#Spectrograms
spectrograms of work in progress
November 9, 2026 at 5:44 AM
the two genders
November 8, 2026 at 7:48 PM
Hey guys I'm working on a Minecraft ARG!

It's about trauma and uses morse code and spectrograms and will fall off hard in viewership after I've fully exhausted the one interesting idea I have. I plan to not upload for months after that and it will turn out to be the ghost of my dead girlfriend idk
November 5, 2026 at 1:26 AM
#MAV
Fusing STFT and Mel spectrograms through a CBAM-enhanced MobileNetV2 lets a Tello quadrotor detect propeller damage from in-flight audio at low compute cost.
Details: https://www.maxapress.com/article/doi/10.48130/mav-0026-0015
#FaultDiagnosis #MobileNetV2 #AudioSignal
November 6, 2026 at 4:15 AM
How the forthcoming Princeton Bird Guide for North America tackles crossbills - Lewington plates combined with spectrograms. Perhaps something similar will become the norm in future bird guides?
#UKBirding
November 5, 2026 at 8:36 AM
For speech, language and more:

- Fine-tune Whisper on corrected transcripts, plus speaker diarization
- Bioacoustics boxes on spectrograms
- Interlinear glossing for fieldwork, and dependency trees
- Document layout, map features from GeoTIFFs, video tracking, robot episodes
November 5, 2026 at 4:37 PM
I don't like apple all that much but their AAC encoder is literally magical.
November 4, 2026 at 2:09 AM
Solving the Mystery of the Electron Radiation Belt at Uranus: Leveraging Knowledge of Earth's Radiation Belts in a Re-Examination of Voyager 2 Observations. R. C. Allen et. al. https://arxiv.org/abs/2611.02221
November 5, 2026 at 5:13 AM
Yeah could be. It's hard to tell because the stem extraction is...not good from that era. (Unless it's an Ella Fitzgerald album. Her voice was special; god bless the producers who recognized it and made sure the recordings were good. Ella spectrograms are as beautiful to see as to hear.)
October 30, 2026 at 2:10 AM
More projects from the MSc students from @uniofstandrews.bsky.social – this time acoustic ecology! Autumn is a great time for acoustics, and they designed projects focussing on bush cricket song, as well as social call production in bats in relation to habitat type. @mikemwebster.bsky.social
October 27, 2026 at 12:44 PM
A Regions of Interest (ROI) algorithm can be used to identify T-phase seismic signals within spectrograms of hydrophone recordings. This can be used to fill in the monitoring gap for remote regions, such as the central Arctic Ocean.

🔗 Read now: seismica.library.mcgill.ca/article/view...
October 26, 2026 at 3:11 PM
Spectrograms are so fucking cool like what do you MEAN you can show an exact sound on a graph and you can see the pitch and you can see the volume and you can see the vowels and the tongue placement and the consonants?!? And you can learn how to read the graph and guess which word is being said!!!
October 26, 2026 at 5:03 AM
"And me? They pay me to organize their radar madrassa cruises that they use to chase down the orbital to try to read its mind. I can see the raw data flows in the spectrograms, sometimes I can feel my brain trying to put it together, the trick is to not think about it."
October 24, 2026 at 3:08 AM
WaveCommitments: Private and Verifiable Speech-Agent Marketplaces
tech_blogs_arxiv | Author: Oguzhan Baser, Kaan Kale, Sriram Vishwanath, Sandeep Chinchali

#Cryptography
WaveCommitments: Private and Verifiable Speech-Agent Marketplaces
Modern speech systems are evolving into ecosystems of autonomous speech agents that speak together, negotiate, and trade assets such as embeddings, spectrograms, or raw data. In such markets, sellers cannot reveal assets for evaluation due to privacy constraints, and buyers cannot price what they ca
arxiv.org
October 21, 2026 at 4:06 AM
Qiwu Wen, Jahangir Alam, Eric Charton: From Spectrograms to Shallow Speech SSL: Audio-Frontend Design for Generator-Disjoint and Low-Latency Audio--Visual Deepfake Detection https://arxiv.org/abs/2610.24138 https://arxiv.org/pdf/2610.24138 https://arxiv.org/html/2610.24138
October 20, 2026 at 6:44 AM
Smartphone voice recordings showed patterns associated with type 2 diabetes. Separate models for women and men reached about 72% balanced accuracy. doi.org/hcn824
Scientists see new vocal patterns associated with type 2 diabetes
A new study in the IEEE Journal of Biomedical and Health Informatics reveals how scientists at Klick Labs created visual maps of sound frequencies (spectrograms) to identify complex, new patterns associated with type 2 diabetes, using only smartphone recordings of randomly selected short English sentences and participant sex as study criteria.
medicalxpress.com
October 19, 2026 at 8:40 PM
anyway i should get on with making species sampler spectrograms for my tetrapod language paper

we've gotta represent the common patterns in bird, reptile, mammal, and amphibian speech
October 17, 2026 at 2:57 PM
Agree you need to define the side views as sums instead of just looking in from that direction, which is indeed unintuitive

Spectrograms are explaining something different though, right? They're saying "here is how the frequency decomposition changes as a function of time" vs "here is the decomp"
October 15, 2026 at 3:52 AM
Found out there was a tiny mistake with an onomatopoeia named "Trri"and "Trriits". I found out it is the same sound I have drawn before as "Krrill" . When looking spectrograms, the shapes and sounds match! It is the metallic bassy sound! Chaotic BRW used that sound in 2023 making amazing dubstep
October 13, 2026 at 5:16 AM
normal spectrogram
October 10, 2026 at 10:31 PM
Process piece spectrograms never get old
October 8, 2026 at 5:31 PM
@pythonhub.dev Free, Open-Source, Software Defined Radio Project. Without SDR, it's a GNU Radio signal chain, that generates spectrograms.

See the microwave modulation technique, in real-time, that inspired decades of insipid internet comments!
Download the OpenV2K SDR Python App Today: Generate Sharp's 1974 "Voice To Skull" Modulation Technique, at Home. With amplification, this is a way to demonstrate, voice modulation of the microwave auditory effect:

github.com/OpenV2K
October 8, 2026 at 5:27 AM
more Sonic Visualizer spectrograms from the new album, these from the track For Every Snake A Sweater
October 8, 2026 at 12:08 AM