Towards a Universal Method for Meaningful Signal Detection

TL;DR

This paper proposes a signal analysis method that scores the meaningfulness of a waveform based solely on its intrinsic properties, effectively distinguishing human speech, animal sounds, and noise without understanding their content.

Contribution

It introduces a universal, content-independent approach to measure signal meaningfulness by clustering and description length minimization, validated across diverse audio types.

Findings

High meaningfulness scores for human speech across languages and speakers

Moderate scores for bird and orca vocalizations

Low scores for ambient noise

Abstract

It is known that human speech and certain animal vocalizations can convey meaningful content because we can decipher the content that a given utterance does convey. This paper explores an alternative approach to determining whether a signal is meaningful, one that analyzes only the signal itself and is independent of what the conveyed meaning might be. We devise a method that takes a waveform as input and outputs a score indicating its degree of `meaningfulness`. We cluster contiguous portions of the input to minimize the total description length, and then take the length of the code of the assigned cluster labels as meaningfulness score. We evaluate our method empirically, against several baselines, and show that it is the only one to give a high score to human speech in various languages and with various speakers, a moderate score to animal vocalizations from birds and orcas, and a low score to ambient noise from various sources.