Method and apparatus for providing an interactive language tutor
View Patent ↗A method and apparatus for generating a pronunciation score by receiving a user phrase intended to conform to a reference phrase and processing the user phrase in accordance with at least one of an articulation-scoring engine, a duration scoring engine and an intonation-scoring engine to derive thereby the pronunciation score. The scores provided by the various scoring engines are adapted to provide a visual and/or numerical feedback that provides information pertaining to correctness or incorrectness in one or more speech-features such as intonation, articulation, voicing, phoneme error and relative word duration. Such useful interactive feedback will allow a user to quickly identify the problem area and take remedial action in reciting “tutor” sentences or phrases.
1. A method for providing speech-feature feedback, said method comprising the steps of:
presenting a reference utterance;
displaying graphically each word of said reference utterance;
displaying graphically a speech-feature associated with speech of said reference utterance;
receiving a user utterance that represents speech of said reference utterance by a user;
displaying graphically a speech-feature associated with speech of said user utterance; and
displaying graphically a score field for each graphically displayed word of said reference utterance, wherein each score field has a length indicative of a duration of said corresponding word of said user utterance, wherein each score field includes at least one numerical score for at least one speech-feature of said word of said user utterance.
2. The method of claim 1 , wherein said speech-feature represents intonation.
3. The method of claim 2 , wherein said speech-feature associated with speech of said reference utterance and said speech-feature associated with speech of said user utterance are graphically displayed as intonation curves.
4. The method of claim 1 , wherein said speech-feature represents acoustic quality.
5. The method of claim 1 , wherein said speech-feature represents word duration.
6. The method of claim 1 , wherein said at least one numerical score comprises an intonation score.
7. The method of claim 1 , wherein said at least one numerical score comprises an acoustic quality score.
8. The method of claim 1 , wherein said at least one numerical score comprises a word duration score.
9. The method of claim 1 , further comprising the step of:
playing said reference utterance.
10. The method of claim 1 , wherein said speech-feature associated with speech of said reference utterance is presented graphically as a plurality of intonation curves corresponding to said words of said reference utterance.
11. The method of claim 1 , wherein said speech-feature associated with speech of said user utterance is presented graphically as a plurality of international phonetic symbols corresponding to a selected graphically displayed word of said reference utterance.
12. The method of claim 11 , wherein a subset of said plurality of international phonetic symbols are highlighted to indicate one or more phonemes of said user utterance that are deemed mispronounced.
13. The method of claim 1 , wherein one or more of said graphically displayed words of said reference utterance are highlighted to indicated one or more words of said user utterance that are deemed mispronounced.
14. The method of claim 1 , wherein said method is implemented by a handheld apparatus.
15. The method of claim 1 , further comprising the step of:
downloading a set of reference utterances from a remote source.
16. The method of claim 1 , wherein numerical scores associated with said at least one speech-feature are graphically displayed for illustrating historical performance.
17. A computer readable medium for storing instructions that, when executed by a processor, perform a method for providing speech-feature feedback, said method comprising the steps of:
presenting a reference utterance;
displaying graphically each word of said reference utterance;
displaying graphically a speech-feature associated with speech of said reference utterance;
receiving a user utterance that represents speech of said reference utterance by a user;
displaying graphically a speech-feature associated with speech of said user utterance; and
displaying graphically a score field for each graphically displayed word of said reference utterance, wherein each score field has a length indicative of a duration of said corresponding word of said user utterance, wherein each score field includes at least one numerical score for at least one speech-feature of said word of said user utterance.
18. Apparatus for providing speech-feature feedback, said apparatus comprising:
means for presenting a reference utterance;
means for displaying graphically each word of said reference utterance;
means for displaying graphically a speech-feature associated with speech of said reference utterance;
means for receiving a user utterance that represents speech of said reference utterance by a user; and
means for displaying graphically a speech-feature associated with speech of said user utterance; and
means for displaying graphically a score field for each graphically displayed word of said reference utterance, wherein each score field has a length indicative of a duration of said corresponding word of said user utterance, wherein each score field includes at least one numerical score for at least one speech-feature of said word of said user utterance.
19. A handheld device, comprising:
a voice input port for receiving a voiced user utterance that represents speech of a reference utterance;
a display device for displaying at least pronunciation scoring information;
a memory for storing software instructions representing an articulation scoring engine, a duration scoring engine, an intonation scoring engine, and a plurality of reference utterances; and
a processor for executing said software instructions representing said scoring engines to derive thereby a pronunciation score for said received utterance;
said display device for displaying graphically a score field for each of a plurality of graphically displayed words of said reference utterance, wherein each score field has a length indicative of a duration of a corresponding one of a respective plurality of words of said user utterance, wherein each score field includes at least one numerical score for at least one speech-feature of said word of said user utterance.