Age Estimation in Short Speech Utterances Based on Bidirectional Gated-Recurrent Neural Networks

Badr, Ameer; Abdul-Hassan, Alia K.

doi:10.30684/etj.v39i1b.1905

Cited by 4 publications

(1 citation statement)

References 24 publications

(36 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Multiple acoustic aspects of a speaker's speech have been retrieved by numerous research, however, it is still unclear which acoustic elements are most appropriate for the various tasks of speaker profiling [10]. Furthermore, despite ongoing research, accurately estimating height, age, and gender with a minimal feature set using advanced machine learning techniques is still difficult [11]. This is because there are many sources of variability that overlap, including the speaker's gender, health, and emotional state, which can all affect speech as well as the design of the sound production system.…”

Section: Introductionmentioning

confidence: 99%

Ensemble Feature Selection for Age Estimation from Speech

2023

IJCCCE

View full text Add to dashboard Cite

The voice signal carries a wide range of data about the speaker, including their physical characteristics, feelings, and level of health. There are several uses for the estimate of these physical characteristics from the speech in forensics, security, surveillance, marketing, and customer service. The primary goal of this research is to identify the auditory characteristics that aid in estimating a speaker’s age. To this end, an ensemble feature selection model is proposed that selects the best features from a baseline acoustic feature vector for age estimation from speech. Using a feature vector that covers various spectral, temporal, and prosodic aspects of speech, an ensemble-based automatic feature selection is performed by, first calculating the feature importance or ranks based on individual feature selection methods, then voting is applied to the resulting feature ranks to attain the top-ranked subset by all feature selection methods. The proposed method is evaluated on the TIMIT dataset and achieved a mean absolute error (MAE) of 5.58 years and 5.12 years for male and female age estimation. Index Terms— Age Estimation, Feature Selection, Ensemble Selection, TIMIT dataset.

show abstract

Section: Introductionmentioning

confidence: 99%

Ensemble Feature Selection for Age Estimation from Speech

2023

IJCCCE

View full text Add to dashboard Cite

show abstract

Creating the Hu-Int dataset: A comprehensive Arabic speech dataset for gender detection and age estimation of Arab celebrities

Younis,

Ruhaiyem,

Badr

et al. 2024

Biomedical Signal Processing and Control

View full text Add to dashboard Cite

Improved Gender Detection and Age Estimation Using Multimodal Speech Datasets for speech Age Classification

Younis,

Raihana,

Samsudin

et al. 2023

Preprint

View full text Add to dashboard Cite

Age estimation and gender detection are essential tasks in speech analysis and understanding, with applications in various domains. Traditional approaches primarily rely on acoustic features extracted from speech signals, which may be limited by environmental noise and recording conditions. To address these challenges, we propose an improved approach that leverages multimodal speech data, combining audio, visual, and textual features for age estimation and gender detection. Our methodology includes a comprehensive analysis of multimodal features, a novel fusion strategy for integrating the features, and an evaluation of a large-scale multimodal speech dataset. Experimental results demonstrate the effectiveness and superiority of our approach compared to state-of-the-art methods in terms of accuracy, robustness, and generalization capabilities. This work contributes to the advancement of speech analysis techniques and enhances the performance of speech-based applications. This study applies four methods, Decision Trees (DT), Random Forests (RF),Neural Networks (CNN), and CNN with cross-validation.. The accuracy of DT, Random Forest, CCN and CNN with cross validation algorithms are 0.9317%, 0.8341%,0.8% and 0.8537%, respectively for male dataset, 0.8563%, 0.657%1, 0.7433% and 0.7682%, respectively for female dataset then 0.8563%, 0.6839%, 0.7241%, 0.7452%, respectively for combined dataset.

show abstract

Age Estimation in Short Speech Utterances Based on Bidirectional Gated-Recurrent Neural Networks

Cited by 4 publications

References 24 publications

Ensemble Feature Selection for Age Estimation from Speech

Ensemble Feature Selection for Age Estimation from Speech

Creating the Hu-Int dataset: A comprehensive Arabic speech dataset for gender detection and age estimation of Arab celebrities

Improved Gender Detection and Age Estimation Using Multimodal Speech Datasets for speech Age Classification

Contact Info

Product

Resources

About