Methods and system for creating and editing an XML-based speech synthesis document

A system for creating and editing an XML-based speech synthesis document for input to a text-to-speech engine, the system comprising:

• one or more processors for executing processor-executable instructions;
• a text-to-speech engine configured to execute on the one or more processors for generating an XML-based speech synthesis document corresponding to pre-selected text and audibly rendering the XML-based speech synthesis document corresponding to the pre-selected text;
• at least one recording device for recording voice utterances of a user reading the pre-selected text and for recording a synthesized speech output generated by the text-to-speech engine based on the XML-based speech synthesis document, the synthesized speech output comprising an audible rendering of the pre-selected text;
• a parser for parsing the recorded voice utterances into individual words and periods of silence and for parsing the synthesized speech output into corresponding individual words and periods of silence;
• and
• a speech synthesis document comparator-annotator for annotating the XML-based speech synthesis document based upon a comparison of the recorded voice utterances and the recorded synthesized speech output, the annotating comprising inserting at least one of an XML emphasis element, an XML prosody element, or an XML break element into the XML-based speech synthesis document.

A non-transitory computer-readable storage medium having computer-readable code embedded therein, which when loaded to and executed by a computing system causes the system to:

• record voice utterances of a user reading a pre-selected text;
• parse the recorded voice utterances into individual words and periods of silence;
• generate an XML-based speech synthesis document corresponding to the pre-selected text;
• record a synthesized speech output generated by a text-to-speech engine based on the XML-based speech synthesis document, the synthesized speech output comprising an audible rendering of the pre-selected text;
• parse the synthesized speech output into individual words and periods of silence;
• and
• annotate a XML-based speech synthesis document based upon a comparison of the recorded voice utterances and the recorded synthesized speech output, the annotating comprising inserting at least one of an XML emphasis element, an XML prosody element, or an XML break element into the XML-based speech synthesis document.