A Review of Audio Features and Statistical Models Exploited for Voice Pattern Design

TL;DR

This paper provides an updated survey of audio fingerprinting techniques, focusing on feature extraction and statistical models used for robust voice pattern design in audio identification systems.

Contribution

It offers a comprehensive review of recent audio fingerprinting algorithms, emphasizing feature design and statistical modeling, filling a gap since the last major survey over eight years ago.

Findings

Various audio features are analyzed for robustness and efficiency.

Statistical models improve the accuracy of voice pattern recognition.

The survey highlights recent advancements in fingerprint design techniques.

Abstract

Audio fingerprinting, also named as audio hashing, has been well-known as a powerful technique to perform audio identification and synchronization. It basically involves two major steps: fingerprint (voice pattern) design and matching search. While the first step concerns the derivation of a robust and compact audio signature, the second step usually requires knowledge about database and quick-search algorithms. Though this technique offers a wide range of real-world applications, to the best of the authors' knowledge, a comprehensive survey of existing algorithms appeared more than eight years ago. Thus, in this paper, we present a more up-to-date review and, for emphasizing on the audio signal processing aspect, we focus our state-of-the-art survey on the fingerprint design step for which various audio features and their tractable statistical models are discussed.