A quick search method for audio signals based on a piecewise linear representation of feature trajectories

TL;DR

This paper introduces a fast audio search method using piecewise linear feature trajectory representation, significantly reducing search time while maintaining accuracy in long unlabeled audio streams.

Contribution

It proposes a novel feature-dimension reduction technique based on piecewise linear trajectories and segment-based KL transform for rapid audio similarity search.

Findings

Search time reduced to 1/12 of previous methods

Detected queries in approximately 0.3 seconds from 200-hour database

Maintains search accuracy despite dimension reduction

Abstract

This paper presents a new method for a quick similarity-based search through long unlabeled audio streams to detect and locate audio clips provided by users. The method involves feature-dimension reduction based on a piecewise linear representation of a sequential feature trajectory extracted from a long audio stream. Two techniques enable us to obtain a piecewise linear representation: the dynamic segmentation of feature trajectories and the segment-based Karhunen-L\'{o}eve (KL) transform. The proposed search method guarantees the same search results as the search method without the proposed feature-dimension reduction method in principle. Experiment results indicate significant improvements in search speed. For example the proposed method reduced the total search time to approximately 1/12 that of previous methods and detected queries in approximately 0.3 seconds from a 200-hour audio database.