Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Towards a Universal Method for Meaningful Signal Detection

Louis Mahon

TL;DR

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, is explored, which is the only one to give a high score to human speech in various languages and with various speakers.

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.

Towards a Universal Method for Meaningful Signal Detection

TL;DR

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, is explored, which is the only one to give a high score to human speech in various languages and with various speakers.

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.
Paper Structure (12 sections, 2 equations, 1 figure, 2 tables)

This paper contains 12 sections, 2 equations, 1 figure, 2 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Method
  4. Formal Description
  5. Implementation Details
  6. Experimental Evaluation
  7. Datasets
  8. Comparison Methods
  9. Main Results
  10. Ablation Studies
  11. Signal Length
  12. Conclusion

Figures (1)

  • Figure 1: Scores of our method for each signal type, as a function of the number of samples (sample rate 44100 Hz). Colours are rougly grouped by signal type, red-orange for speech, green for animal vocalizations and blue-grey for others. For each language, the first speaker ('-s1') is male, and the second female.