Audio Fragment Capture via Theme Distance Calculation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users face difficulties in capturing specific fragments of music for ringtones when they forget song names or lyrics, as existing methods rely heavily on manual determination of start and end points using audio capturing software, which is inefficient.
Innovation Solution
An audio generation method that involves obtaining a comparison audio, performing theme extraction to obtain note sequences, retrieving matching original audio, calculating theme distances, and generating audio fragments with the smallest theme distance, allowing for automatic and efficient capture of matching audio segments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual determination of start and end points using audio capturing software is used, then capturing precision can be achieved, but operation complexity and time consumption increase significantly
Solution Approach 1:
The system performs preliminary theme extraction on the comparison audio to obtain note sequence information (note positions, pitches, durations) before the actual capturing process. This pre-processing enables automatic identification of audio fragments matching the user's humming melody, eliminating the need for manual start and end point determination during operation.
Solution Approach 2:
The system automatically retrieves matching original audio, extracts note sequences, calculates theme distances, and identifies optimal capturing fragments without requiring manual intervention. The algorithm self-determines the start and end points by finding the fragment with the smallest theme distance, making the capturing process autonomous and user-friendly.
2Measurement precision
If manual determination of start and end points is required, then capturing accuracy can be maintained, but time consumption increases
Solution Approach 1:
The system replaces the mechanical manual operation of determining start and end points with an automated computational system. The theme extraction algorithm processes the comparison audio and original audio to calculate theme distances, automatically identifying the optimal capturing fragment. This substitution dramatically reduces time consumption while maintaining capturing accuracy through algorithmic precision.
Solution Approach 2:
The system transforms the capturing task from manual time-based selection to automated parameter-based identification. By extracting note sequences with specific parameters (note positions, pitches, durations) and calculating theme distances, the system objectively determines the optimal fragment, eliminating subjective manual judgment and reducing time consumption.
3Ease of operation
If theme extraction and automatic matching is implemented, then ease of operation improves, but device complexity increases
Solution Approach 1:
The system segments the audio processing task into distinct functional modules: theme extraction module that processes comparison audio to obtain note sequences, audio retrieval module that finds matching original audio, theme distance calculation module that compares note sequences, and fragment selection module that identifies the optimal capturing segment. This modular segmentation manages system complexity by organizing functions into independent, manageable components.
Solution Approach 2:
The system introduces note sequence information (comprising note positions, pitches, and durations) as an intermediary representation between the raw audio input and the final capturing output. This intermediary structure enables systematic comparison and automatic matching while keeping the overall system architecture organized and manageable through standardized data formats.
Data Source
AI summary
Audio generation method, server and storage medium are provided. The method includes obtaining a comparison audio, and performing a theme extraction on the comparison audio to obtain a comparison note sequence, the comparison note sequence comprising comparison note positions, comparison note pitches, and a comparison note duration; obtaining an original audio matching with the comparison audio via audio retrieval, and obtaining an original note sequence corresponding to the original audio by performing a theme extraction on the original audio, the original note sequence comprising original note positions, original note pitches, and an original note duration; calculating theme distances between fragments of the comparison audio and fragments of the original audio according to the comparison note sequence and the original note sequence; and generating an audio by capturing a fragment that is of the original audio and that satisfies the smallest theme distance.