Audio Processing Apparatus and Method for Localizing an Audio Source

Simple SummaryContent extracted from patent full text and abstract with AI.

This invention relates to an audio processing apparatus and method that improves the localization of audio sources, such as detecting the direction from which a sound is coming. The system uses multiple audio sensors (like microphones) and combines results from two different localization schemes—one prone to ambiguities and another that is more robust—to more accurately and efficiently determine the true direction of an audio source. The approach resolves common issues such as front-back ambiguity, especially in complex environments with multiple sound sources.

Use CasesContent extracted from patent full text and abstract with AI.

• Smartphones and smart speakers for accurately detecting where voices or sounds are coming from, improving voice command recognition.
• Conference call systems for separating multiple speakers in a room and improving clarity.
• Surveillance systems that need to identify the location of noises or incidents in complex environments.
• Hearing aids or assistive listening devices to help users focus on specific sound sources in noisy environments.
• Robotic systems or autonomous vehicles for audio-based navigation and obstacle detection.

BenefitsContent extracted from patent full text and abstract with AI.

• Improved accuracy in locating audio sources, even in noisy or reverberant environments.
• Efficient resolution of front-back ambiguity, reducing the number of false detections (ghost sources).
• Compatibility with conventional blind source separation systems, facilitating integration in existing audio technologies.
• Reduced computational complexity compared to exhaustive search or traditional data-association methods.
• Ability to separate multiple sound sources and retain information during periods when some sources are silent (e.g., during speech pauses).
• Flexible implementation in hardware or software, including on mobile devices or embedded systems.

Technical Classifications (CPCs)

Inventors & Applicants

Patent Abstract

Audio processing apparatus and method for localizing an audio source The invention relates to an audio processing apparatus (400) for localizing an audio source. The audio processing apparatus (400) comprises a plurality of audio sensors (402i), including a primary audio sensor and at least two secondary audio sensors, configured to detect an audio signal from a target audio source, wherein the primary audio sensor defines at least two pairs of audio sensors with the at least two secondary audio sensors; and a processing circuitry. The processing circuitry is configured to: determine for each pair of audio sensors a first set of likelihoods of spatial directions of the target audio source using a first localization scheme; determine a second set of likelihoods of spatial directions of the target audio source using a second localization scheme; and determine a third set of likelihoods of spatial directions of the target audio source on the basis of the first sets of likelihoods and the second set of likelihoods. Moreover, the invention relates to a corresponding audio processing method.