AUDIO-MTHRFCKR

AUDIO-MTHRFCKR

1383 bookmarks
Newest
TONet
TONet
The official implementation of "TONet: Tone-Octave Network for Singing Melody Extraction from Polyphonic Music"
·github.com·
TONet
VMAudioBack
VMAudioBack
Workaround for VMware guest OS Audio Distortion (Windows) that run natively in Win2k and XP without needing DotNet framework. - Raymai97/VMAudioBack
·github.com·
VMAudioBack
AudioPick
AudioPick
A Chrome Extension to pick a preferred audio output device for HTML5 audio and video elements - rain-fighters/AudioPick
·github.com·
AudioPick
feelskunaman
feelskunaman
A tool for visualizing emotions in music using a Python wrapper for Spotify API. Independent post-baccalaureate research by Nick Stapleton. For Kunaveer, a friend.
·github.com·
feelskunaman
GitHub mjhydriSingingVocalBeatTracking This repo contains the source code of the first deep learningbase singing voice beat tracking system It leverages WavLM and DistilHuBERT pretrained speech models to create vocal embeddings and trains linear multihead selfattention layers on top of them to extract vocal beat activations Then it uses HMM decoder to infer signing beats and tempo
GitHub mjhydriSingingVocalBeatTracking This repo contains the source code of the first deep learningbase singing voice beat tracking system It leverages WavLM and DistilHuBERT pretrained speech models to create vocal embeddings and trains linear multihead selfattention layers on top of them to extract vocal beat activations Then it uses HMM decoder to infer signing beats and tempo
This repo contains the source code of the first deep learningbase singing voice beat tracking system It leverages WavLM and DistilHuBERT pretrained speech models to create vocal embeddings and trains linear multihead selfattention layers on top of them to extract vocal beat activations Then it uses HMM decoder to infer signing beats and tempo GitHub mjhydriSingingVocalBeatTracking This repo contains the source code of the first deep learningbase singing voice beat tracking system It leverages WavLM and DistilHuBERT pretrained speech models to create vocal embeddings and trains linear multihead selfattention layers on top of them to extract vocal beat activations Then it uses HMM decoder to infer signing beats and tempo
·github.com·
GitHub mjhydriSingingVocalBeatTracking This repo contains the source code of the first deep learningbase singing voice beat tracking system It leverages WavLM and DistilHuBERT pretrained speech models to create vocal embeddings and trains linear multihead selfattention layers on top of them to extract vocal beat activations Then it uses HMM decoder to infer signing beats and tempo