Targeted voice separation by speaker conditioned on spectrogram masking
AssigneeGoogle Inc.
InventorsQuan Wang, Prashant Sridhar, Ignacio Lopez Moreno, Hannah Muckenhim
Life of this patent
Estimating the term…
Loading patent…
AssigneeGoogle Inc.
InventorsQuan Wang, Prashant Sridhar, Ignacio Lopez Moreno, Hannah Muckenhim
Estimating the term…
Techniques are disclosed that enable processing of audio data to generate one or more refined versions of audio data, where each of the refined versions of audio data isolate one or more utterances of a single respective human speaker. Various implementations generate a refined version of audio data that isolates utterance(s) of a single human speaker by processing a spectrogram representation of the audio data (generated by processing the audio data with a frequency transformation) using a mask generated by processing the spectrogram of the audio data and a speaker embedding for the single human speaker using a trained voice filter model. Output generated over the trained voice filter model is processed using an inverse of the frequency transformation to generate the refined audio data.
A client device comprising:
A method implemented by one or more processors, the method comprising:
A non-transitory computer-readable storage medium storing instructions executable by one or more processors of a client device to perform a method of:
Dependencies are inferred from the claim text.