Seeing Voices: 1 - Intro to Spectrograms

Jay explores an incredible visualization method used in speech recognition technology and in the analysis of animal communication. Spectrograms show which frequencies (high-pitch/low pitch) are active in a specific sound. They reveal a lot about the nature of sound, aid artificial intelligence, but more excitingly, inform us about the intelligence of animals we underestimate.

Prairie Dogs: America's Meerkats - Language

Wild Dolphins Swimming in HD Compilation

Speech Recognition, Mitch Marcus [slides]

[nicenoces]

Thank you so much. This is very interesting topic. I'm looking forward for the next episode.

[ambrishawasthi]

Super cool ...just looking for sound exploration ...please make more on this ....also make video about notes in sound

[RobertoSilva-hjyn]

Very helpfull video, very well explained

[mjacfardk]

As usual, you always share with us high quality content. 🙏 Thank you again, is there any notebook or code example?

[mudasserahmad]

Hey what does it mean dealing with mel spectrograms (128, 216, 3). By using 3 windows length 93ms, 46ms and 23ms and in the end they have write 128, 216, 3 what does 3 shows here??

[zenmasterjay]

I am designing an animal communication app using riffusion.