Automated Sound Effect Placement via Onset Strength Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current audio mixing processes rely heavily on manual experimentation and trial-and-error for placing sound effects in music, which can be time-consuming and inaccessible to those without experience.

Innovation Solution

An automated method for selecting sound effect placement points in a music audio signal using onset strength analysis, boosting, and mel-spectrogram or constant-Q transform criteria, allowing for the systematic insertion of sound effects into music audio signals.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If manual experimentation and trial-and-error methods are used for placing sound effects, then the mixing process allows for creative exploration, but the process becomes time-consuming and inaccessible to inexperienced users

Engineering Contradiction:
ImproveAccessibility to inexperienced usersVSAvoidTime required for mixing process
Core Design Contradiction:
Ease of operationVSLoss of time

Solution Approach 1:

The system performs automatic sound effect placement by analyzing the music audio signal itself to identify suitable insertion points based on onset strength, allowing the signal to select its own optimal placement locations without requiring manual user intervention or expertise

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The manual mechanical process of trial-and-error mixing is replaced with an automated computational system that uses signal processing algorithms to objectively determine sound effect placement points based on acoustic features like onset strength

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Extent of automation

If automated methods are used to determine sound effect placement points, then the mixing process becomes accessible to inexperienced users, but the system complexity increases

Engineering Contradiction:
ImproveAutomation of sound effect placementVSAvoidSystem complexity
Core Design Contradiction:
Extent of automationVSDevice complexity

Solution Approach 1:

The system extracts only the essential feature (onset strength) from the complex music audio signal to determine placement points, isolating the critical information needed for automated decision-making while ignoring other complex aspects of the audio signal

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The system transforms the complex audio signal into a simplified parameter representation (onset strength time series) that captures the essential temporal structure needed for placement decisions, changing the parameter space from raw audio waves to meaningful acoustic features

Inventive Principle:
Principle #35Parameter changes

3Measurement precision

If sound effects are placed at points with highest onset strength only, then the placement is objectively determined, but important rhythmic patterns may be missed

Engineering Contradiction:
ImproveObjectivity of placement point selectionVSAvoidRhythmic pattern information
Core Design Contradiction:
Measurement precisionVSLoss of information

Solution Approach 1:

The system merges multiple criteria (onset strength detection and rhythmic pattern recognition) into a unified placement decision process, combining the objective temporal information from onset strength with the musical structure information from rhythmic patterns to select final placement points

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentEP4105924B1System and method for selecting points in a music and audio signal for placement of sound effect
Publication Date: 2024.04.24 LEMON INC(GB)
  • EP4105924B1 patent drawingFigure 1
  • EP4105924B1 patent drawingFigure 2
  • EP4105924B1 patent drawingFigure 2

AI summary

A method of selecting points in a music audio signal for placement of a sound effect comprises searching for points in the music audio signal as potential candidate placement points based on one or more criteria such as melspec or CQT. An onset strength time series for the music audio signal is determined and boosted at points found by the search. Points are then selected from the boosted onset strength time series with a value larger than a predetermined threshold as candidate points for the placement of the sound effect.