Four posts into this (one, two, three, four), it’s probably time to back up for a moment and recap.


Questions

I’ve been looking at two different questions:

Given raw MBARI hydrophone clips, can Perch 2.0:

  1. Distinguish between clips where a humpback vocalization is present vs not?
  2. Distinguish between different types of humpback vocalizations?

Data

Using three different groups of clips:1

  1. High-confidence detector-score clips (as estimated by the Google humpback detector model with scores of >=90% and <=5%)
  2. Lower-confidence detector-score clips (scores of 70–90% and 10–30%)
  3. A large (~9000) stratified sample across detector-score buckets

Assessment

And checking the results in two ways:

  1. 2D dimensionality reduction plots
  2. Manual listening to embedding nearest neighbors

Which ends up being twelve different potential experiments:

Present or Not

PCA/UMAPNearest-neighbor listening
High-confidence clipsVisually yeslater?
Lower-confidence clipsNot clearlyNot really
Stratified samplelater?next?

Types of vocalizations

PCA/UMAPNearest-neighbor listening
High-confidence clips
Lower-confidence clips
Stratified samplelater?One tentative yes (bloops only so far)

This is all still quite exploratory, but the matrix will keep me from treating different tests as if they answered the same question.

I don’t think I need to fill in all twelve boxes just for completeness, but the “next?” box looks like the best next step and I’ll keep the boxes marked “later?” in mind.


  1. All clips are from the MBARI December 21, 2016 16 kHz full-day audio file. ↩︎