Multi-unit approach to text-to-speech synthesis

A method, including:

• receiving a stream of textual input;
• matching portions of the input textual stream to audio segments derived from one or more voice samples at multiple levels;
• and
• synthesizing matching audio segments into speech output.

A computer program product including instructions tangibly stored on a computer-readable medium, the product including instructions for causing a computing device to:

• match phrase units of an input string to audio segments from a plurality of audio segments;
• parse unmatched phrase units into word units;
• match the word units to audio segments;
• and
• synthesize the input string, including combining the audio segments associated with the phrase and word units.

A system, including:

• an input capture routine to receive an input string that includes phrase units;
• a unit matching engine, in communication with the input capture routine, to match the phrase units to audio segments from a plurality of audio segments including using properties of or between audio segments for matching phrase units;
• a parsing engine, in communication with the unit matching engine, to parse unmatched phrase units into word units, the unit matching engine configured to match the word units to audio segments including using properties of or between the audio segments for matching word units;
• a synthesis block, in communication with the unit matching engine, to synthesize the input string, including combining the audio segments associated with the phrase and word units;
• and
• a storage unit to store audio segments and properties of or between the audio segments.

A method including

• providing a library of audio segments and associated metadata defining properties of or between a given segment and another segment, the library including one or more levels of units in accordance with a hierarchy;
• matching, at a first level of the hierarchy, units of a received input string to audio segments, the received input string having one or more units at a first level;
• parsing unmatched units to units at a second level in the hierarchy;
• matching one or more units at the second level of the hierarchy to audio segments;
• and
• synthesizing the input string including combining the audio segments associated with the first and second levels.

A method including

• receiving audio segments;
• parsing the audio segments into units of a first level in a hierarchy of levels;
• defining properties of or between units;
• storing the units and the properties;
• parsing the units into sub-units;
• defining properties of or between the sub-units;
• and
• storing the sub-units and properties.

A method including

• receiving audio segments;
• parsing the audio segments into units of a first level in a hierarchy of levels;
• defining properties of or between units;
• storing the units and the properties;
• parsing the units into units of a next level in the hierarchy of levels;
• defining properties of or between units in the next level;
• storing the units and properties;
• and
• continuing to parse units at a given level into units at a next level in the hierarchy until a final parsing is performed;
• at each level, defining properties of or between units and storing the units and the properties;
• and
• at a final level in the hierarchy storing units.