# TIMIT Speaker Profiling: A Comparison of Multi-task learning and Single-task learning Approaches

arXiv: https://arxiv.org/abs/2404.12077 · HTML: https://mlsanity.com/paper/2404.12077/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 10 references that are in the map.
- First posted on arXiv 18 Apr 2024.

## Builds on (most cited first, 5 of 5)

- [A Survey on Multi-Task Learning](https://mlsanity.com/paper/1707.08114/) (2017)
- [Convolutional Neural Networks and Language Embeddings for End-to-End Dialect Recognition](https://mlsanity.com/paper/1803.04567/) (2018)
- [Joint gender and age estimation based on speech signals using x-vectors and transfer learning](https://mlsanity.com/paper/2012.01551/) (2020)
- [Accent Recognition with Hybrid Phonetic Features](https://mlsanity.com/paper/2105.01920/) (2021)
- [Multi-task Recurrent Model for Speech and Speaker Recognition](https://mlsanity.com/paper/1603.09643/) (2016)

## Built on by (most cited first, 1 of 1)

- [Tessellated Linear Model for Age Prediction from Voice](https://mlsanity.com/paper/2501.09229/) (2025)

## Abstract (arXiv)

This study employs deep learning techniques to explore four speaker profiling tasks on the TIMIT dataset, namely gender classification, accent classification, age estimation, and speaker identification, highlighting the potential and challenges of multi-task learning versus single-task models. The motivation for this research is twofold: firstly, to empirically assess the advantages and drawbacks of multi-task learning over single-task models in the context of speaker profiling; secondly, to emphasize the undiminished significance of skillful feature engineering for speaker recognition tasks. The findings reveal challenges in accent classification, and multi-task learning is found advantageous for tasks of similar complexity. Non-sequential features are favored for speaker recognition, but sequential ones can serve as starting points for complex models. The study underscores the necessity of meticulous experimentation and parameter tuning for deep learning models.