A Combined Method for Localizing Two Overlapping Acoustic Sources Based on Deep Learning
Deep learning approaches for multi-source sound localization face significant challenges, particularly the need for extensive training datasets encompassing diverse spatial configurations to achieve robust generalization. This requirement leads to substantial computational demands, which are further...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/12/6768 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850156839938818048 |
|---|---|
| author | Alexander Lyapin Ghiath Shahoud Evgeny Agafonov |
| author_facet | Alexander Lyapin Ghiath Shahoud Evgeny Agafonov |
| author_sort | Alexander Lyapin |
| collection | DOAJ |
| description | Deep learning approaches for multi-source sound localization face significant challenges, particularly the need for extensive training datasets encompassing diverse spatial configurations to achieve robust generalization. This requirement leads to substantial computational demands, which are further exacerbated when localizing overlapping sources in complex acoustic environments with reverberation and noise. In this paper, a new methodology is proposed for simultaneous localization of two overlapping sound sources in the time–frequency domain in a closed, reverberant environment with a spatial resolution of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mn>10</mn><mo>°</mo></msup></semantics></math></inline-formula> using a small-sized microphone array. The proposed methodology is based on the integration of the sound source separation method with a single-source sound localization model. A hybrid model was proposed to separate the sound source signals received by each microphone in the array. The model was built using a bidirectional long short-term memory (BLSTM) network and trained on a dataset using the ideal binary mask (IBM) as the training target. The modeling results show that the proposed localization methodology is efficient in determining the directions for two overlapping sources simultaneously, with an average localization accuracy of 86.1% for the test dataset containing short-term signals of 500 ms duration with different signal-to-signal ratio values. |
| format | Article |
| id | doaj-art-9dfd9b100d5a47b6a0488699658c76e1 |
| institution | OA Journals |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-9dfd9b100d5a47b6a0488699658c76e12025-08-20T02:24:22ZengMDPI AGApplied Sciences2076-34172025-06-011512676810.3390/app15126768A Combined Method for Localizing Two Overlapping Acoustic Sources Based on Deep LearningAlexander Lyapin0Ghiath Shahoud1Evgeny Agafonov2Department of Computational and Information Technology, Siberian Federal University, 660041 Krasnoyarsk, RussiaDepartment of Automation Systems, Automated Control and Design, Siberian Federal University, 660041 Krasnoyarsk, RussiaDepartment of Automation Systems, Automated Control and Design, Siberian Federal University, 660041 Krasnoyarsk, RussiaDeep learning approaches for multi-source sound localization face significant challenges, particularly the need for extensive training datasets encompassing diverse spatial configurations to achieve robust generalization. This requirement leads to substantial computational demands, which are further exacerbated when localizing overlapping sources in complex acoustic environments with reverberation and noise. In this paper, a new methodology is proposed for simultaneous localization of two overlapping sound sources in the time–frequency domain in a closed, reverberant environment with a spatial resolution of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mn>10</mn><mo>°</mo></msup></semantics></math></inline-formula> using a small-sized microphone array. The proposed methodology is based on the integration of the sound source separation method with a single-source sound localization model. A hybrid model was proposed to separate the sound source signals received by each microphone in the array. The model was built using a bidirectional long short-term memory (BLSTM) network and trained on a dataset using the ideal binary mask (IBM) as the training target. The modeling results show that the proposed localization methodology is efficient in determining the directions for two overlapping sources simultaneously, with an average localization accuracy of 86.1% for the test dataset containing short-term signals of 500 ms duration with different signal-to-signal ratio values.https://www.mdpi.com/2076-3417/15/12/6768deep learningmulti-source sound localizationoverlapping sound sourcesreverberant environmentsmall-sized microphone arraysound source separation |
| spellingShingle | Alexander Lyapin Ghiath Shahoud Evgeny Agafonov A Combined Method for Localizing Two Overlapping Acoustic Sources Based on Deep Learning Applied Sciences deep learning multi-source sound localization overlapping sound sources reverberant environment small-sized microphone array sound source separation |
| title | A Combined Method for Localizing Two Overlapping Acoustic Sources Based on Deep Learning |
| title_full | A Combined Method for Localizing Two Overlapping Acoustic Sources Based on Deep Learning |
| title_fullStr | A Combined Method for Localizing Two Overlapping Acoustic Sources Based on Deep Learning |
| title_full_unstemmed | A Combined Method for Localizing Two Overlapping Acoustic Sources Based on Deep Learning |
| title_short | A Combined Method for Localizing Two Overlapping Acoustic Sources Based on Deep Learning |
| title_sort | combined method for localizing two overlapping acoustic sources based on deep learning |
| topic | deep learning multi-source sound localization overlapping sound sources reverberant environment small-sized microphone array sound source separation |
| url | https://www.mdpi.com/2076-3417/15/12/6768 |
| work_keys_str_mv | AT alexanderlyapin acombinedmethodforlocalizingtwooverlappingacousticsourcesbasedondeeplearning AT ghiathshahoud acombinedmethodforlocalizingtwooverlappingacousticsourcesbasedondeeplearning AT evgenyagafonov acombinedmethodforlocalizingtwooverlappingacousticsourcesbasedondeeplearning AT alexanderlyapin combinedmethodforlocalizingtwooverlappingacousticsourcesbasedondeeplearning AT ghiathshahoud combinedmethodforlocalizingtwooverlappingacousticsourcesbasedondeeplearning AT evgenyagafonov combinedmethodforlocalizingtwooverlappingacousticsourcesbasedondeeplearning |