(PDF) A binaural sound source localization method using auditive cues ...
This paper addresses the localization problem in a robotic humanoid context, providing a novel learning algorithm that uses binaural cues to determine the sound source's position.
Most of these methods achieved an important level of accurecy in predicting one sound source from binaural signal. A greater challenge is to carry out accurate multisource localization by using only binaural information.
(PDF) A binaural sound source localization method using auditive cues ...
A fundamental task for a robotic audition system is sound source localization . This paper addresses the localization problem in a robotic humanoid context, providing a novel learning algorithm that uses binaural cues to determine the sound source's position. Sound signals are extracted from a humanoid robot's ears. Binaural cues are then computed to provide inputs for a neural network. The ...
The thesis is about applying a novel combination of two advanced machine learning methods to detect the person location according its spatial coordinates. Spiking neural network has been applied ...
PDF Binaural Sound Source Localization Using a Hybrid Time and Frequency ...
Our research attempt to integrate DL techniques into sound localization utilizing a two-microphone setup and using the HRTF. This work proposes a model capable of accurately learning sound source localization from binaural recordings, especially for limited microphones or wearable devices such as hearing aids and CIs.
In this paper, we propose a deep learning method for pixel-level sound source localization by leveraging both binaural recordings and the corresponding videos. Specif-ically, we design a novel Binaural Audio-Visual Network (BAVNet), which concurrently extracts and integrates fea-tures from binaural recordings and videos.
PDF Brain
This is the first work that tries to apply LSM on sound source localization tasks. BSSL-LSM can receive binaural signals as input and automatically extract binaural acoustic cues to do angle classification without manual intervention.
BINAURAL sound source localization (SSL) is to deter-mine the spatial direction of a sound source , utilizing the audio recorded by two microphones mounted in the left and right ears. It has wide applications in speech enhancement, speech segregation, hearing aids, human-robot interaction (HRI) and intelligent video conferencing, etc [1]-[4]. Recently, with the advances in array signal ...
PDF Towards all
I. INTRODUCTION Humans localize sound by learning to map sound source locations to features embedded into the two ear input signals. A machine able to localize sound from binaural audio has important applications including robotics, sound scene analy-sis, as well as psychoacoustics and binaural audio evaluation.
This study presents a systematic evaluation of time-frequency feature design for binaural sound source localization (SSL), focus-ing on how feature selection influences model performance across diverse conditions.