公开(公告)号：US20190204998A1

公开(公告)日：2019-07-04

申请号：US15873839

申请日：2018-01-17

Applicant: Google LLC

Inventor： Greg Don Hartrell ,  Brady Duga ,  Alan Newberger ,  Christopher Salvarani ,  Garth Conboy ,  John Rivlin ,  Andrew Casey Brown

IPC: G06F3/0483 ,  G10L15/26 ,  G06F3/16

CPC classification number: G06F3/0483 ,  G06F3/167 ,  G10L15/265 ,  G10L25/78

Abstract: An audio book server may identify, from a plurality of electronic texts, an electronic text that corresponds with an audio book. The audio book server may determine, based at least in part on the electronic text, organizational data associated with a plurality of time-based locations of the audio book. The audio book server may output the audio book and the organizational data to a remote computing device.

公开(公告)号：US20250053738A1

公开(公告)日：2025-02-13

申请号：US18720376

申请日：2021-12-20

Applicant: Google LLC

Inventor： Ryan Dingler ,  John Rivlin ,  Christopher Salvarani ,  Yuanlei Zhang ,  Nazarii Kukhar ,  Russell John Wyatt Skerry-Ryan ,  Daisy Stanton ,  Judy Chang ,  Md Enzam Hossain

IPC: G06F40/253 ,  G06F3/0484 ,  G06F3/16 ,  G06F40/169 ,  G06F40/289 ,  G10L13/08

Abstract: Aspects of this disclosure are directed to techniques that enable efficient automated text-to-speech pronunciation editing for long form text documents. A computing device comprising a memory and a processor may be configured to perform the techniques. The memory may store a text document. The processor may process words in the text document to identify first candidate words that are predicted to be mispronounced during automated text-to-speech processing of the text document. The processor may next filter the first candidate words to remove one or more candidate words of the first candidate words and obtain second candidate words that have fewer candidate words than the first candidate words. The processor may then annotate the text document to obtain an annotated text document that identifies the second candidate words, and output at least a portion of the annotated text document that identifies at least one candidate word of the second candidate words.