GitHub

edgeimpulse/ai-labeling-audio-spectrogram-transformer

This is an Edge Impulse AI Actions block that uses Audio Spectrogram Transformers from HuggingFace to automatically label audio data. You can use this repo as the basis for custom tasks that use big ...
iPhoneAddict

Voice Spectrogram Logger

The spectrogram of voice is displayed in the range of 20 - 2500Hz. You can zoom in/out the spectrogram by pinching in/out smoothly. Also landscape orientation is supported. By moving "vivid" slider, ...
GitHub

Using SciPy's ShortTimeFFT instead of spectrogram function for compute_spectrum

This issue has been somewhat brought up in another post, but I also wanted to point out that the scipy.spectrogram function used in compute_spectrum_welch is now considered a legacy function. There's ...
IEEE

Waveform-Domain Speech Enhancement Using Spectrogram Encoding for Robust Speech Recognition

Abstract: While waveform-domain speech enhancement (SE) has been extensively investigated in recent years and achieves state-of-the-art performance in many datasets, spectrogram-based SE tends to show ...
IEEE

Speech Enhancement Algorithm based on Reassigned Spectrogram and Auditory Masking

Abstract: A single channel speech enhancement algorithm is proposed based on reassigned spectrogram and masking properties of the human auditory system. According to the strong correlation of speech ...