Apparatus and Method for Source Separation Using an Estimation and Control of Sound Quality

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

This invention provides an apparatus and method for separating a target audio signal (like speech or music) from a mixed audio input (which may contain noise, background sounds, or other unwanted signals) by estimating and controlling the resulting sound quality during the separation. The system uses computational models and possibly artificial neural networks to estimate the sound quality of the extracted signal and automatically adjusts its separation parameters to maintain user-defined (or application-defined) sound quality, balancing the trade-off between removing interference and preserving natural audio quality.

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

• Improving speech clarity in television, radio, or movie audio by enhancing dialogue over background sounds.
• Hearing aids and assistive listening devices, where it is desirable to enhance speech while maintaining comfortable sound quality.
• Voice assistant devices or smart speakers to separate user commands from background noise.
• Conference calling systems or telecommunication devices to enhance speech while reducing background noise, ensuring intelligibility and minimizing artifacts.
• Recording studios for music or post-production to separate instruments or vocals from mixed audio recordings.
• Security, surveillance, or forensic applications to enhance target sounds from noisy environments.

BenefitsContent extracted from patent full text and abstract with AI.

• Adaptive control of sound quality allows the system to maintain a minimum quality threshold, reducing unwanted artifacts and listener fatigue.
• Balances the trade-off between separation (noise/interference removal) and audio fidelity in a flexible, user- or scenario-specific manner.
• Machine-learning models can tailor separation to specific environments or types of audio content.
• Improves speech and audio intelligibility in complex listening situations without introducing excessive distortion.
• Can be integrated with a wide range of source separation methods and is compatible with data-driven approaches like neural networks.
• Enables real-time audio processing suitable for consumer electronics, broadcast, telecommunications, and assistive devices.

Technical Classifications (CPCs)

Inventors & Applicants

Patent Abstract

An apparatus for generating a separated audio signal from an audio input signal is provided. The audio input signal comprises a target audio signal portion and a residual audio signal portion. The residual audio signal portion indicates a residual between the audio input signal and the target audio signal portion. The apparatus comprises a source separator (110), a determining module (120) and a signal processor (130). The source separator (110) is configured to determine an estimated target signal which depends on the audio input signal, the estimated target signal being an estimate of a signal that only comprises the target audio signal portion. The determining module (120) is configured to determine one or more result values depending on an estimated sound quality of the estimated target signal to obtain one or more parameter values, wherein the one or more parameter values are the one or more result values or depend on the one or more result values. The signal processor (130) is configured to generate the separated audio signal depending on the one or more parameter values and depending on at least one of the estimated target signal and the audio input signal and an estimated residual signal, the estimated residual signal being an estimate of a signal that only comprises the residual audio signal portion.