Pinned Repositories
asteroid
The PyTorch-based audio source separation toolkit for researchers
CognitiveServicesLab
hse-intro2DL
ml-course-hse
Машинное обучение на ФКН ВШЭ
NNoevSnake
perflab
svoice
We provide a PyTorch implementation of the paper Voice Separation with an Unknown Number of Multiple Speakers In which, we present a new method for separating a mixed audio sequence, in which multiple voices speak simultaneously. The new method employs gated neural networks that are trained to separate the voices at multiple processing steps, while maintaining the speaker in each output channel fixed. A different model is trained for every number of possible speakers, and the model with the largest number of speakers is employed to select the actual number of speakers in a given sample. Our method greatly outperforms the current state of the art, which, as we show, is not competitive for more than two speakers.
WhoIsImposterBot
svoice
We provide a PyTorch implementation of the paper Voice Separation with an Unknown Number of Multiple Speakers In which, we present a new method for separating a mixed audio sequence, in which multiple voices speak simultaneously. The new method employs gated neural networks that are trained to separate the voices at multiple processing steps, while maintaining the speaker in each output channel fixed. A different model is trained for every number of possible speakers, and the model with the largest number of speakers is employed to select the actual number of speakers in a given sample. Our method greatly outperforms the current state of the art, which, as we show, is not competitive for more than two speakers.
kaka2makaka's Repositories
kaka2makaka/asteroid
The PyTorch-based audio source separation toolkit for researchers
kaka2makaka/WhoIsImposterBot
kaka2makaka/hse-intro2DL
kaka2makaka/svoice
We provide a PyTorch implementation of the paper Voice Separation with an Unknown Number of Multiple Speakers In which, we present a new method for separating a mixed audio sequence, in which multiple voices speak simultaneously. The new method employs gated neural networks that are trained to separate the voices at multiple processing steps, while maintaining the speaker in each output channel fixed. A different model is trained for every number of possible speakers, and the model with the largest number of speakers is employed to select the actual number of speakers in a given sample. Our method greatly outperforms the current state of the art, which, as we show, is not competitive for more than two speakers.
kaka2makaka/perflab
kaka2makaka/NNoevSnake
kaka2makaka/ml-course-hse
Машинное обучение на ФКН ВШЭ
kaka2makaka/CognitiveServicesLab