# Towards End-to-End Acoustic Localization using Deep Learning: from Audio Signal to Source Position Coordinates

arXiv: https://arxiv.org/abs/1807.11094 · HTML: https://mlsanity.com/paper/1807.11094/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jul 2018.

## Built on by (most cited first, 11 of 11)

- [A Survey of Sound Source Localization with Deep Learning Methods](https://mlsanity.com/paper/2109.03465/) (2021)
- [Extending GCC-PHAT using Shift Equivariant Neural Networks](https://mlsanity.com/paper/2208.04654/) (2022)
- [A Deep Reinforcement Learning Approach to Audio-Based Navigation in a Multi-Speaker Environment](https://mlsanity.com/paper/2105.04488/) (2021)
- [Emergency Vehicles Audio Detection and Localization in Autonomous Driving](https://mlsanity.com/paper/2109.14797/) (2021)
- [Direction of Arrival Estimation of Sound Sources Using Icosahedral CNNs](https://mlsanity.com/paper/2203.16940/) (2022)
- [Dual input neural networks for positional sound source localization](https://mlsanity.com/paper/2308.04169/) (2023)
- [A Deep Reinforcement Learning Approach for Audio-based Navigation and Audio Source Localization in Multi-speaker Environments](https://mlsanity.com/paper/2110.12778/) (2021)
- [wav2pos: Sound Source Localization using Masked Autoencoders](https://mlsanity.com/paper/2408.15771/) (2024)
- [A Review on Sound Source Localization in Robotics: Focusing on Deep Learning Methods](https://mlsanity.com/paper/2507.01143/) (2025)
- [Sound field decomposition based on two-stage neural networks](https://mlsanity.com/paper/2309.06661/) (2023)
- [SONNET: Enhancing Time Delay Estimation by Leveraging Simulated Audio](https://mlsanity.com/paper/2411.13179/) (2024)

## Abstract (arXiv)

This paper presents a novel approach for indoor acoustic source localization using microphone arrays and based on a Convolutional Neural Network (CNN). The proposed solution is, to the best of our knowledge, the first published work in which the CNN is designed to directly estimate the three dimensional position of an acoustic source, using the raw audio signal as the input information avoiding the use of hand crafted audio features. Given the limited amount of available localization data, we propose in this paper a training strategy based on two steps. We first train our network using semi-synthetic data, generated from close talk speech recordings, and where we simulate the time delays and distortion suffered in the signal that propagates from the source to the array of microphones. We then fine tune this network using a small amount of real data. Our experimental results show that this strategy is able to produce networks that significantly improve existing localization methods based on textitSRP-PHAT strategies. In addition, our experiments show that our CNN method exhibits better resistance against varying gender of the speaker and different window sizes compared with the other methods.