Multi-Speaker Localization Using Convolutional Neural Network Trained with Noise
Not on the map. Why?
Abstract (arXiv)
The problem of multi-speaker localization is formulated as a multi-class multi-label classification problem, which is solved using a convolutional neural network (CNN) based source localization method. Utilizing the common assumption of disjoint speaker activities, we propose a novel method to train the CNN using synthesized noise signals. The proposed localization method is evaluated for two speakers and compared to a well-known steered response power method.
Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Dec 2017.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 3; 2022: 0; 2023: 1.
4 papers.
- 2021A Survey of Sound Source Localization with Deep Learning Methodscited by 45
- 2021A Deep Reinforcement Learning Approach to Audio-Based Navigation in a Multi-Speaker Environmentcited by 6
- 2021A Deep Reinforcement Learning Approach for Audio-based Navigation and Audio Source Localization in Multi-speaker Environmentscited by 1
- 2023LOCUS: LOcalization with Channel Uncertainty and Sporadic Energycited by 1
- 2023LOCUS: LOcalization with Channel Uncertainty and Sporadic Energy18 Feb 2023
- 2021A Deep Reinforcement Learning Approach for Audio-based Navigation and Audio Source Localization in Multi-speaker Environments25 Oct 2021
- 2021A Survey of Sound Source Localization with Deep Learning Methods8 Sep 2021
- 2021A Deep Reinforcement Learning Approach to Audio-Based Navigation in a Multi-Speaker Environment10 May 2021