Application of emotion-based intonation and prosody to speech in text-to-speech systems
View Patent ↗A text-to-speech system that includes an arrangement for accepting text input, an arrangement for providing synthetic speech output, and an arrangement for imparting emotion-based features to synthetic speech output. The arrangement for imparting emotion-based features includes an arrangement for accepting instruction for imparting at least one emotion-based paradigm to synthetic speech output, as well as an arrangement for applying at least one emotion-based paradigm to synthetic speech output.
1. A text-to-speech system comprising:
an input to accept text;
a user interface adapted to accept at least one emoticon-based command that indicates at least one emotion to impart to speech synthesized from at least a portion of the text;
a segment selection and concatenation unit adapted to select a plurality of segments of speech from a database containing available segments for concatenation, the plurality of segments selected based at least in part on the at least one emoticon-based command to assist in imparting the at least one emotion to the speech synthesized from at least the portion of the text; and
a prosody prediction unit to determine at least one prosodic pattern to be applied to at least some of the plurality of segments based, at least in part, on the at least one emoticon-based command to further assist in imparting the at least one emotion to generate expressive synthetic speech output using the plurality of segments.
2. The system according to claim 1 , further comprising a translator to translate the at least one emoticon-based command into an emotion-based markup language.
3. A method of converting text to speech, said method comprising acts of:
accepting text input;
accepting at least one emoticon-based command from a user interface that indicates at least one emotion to impart to speech synthesized from at least a portion of the text;
selecting a plurality of segments of speech from a database containing available segments for concatenation, the plurality of segments selected based at least in part on the at least one emoticon-based command to assist in imparting the at least one emotion to the speech synthesized from at least the portion of the text and based at least in part on the text input; and
determining at least one prosodic pattern to be applied to at least some of the plurality of segments based, at least in part, on the at least one emoticon-based command to further assist in imparting the at least one emotion to the speech synthesized from at least the portion of the text.
4. The method according to claim 3 , further comprising an act of:
translating the at least one emoticon-based command into an emotion-based markup language.
5. A program storage device readable by machine, tangibly embodying a program of instructions executable by the machine to cause the machine to perform acts of:
accepting text input;
accepting at least one emoticon-based command from a user interface;
selecting a plurality of segments of speech from a database containing available segments for concatenation, the plurality of segments selected based at least in part on the at least one emoticon-based command to assist in imparting the at least one emotion to speech synthesized from at least the portion of the text and based at least in part on the text input; and
determining at least one prosodic pattern to be applied to at least some of the plurality of segments based, at least in part, on the at least one emoticon-based command to further assist in imparting the at least one emotion to the speech synthesized from at least the portion of the text.
6. The program storage device of claim 5 , wherein the method further comprises an act of:
translating the at least one emoticon-based command into an emotion-based markup language.