Patents by Inventor Hannah Muckenhirn

Hannah Muckenhirn has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Targeted voice separation by speaker conditioned on spectrogram masking
    Patent number: 11922951
    Abstract: 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.
    Type: Grant
    Filed: January 3, 2022
    Date of Patent: March 5, 2024
    Assignee: GOOGLE LLC
    Inventors: Quan Wang, Prashant Sridhar, Ignacio Lopez Moreno, Hannah Muckenhirn
  • TARGETED VOICE SEPARATION BY SPEAKER CONDITIONED ON SPECTROGRAM MASKING
    Publication number: 20220122611
    Abstract: 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.
    Type: Application
    Filed: January 3, 2022
    Publication date: April 21, 2022
    Inventors: Quan Wang, Prashant Sridhar, Ignacio Lopez Moreno, Hannah Muckenhirn
  • Targeted voice separation by speaker conditioned on spectrogram masking
    Patent number: 11217254
    Abstract: 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.
    Type: Grant
    Filed: October 10, 2019
    Date of Patent: January 4, 2022
    Assignee: GOOGLE LLC
    Inventors: Quan Wang, Prashant Sridhar, Ignacio Lopez Moreno, Hannah Muckenhirn
  • TARGETED VOICE SEPARATION BY SPEAKER CONDITIONED ON SPECTROGRAM MASKING
    Publication number: 20200202869
    Abstract: 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.
    Type: Application
    Filed: October 10, 2019
    Publication date: June 25, 2020
    Inventors: Quan Wang, Prashant Sridhar, Ignacio Lopez Moreno, Hannah Muckenhirn