Patents by Inventor Ernest J. PUSATERI

Ernest J. PUSATERI 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).

  • Inverse text normalization for automatic speech recognition
    Patent number: 10592604
    Abstract: Techniques for inverse text normalization are provided. In some examples, speech input is received and a spoken-form text representation of the speech input is generated. The spoken-form text representation includes a token sequence. A feature representation is determined for the spoken-form text representation and a sequence of labels is determined based on the feature representation. The sequence of labels is assigned to the token sequence and specifies a plurality of edit operations to perform on the token sequence. Each edit operation of the plurality of edit operations corresponds to one of a plurality of predetermined types of edit operations. A written-form text representation of the speech input is generated by applying the plurality of edit operations to the token sequence in accordance with the sequence of labels. A task responsive to the speech input is performed using the generated written-form text representation.
    Type: Grant
    Filed: June 29, 2018
    Date of Patent: March 17, 2020
    Assignee: Apple Inc.
    Inventors: Ernest J. Pusateri, Bharat Ram Ambati, Elizabeth S. Brooks, Donald R. McAllaster, Venkatesh Nagesha, Ondrej Platek
  • INVERSE TEXT NORMALIZATION FOR AUTOMATIC SPEECH RECOGNITION
    Publication number: 20190278841
    Abstract: Techniques for inverse text normalization are provided. In some examples, speech input is received and a spoken-form text representation of the speech input is generated. The spoken-form text representation includes a token sequence. A feature representation is determined for the spoken-form text representation and a sequence of labels is determined based on the feature representation. The sequence of labels is assigned to the token sequence and specifies a plurality of edit operations to perform on the token sequence. Each edit operation of the plurality of edit operations corresponds to one of a plurality of predetermined types of edit operations. A written-form text representation of the speech input is generated by applying the plurality of edit operations to the token sequence in accordance with the sequence of labels. A task responsive to the speech input is performed using the generated written-form text representation.
    Type: Application
    Filed: June 29, 2018
    Publication date: September 12, 2019
    Inventors: Ernest J. PUSATERI, Bharat Ram AMBATI, Elizabeth S. BROOKS, Donald R. MCALLASTER, Venkatesh NAGESHA, Ondrej PLATEK