Audio Processing Recommendations in Digital Audio Workstations

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current digital audio workstations rely heavily on human expertise for audio mixing and processing, which can be time-consuming and inconsistent, as they require manual selection of audio processing functions for individual tracks, lacking an efficient automated recommendation system for optimal audio processing.

Innovation Solution

A machine learning-based system that extracts audio features from original tracks, compares them to a database of training data, and provides personalized recommendations for processing, allowing users to input target features and tags for tailored audio processing and mixing, utilizing techniques like STFT and MFCC preprocessing and neural networks for feature extraction and similarity analysis.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual selection of audio processing functions is used, then audio processing quality can be maintained through human expertise, but the process becomes time-consuming and inconsistent

Engineering Contradiction:

Improveaudio processing quality consistencyVSAvoidtime for manual audio mixing

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system creates a database of audio processing operations performed by human experts on training audio tracks. This database serves as a copy of human expertise that can be automatically applied to new audio tracks through similarity matching, eliminating the need for manual processing while preserving expert-level quality consistency

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The system transforms audio tracks into feature space using STFT and MFCC transformations, converting complex audio signals into comparable parameter sets. This enables automated comparison and matching of audio tracks with appropriate processing operations from the database based on feature similarity

Inventive Principle:

Principle #35Parameter changes

2Productivity

If automated audio processing is implemented, then processing speed and consistency improve, but the system lacks the ability to provide optimal processing recommendations

Engineering Contradiction:

Improveaudio processing speedVSAvoidability to provide optimal processing recommendations

Core Design Contradiction:

ProductivityVSAdaptability or versatility

Solution Approach 1:

The system uses audio features extracted from input tracks as feedback to query the database and retrieve similar training examples with their associated processing operations. This feedback mechanism enables the system to adaptively select optimal processing recommendations based on the specific characteristics of each audio track

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system pre-processes training audio tracks by extracting features and storing them in a database along with their processing operations before they are needed. This preliminary organization of data in feature space enables rapid retrieval and recommendation of optimal processing operations when new audio tracks are processed

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS11687314B2Digital audio workstation with audio processing recommendations

Publication Date: 2023.06.27 WAVES AUDIO

AI summary

Presentation of a recommendation to a user for individual processing of audio tracks in a digital audio workstation. Training audio tracks are provided to a human sound mixer and responsive to the training audio tracks individually processed training audio tracks are received from the human sound mixer. The training audio tracks and the individually processed training audio tracks are input to a machine to train the machine. Audio processing operations are output from the trained machine and stored in a record of a database.