Method for collecting and storing annotations associated to a voice audio data
Present invention refers to a method for collecting, organizing and storing annotations associated to a voice audio data. The method comprises providing the voice audio data; transcribing said voice audio data into text data; then, identifying in the text data a piece of information according to a pattern previously set; generating automatically an annotation containing the piece of information identified; assigning automatically a level of relevance for the annotation; asking a user for confirming the automatically assigned level of relevance; if the user does not confirm the automatically assigned level of relevance, assigning a second level of relevance instead of the automatically assigned according to a user input; and storing the annotation associated to the level of relevance assigned. A user can access later to these annotations to recall a phone call conversation or a voice message.
1. A computer-implemented method for collecting, organizing and storing annotations associated to a voice audio data characterized by the steps of:
a) providing the voice audio data;
b) transcribing said voice audio data into text data;
c) identifying at least one text pattern from the text data according to a pattern previously set;
d) generating automatically an annotation containing the text pattern identified;
e) assigning automatically a level of relevance for the annotation;
f) asking a user for confirming the automatically assigned level of relevance;
g) if the user does not confirm the automatically assigned level of relevance, assigning a second level of relevance instead of the automatically assigned according to a user input;
h) storing the annotation associated to the level of relevance assigned.
2. The method according to claim 1 further comprising a user generating an annotation manually.
3. The method according to claim 2 , wherein there are three levels of relevance: a first level of relevance corresponding to annotations manually generated by a user and automatically generated annotations which level of relevance is reassigned to first level by a user, and automatically generated annotations which level of relevance is confirmed as first level by a user; a second level of relevance corresponding to automatically generated annotations which level of relevance is reassigned to second level by a user, and automatically generated annotations which level of relevance is confirmed as second level by a user; and a third level of relevance corresponding to the whole transcription of the voice audio data.
4. The method according to claim 2 , wherein the voice audio data is derived from a phone call conversation or a voice message.
5. The method according to claim 4 further comprising grouping the annotations according to the level of relevance assigned.
6. The method according to claim 5 , wherein there are three levels of relevance: a first level of relevance corresponding to annotations manually generated by a user and automatically generated annotations which level of relevance is reassigned to first level by a user, and automatically generated annotations which level of relevance is confirmed as first level by a user; a second level of relevance corresponding to automatically generated annotations which level of relevance is reassigned to second level by a user, and automatically generated annotations which level of relevance is confirmed as second level by a user; and a third level of relevance corresponding to the whole transcription of the voice audio data.
7. The method according to claim 6 further comprising providing data related to a context of the voice audio data.
8. The method according to claim 7 further comprising running the steps of the method in a mobile telephone.
9. The method according to claim 1 , wherein the voice audio data is derived from a phone call conversation or a voice message.
10. The method according to claim 9 , wherein the phone call conversation or voice message is displayed associated to the annotation stored.
11. The method according to claim 1 further comprising grouping the annotations according to the level of relevance assigned.
12. The method according to claim 11 wherein the groups of annotations are displayed according to a layer scheme, referring each layer to a different level of relevance.
13. The method according to claim 1 further comprising providing data related to a context of the voice audio data.
14. The method according to claim 13 wherein the context comprises a selection of at least one of temporal data, geographical data, GPS data, accelerometer data or to name of the caller.
15. The method according to claim 1 , wherein the text patterns comprise text data being numbers, question adverbs, proper names or geographical places.
16. The method according to claim 1 , wherein the voice audio data is provided by a telecommunication network.
17. The method according to claim 1 further comprising uploading the voice audio data to a server.
18. The method according to claim 1 further comprising running the steps of the method in a mobile telephone.
19. A computer program product comprising computer program code adapted to perform the method according to claim 1 when said program code is executed on a computer, a digital signal processor, a field-programmable gate array, an application-specific integrated circuit, a micro-processor, a micro-controller, or any other form of programmable hardware.
20. A digital data storage medium storing a computer program product comprising instructions causing a computer executing the program, to perform all steps of a method according to claim.