On Learning to Identify Genders from Raw Speech Signal Using CNNs

Abstract

Automatic Gender Recognition (AGR) is the task of identifying the gender of a speaker given a speech signal. Standard approaches extract features like fundamental frequency and cepstral features from the speech signal and train a binary classifier. Inspired from recent works in the area of automatic speech recognition (ASR), speaker recognition and presentation attack detection, we present a novel approach where relevant features and classifier are jointly learned from the raw speech signal in end-to-end manner. We propose a convolutional neural networks (CNN) based gender classifier that consists of: (1) convolution layers, which can be interpreted as a feature learning stage and (2) a multilayer perceptron (MLP), which can be interpreted as a classification stage. The system takes raw speech signal as input, and outputs gender posterior probabilities. Experimental studies conducted on two datasets, namely AVspoof and ASVspoof 2015, with different architectures show that with simple architectures the proposed approach yields better system than standard acoustic features based approach. Further analysis of the CNNs show that the CNNs learn formant and fundamental frequency information for gender identification.

Learning Voice Source Related Information for Depression Detection

“…In this paper, rather than extracting voice source related features from speech signals and then modelling them through a classifier, we develop methods to directly learn voice source related information in an end-to-end manner for depression detection. This is motivated from recent works that have shown that CNNs can learn task dependent information from raw speech signals in an end-to-end manner [20,21,22,23]. Specifically, we show that, by combining prior knowledge based signal processing and the capability of CNNs to learn task dependent information from raw signals, depression can be effectively detected from the voice source information.…”

Privacy Implications of Voice and Speech Analysis – Information Disclosure by Inference

“…Numerous attempts have been made to uncover links between speech parameters and speaker demographics [26,34,48,92]. A person's gender, for instance, can be reflected in voice onset time, articulation, and duration of vowels, which is due to various reasons, including differences in vocal fold anatomy, vocal tract dimensions, hormone levels, and sociophonetic factors [92].…”

“…It has also been shown that male and female speakers differ measurably in word use [26]. Like humans, computer algorithms can identify the sex of a speaker from a voice sample with high accuracy [48]. Precise classification results are achieved even under adverse conditions, such as loud background noise or emotional and intoxicated speech [34].…”

Improving Children Speech Recognition through Feature Learning from Raw Speech Signal

“…In [12], a spectral dictionary interpretation was proposed to understand the information modeled by the first convolution layer. This approach has been applied in other studies, such as [23] and [24], to understand the spectral information modeled by the CNNs. In this approach, the spectral response of the filters to the input speech is calculated in the following manner: 1) s c t was taken as the input speech segment.…”