US Patent 9728185 Recognizing speech using neural networks
Patent 9728185 was granted and assigned to Google on August, 2017 by the United States Patent and Trademark Office.
All edits
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for recognizing speech using neural networks. One of the methods includes receiving an audio input; processing the audio input using an acoustic model to generate a respective phoneme score for each of a plurality of phoneme labels; processing one or more of the phoneme scores using an inverse pronunciation model to generate a respective grapheme score for each of a plurality of grapheme labels; and processing one or more of the grapheme scores using a language model to generate a respective text label score for each of a plurality of text labels.
US Patent 09728185 Recognizing speech using neural networks US Patent 9728185 Recognizing speech using neural networks
US Patent 09728185 Recognizing speech using neural networks
Find more entities like US Patent 9728185 Recognizing speech using neural networks
