Speech-based Age and Gender Prediction with Transformers

2023/06/29 by Burkhardt, Felix, Wagner, Johannes, Wierstorf, Hagen +2 · 6 citations
#Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Sound (cs.SD) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2306.16962

Abstract

We report on the curation of several publicly available datasets for age and gender prediction. Furthermore, we present experiments to predict age and gender with models based on a pre-trained wav2vec 2.0. Depending on the dataset, we achieve an MAE between 7.1 years and 10.8 years for age, and at least 91.1% ACC for gender (female, male, child). Compared to a modelling approach built on handcrafted features, our proposed system shows an improvement of 9% UAR for age and 4% UAR for gender. To make our findings reproducible, we release the best performing model to the community as well as the sample lists of the data splits.

Cited by

• Spoken DialogSum: An Emotion-Rich Conversational Dataset for Spoken Dialogue Summarization
• NaturalVoices: A Large-Scale, Spontaneous and Emotional Podcast Dataset for Voice Conversion
• VoiceBBQ: Investigating Effect of Content and Acoustics in Social Bias of Spoken Language Model
• Reference-free Adversarial Sex Obfuscation in Speech
• MECAT: A Multi-Experts Constructed Benchmark for Fine-Grained Audio Understanding Tasks
• The Man Behind the Sound: Demystifying Audio Private Attribute Profiling via Multimodal Large Language Model Agents

Related

• Joint gender and age estimation based on speech signals using x-vectors and transfer learning
• SEGAA: A Unified Approach to Predicting Age, Gender, and Emotion in Speech
• Automated Sex Classification of Children's Voices and Changes in Differentiating Factors with Age
• VoxCeleb Enrichment for Age and Gender Recognition
• Estimation of speaker age and height from speech signal using bi-encoder transformer mixture model