Why are some words easier to recognize than others? Some talk about perceptual neighborhood density, a measure of how many words sound similar to a query word. Visualizing these distances is the first step. Thus...
Check out the acoustic network embedding (ANE) visualization at
https://quicksin.stanford.edu/ane
Enter an English word in the search bar and see the words that are closest to your chosen word. You can change the number of neighbors displayed and the underling embedding dimension. Move your mouse over a word to see it’s distance from the search word.
This visualization is based on Woojay Jeon's (@Apple) Acoustic Neighbor Embeddings (ACN). His network learns a high-dimensional embedding that puts each English word into a point in a multi-dimensional space so that acoustic distances between words are preserved.
For more details see this blog posting: https://ccrma.stanford.edu/blogs/malcolm/visualizing-word-acoustic-neighborhood-embeddings-ane
Have fun! Go to https://quicksin.stanford.edu/ane
- Malcolm