Music Feature Segment Extraction for Humming Search
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing music search technologies face inefficiencies in quickly identifying representative segments within music files, leading to increased querying time and storage requirements, particularly in humming searches and mobile applications.
Innovation Solution
A method and system for automatically acquiring feature segments in music files by converting them into character strings, evaluating segments based on music features such as repetition, average pitch, segment location, and semitone percentage, and determining the most representative segments for efficient search and storage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the entire music file is stored and searched for humming search, then search accuracy is maintained, but storage space increases and search time increases
Solution Approach 1:
The patent extracts only the most representative segments (feature segments) from the entire music file for storage and search operations. By identifying and isolating these key segments that contain the most distinctive musical characteristics, the system maintains search accuracy while dramatically reducing the amount of data that needs to be stored and processed.
Solution Approach 2:
The music file is divided into multiple segments, and the system evaluates each segment to identify the most representative ones. This segmentation approach allows the system to work with discrete, manageable portions of the music rather than treating it as a continuous whole, enabling efficient storage and targeted search operations.
2Reliability
If the entire music file is searched for humming search, then search completeness is maintained, but querying time increases
Solution Approach 1:
The system extracts and stores only the most representative segments from the music file that are most likely to contain the humming query. By pre-identifying and isolating these feature segments, the system reduces the search space from the entire music file to just the most relevant portions, significantly decreasing querying time while maintaining search completeness for humming-based queries.
Solution Approach 2:
The system performs preliminary analysis of the music file to identify and mark feature segments before the actual search operation. This preliminary action of pre-processing and segment identification ensures that when a humming search is performed, the system only needs to compare against the pre-identified feature segments rather than scanning the entire file, thus reducing querying time.
3Measurement precision
If manual selection of feature segments is performed, then segment accuracy is improved, but labor cost increases
Solution Approach 1:
The system employs automated algorithms that enable the music file to essentially select its own feature segments through computational analysis. The automated segment evaluation and selection process eliminates the need for manual human intervention, thereby maintaining high segment accuracy through objective musical feature analysis while completely eliminating the labor costs associated with manual selection.
Solution Approach 2:
The patent replaces the mechanical process of manual segment selection with an automated computational system. By using algorithms that objectively evaluate musical features such as melody, harmony, and rhythm patterns, the system substitutes human manual work with automated processing, maintaining or even improving segment accuracy while eliminating labor costs.
Data Source
AI summary
A method of automatically acquiring a feature segment in a music file includes receiving, with a processing device, a music file; converting the music file into a character string; evaluating at least one character string segment in the character string based on one or more music features; and determining, based on an evaluation result, at least one music segment corresponding to at least one character string segment in the character string as a feature segment.