| CPC G10L 15/1815 (2013.01) [G10L 15/05 (2013.01); G10L 15/19 (2013.01)] | 25 Claims |
|
1. A computer-implemented method comprising the steps of:
presenting, by one or more computing devices, in a region of a display of a computing device, some first text, dictated or not;
receiving, by the one or more computing devices, audio data of an utterance;
executing, by the one or more computing devices, automated speech recognition (ASR) software to generate a transcription of the utterance;
determining, by the one or more computing devices, whether to substitute a transcription of the utterance for a fragment of the first text that is not explicitly specified by the user, to insert into or append to the first text the transcription as new additional text or to perform another operation;
responding to the determining whether to substitute the transcription of the utterance for a fragment of the first text that is not explicitly specified by the user, to insert into or append to the first text the transcription as new additional text, or to perform another operation, by presenting by the one or more computing devices, in the region of a display of a computing device, a second text, wherein the second text further comprises the transcription of the utterance either automatically substituted for the fragment of the first text, or else, inserted as additional text, or transformed into another modification of the first text, or no modification, wherein a portion of the second text around the substituted with or inserted transcription of the utterance, is optionally further adjusted for proper punctuation, word repetition, grammar and semantics, wherein the fragment of the first text to be replaced is optionally highlighted briefly prior to presenting the second text.
|