Speech learning apparatus and method
View Patent ↗According to one embodiment, a speech learning apparatus includes a detection unit, a first calculation unit, a generation unit, an addition unit and a speech synthesis unit. The first calculation unit calculates a score indicating a degree of emphasis of a keyword based on a type of the marker and a manner of selecting the keyword. The generation unit generates a synthesis parameter to determine a degree of reading of the keyword in accordance with the score and the type of the marker. The addition unit adds to the keyword a tag for reading the keyword in accordance with the synthesis parameter. The speech synthesis unit generates synthesized speech obtained by synthesizing speech of the keyword in accordance with the tag.
1. A speech learning apparatus comprising:
a processor, programmed to
detect a keyword corresponding to a character string selected from a text;
calculate a score indicating a degree of emphasis of the keyword based on a manner of selecting the keyword;
generate a synthesis parameter to determine a degree of reading of the keyword in accordance with the score;
add to the keyword a tag for reading the keyword in accordance with the synthesis parameter;
generate synthesized speech obtained by synthesizing speech of the keyword in accordance with the tag;
calculate a social score indicating a score of the keyword selected by one or more other users different from the user; and
calculate an integration score using the score and the social score,
wherein the synthesis parameter is generated in accordance with the integration score.
2. The apparatus according to claim 1 , wherein the synthesis parameter is generated such that as the score decreases, the reading becomes closer to that in a case where the tag is not added.
3. The apparatus according to claim 1 , further comprising a marker that is used for the manner of selecting the keyword, the reading varies with a type of the marker.
4. The apparatus according to claim 1 , wherein the processor is further programmed to
give a question relating to a keyword to the user; and
calculate a correct answer rate based on an answer to the question from the user, to generate a learning history including information associated with the question and the correct answer rate,
wherein the score indicating the degree of emphasis of the keyword calculates the score which becomes lower as the correct answer rate increases, in accordance with the learning history.
5. The apparatus according to claim 4 , wherein the processor is further programmed to
estimate an attribute of the keyword,
wherein the giving of the question relating to the keyword to the user converts a first character string indicating the keyword into a second character string indicating the attribute, and
wherein the generated synthesized speech obtained by synthesizing speech of the keyword synthesizes speech of the second character string.
6. A speech learning method comprising:
detecting a keyword corresponding to a character string selected from text from a text acquisition unit comprising a stylus or a keyboard;
calculating a score indicating a degree of emphasis of the keyword based on a manner of selecting the keyword;
generating a synthesis parameter to determine a degree of reading of the keyword in accordance with the score;
adding to the keyword a tag for reading the keyword in accordance with the synthesis parameter;
generating synthesized speech obtained by synthesizing speech of the keyword in accordance with the tag;
calculating a social score indicating a score of the keyword selected by one or more other users different from the user; and
calculating an integration score using the score and the social score,
wherein the generating the synthesis parameter generates the synthesis parameter in accordance with the integration score.
7. A non-transitory computer readable medium including computer executable instructions, wherein the instructions, when executed by a processor, cause the processor to perform a method comprising:
detecting a keyword corresponding to a character string selected from text;
calculating a score indicating a degree of emphasis of the keyword based on a manner of selecting the keyword;
generating a synthesis parameter to determine a degree of reading of the keyword in accordance with the score;
adding to the keyword a tag for reading the keyword in accordance with the synthesis parameter;
generating synthesized speech obtained by synthesizing speech of the keyword in accordance with the tag;
calculating a social score indicating a score of the keyword selected by one or more other users different from the user; and
calculating an integration score using the score and the social score,
wherein the generating the synthesis parameter generates the synthesis parameter in accordance with the integration score.