Method and system for providing audio playback of a multi-source document
AssigneeMicrosoft Corporation
InventorsJeffrey C. Reynar, Erik Rucker, Paul Kyong Hvan Kim
Life of this patent
Estimating the term…
Abstract
A multi-source input and playback utility that accepts inputs from various sources, transcribes the inputs as text, and plays aloud user-selected portions of the text is disclosed. The user may select a portion of the text and request audio playback thereof. The utility examines each transcribed word in the selected text. If stored audio data is associated with a given word, that audio data is retrieved and played. If no audio data is associated, then a textto-speech entry or series of entries is retrieved and played instead.
Claims30
A method for linking audio to text in a multi-source input and playback system, said method comprising the steps of:
- dictating one or more words;
- transcribing the one or more words to form a first text set within a document;
- storing the first text set on a storage medium;
- comparing each audio element of a stored audio version of the one or more words with each corresponding text element of the first text set;
- inserting second text into the document, wherein the second text is non-audio text;
- associating a text-to-speech entry with the second text;
- and
- forming a continuous stream of audio from (1) stored audio data corresponding to the first text set and (2) the text-to-speech entry corresponding to the second text.
A computer-implemented method for creating and vocalizing a document, comprising the steps of:
- speaking one or more words into an input device;
- transcribing the one or more words as a first text entry within a document;
- storing the one or more words on a storage-medium;
- comparing each word of the one or more words with each word of said first text entry;
- inputting a second text entry within the document, wherein the step of inputting the second text entry does not comprise speaking;
- assigning a text-to-speech entry to said second text entry;
- and
- playing back the one or more words and the text-to-speech entry in an order corresponding to a placement of the first and second entries within said document.
A computer-implemented method for providing audio playback of a text document, comprising the steps of:
- selecting a text set comprising at least one word, wherein each word comprises at least one phoneme;
- determining whether a user-dictated audio input corresponds to a first word of the text set;
- in the event that a user-dictated audio input corresponds to the first word, playing the user-dictated audio input through an audio output device;
- otherwise, determining whether one of a plurality of text-to-speech entries corresponds to the first word;
- in the event that a text-to-speech entry corresponds to the first word, playing the text-to-speech entry through an audio output device;
- otherwise, determining which of the plurality of text-to-speech entries corresponds to a phoneme of the first word;
- and
- in response to determining which of the plurality of text-to-speech entries corresponds to the phoneme of the first word, playing the corresponding text-to-speech entry through an audio output device.
A method for compiling and evaluating text within a document, said method comprising the steps of:
- inputting dictated words into a document;
- converting said dictated words into a first text set within said document by use of a voice recognition process;
- storing said dictated words separately but linked to said first text set for later audio playback;
- inputting non-audio text into said document as a second text set within said document, wherein said non-audio text is inputted by one or more of (a) typing the non-audio text into the document using a keyboard, (b) copying the non-audio text into the document using a mouse, and (c) handwriting text which is converted to the non-audio text using a handwriting recognition program module;
- and
- playing back audio corresponding to said first and second text sets in an order corresponding to a placement of said first and second text sets within said document, wherein a first portion of said audio corresponding to said first text set is provided by playback of said stored dictated words, and a second portion of said audio corresponding to said second text set is provided by playback of a text-to-speech process.
Dependencies are inferred from the claim text.