Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2402.03867 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929235180912640 |
|---|---|
| author | Geva, Gil Warusfel, Olivier Dubnov, Shlomo Dubnov, Tammuz Amedi, Amir Hel-Or, Yacov |
| author_facet | Geva, Gil Warusfel, Olivier Dubnov, Shlomo Dubnov, Tammuz Amedi, Amir Hel-Or, Yacov |
| contents | This paper introduces a new approach to sound source localization using head-related transfer function (HRTF) characteristics, which enable precise full-sphere localization from raw data. While previous research focused primarily on using extensive microphone arrays in the frontal plane, this arrangement often encountered limitations in accuracy and robustness when dealing with smaller microphone arrays. Our model proposes using both time and frequency domain for sound source localization while utilizing Deep Learning (DL) approach. The performance of our proposed model, surpasses the current state-of-the-art results. Specifically, it boasts an average angular error of $0.24 degrees and an average Euclidean distance of 0.01 meters, while the known state-of-the-art gives average angular error of 19.07 degrees and average Euclidean distance of 1.08 meters. This level of accuracy is of paramount importance for a wide range of applications, including robotics, virtual reality, and aiding individuals with cochlear implants (CI). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_03867 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Binaural sound source localization using a hybrid time and frequency domain model Geva, Gil Warusfel, Olivier Dubnov, Shlomo Dubnov, Tammuz Amedi, Amir Hel-Or, Yacov Sound Audio and Speech Processing This paper introduces a new approach to sound source localization using head-related transfer function (HRTF) characteristics, which enable precise full-sphere localization from raw data. While previous research focused primarily on using extensive microphone arrays in the frontal plane, this arrangement often encountered limitations in accuracy and robustness when dealing with smaller microphone arrays. Our model proposes using both time and frequency domain for sound source localization while utilizing Deep Learning (DL) approach. The performance of our proposed model, surpasses the current state-of-the-art results. Specifically, it boasts an average angular error of $0.24 degrees and an average Euclidean distance of 0.01 meters, while the known state-of-the-art gives average angular error of 19.07 degrees and average Euclidean distance of 1.08 meters. This level of accuracy is of paramount importance for a wide range of applications, including robotics, virtual reality, and aiding individuals with cochlear implants (CI). |
| title | Binaural sound source localization using a hybrid time and frequency domain model |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2402.03867 |