitution and augmentation with synthetically generated stress-like samples, improves the performance of the system.

Data Augmentation for Speaker Identification under Stress Conditions to Combat Gender-Based Violence

“…The audio recorded is then stored in an only-read Cloud with several encrypting processes and accessibility restrictions. Regarding speech, there are two main tasks to be performed within Bindi, Stress Detection [7] and Speaker Identification [1]. The former focuses in the detection of stress in the victim's voice whereas the latter relies on the proper identification of the victim despite the emotional conditions that may be present in her voice.…”

“…We aim at finding techniques to improve speaker identification systems when facing stressed speech, either by neutralizing the effects of stress or by training the system to cope with it. We propose data augmentation techniques both statistical and using synthetically generated speech under stressed conditions together with an analysis of the best feature extraction methods to design a stress-robust system [1].…”

End-to-end recurrent denoising autoencoder embeddings for speaker identification

“…In our previous works ( [19], [20]) we explored data augmentation techniques where we created synthetic stressed speech by modifying its pitch and speed. This increased the robustness of the SR system to the distortions caused by the stressed speech signals, achieving a 20% of relative improvement in accuracy.…”