Deep tagging background noises

1. A method for deep tagging a recording, the method comprising the steps of:

a computer recording audio of a communication between a plurality of participants, wherein the audio comprises speech from one or more of the plurality of participants;

the computer detecting a non-speech sound within the audio, wherein the non-speech sound is transmitted to the plurality of participants;

the computer automatically determining that the non-speech sound corresponds to a type of sound, and in response, automatically associating a descriptive term with a time of occurrence of the non-speech sound within the recorded audio to form a searchable tag, wherein the descriptive term includes a phonetic translation of the non-speech sound; and

the computer storing the searchable tag as metadata of the recorded audio.

2. The method of claim 1 , wherein the audio is received in a plurality of separate media streams each from a separate electronic device.

3. The method of claim 1 , further comprising the computer receiving an input from one or more of the plurality of participants to assist in tagging the non-speech sound.

4. The method of claim 1 , wherein the communication is a teleconference.

5. The method of claim 1 , wherein the descriptive term comprises an identifier of a user of an electronic device from which the non-speech sound originated.

6. The method of claim 1 , wherein the step of automatically associating the descriptive term with the time of the occurrence of the non-speech sound within the recorded audio comprises the computer obtaining the descriptive term from a mapping between the type of sound and one or more descriptive terms.

7. The method of claim 1 , further comprising the steps of:

the computer determining that a sound occurring within the audio has ceased at a point in time within the audio; and

the computer creating a searchable tag associated with the point in time within the audio indicating that the sound occurring within the audio has ceased.

8. The method of claim 1 , further comprising the steps of:

the computer receiving a search query;

the computer matching the search query to the searchable tag; and

the computer responding to the search query with the recorded audio and an indication of the time of occurrence of the non-speech sound.

9. The method of claim 8 , wherein the step of matching the search query to the searchable tag comprises:

the computer identifying a type of sound associated with a search term of the search query;

the computer identifying a plurality of terms associated with the identified type of sound; and

the computer searching the recorded audio for a searchable tag matching a term from the plurality of terms.

10. The method of claim 1 , further comprising the steps of:

the computer receiving a search query;

the computer matching the search query to the searchable tag; and

the computer responding to the search query with a link to a location in the recorded audio corresponding to the time of occurrence of the non-speech sound.

11. The method of claim 1 , wherein the step of determining that the non-speech sound corresponds to a type of sound, further comprises, the computer determining that the type of sound is in a list of preferences indicating that the type of sound should be tagged.

12. A computer program product for deep tagging a recording, the computer program product comprising:

one or more computer-readable storage media; and

program instructions stored on at least one of the one or more computer-readable storage media, the program instructions comprising:

program instructions to record audio of a communication between a plurality of participants, wherein the audio comprises speech from one or more of the plurality of participants;

program instructions to detect a non-speech sound within the audio, wherein the non-speech sound is transmitted to the plurality of participants;

program instructions to automatically determine that the non-speech sound corresponds to a type of sound, and in response, to automatically associate a descriptive term with a time of occurrence of the non-speech sound within the recorded audio to form a searchable tag, wherein the descriptive term includes a phonetic translation of the non-speech sound; and

program instructions to store the searchable tag as metadata of the recorded audio.

13. The computer program product of claim 12 , wherein the audio is in plurality of separate media streams received from a plurality of distinct electronic devices.

14. The computer program product of claim 12 , further comprising program instructions to receive an input from one or more of the plurality of participants to assist in tagging the non-speech sound.

15. The computer program product of claim 12 , wherein the communication is a teleconference.

16. The computer program product of claim 12 , wherein the descriptive term comprises an identifier of a user of an electronic device from which the non-speech sound originated.

17. The computer program product of claim 12 , wherein the program instructions to automatically associate the descriptive term with the time of the occurrence of the non-speech sound within the recorded audio comprise program instructions to obtain the descriptive term from a mapping between the type of sound and one or more descriptive terms.

18. The computer program product of claim 12 , further comprising program instructions, stored on at least one of the one or more computer-readable storage media, to:

determine that a sound occurring within the audio has ceased at a point in time within the audio; and

create a searchable tag associated with the point in time within the audio indicating that the sound occurring within the audio has ceased.

19. A system for deep tagging a recording, the system comprising:

one or more computer processors;

one or more computer-readable storage media;

program instructions stored on at least one of the one or more computer-readable storage media for execution by at least one of the one or more computer processors, the program instructions comprising:

program instructions to record audio of a communication between a plurality of participants, wherein the audio comprises speech from one or more of the plurality of participants;

program instructions to detect a non-speech sound within the audio, wherein the non-speech sound is transmitted to the plurality of participants;

program instructions to automatically determine that the non-speech sound corresponds to a type of sound, and in response, to automatically associate a descriptive term with a time of occurrence of the non-speech sound within the recorded audio to form a searchable tag, wherein the descriptive term includes a phonetic translation of the non-speech sound; and

program instructions to store the searchable tag as metadata of the recorded audio.

20. The system of claim 19 , wherein the audio is in a plurality of separate media streams received from a plurality of distinct electronic devices.

21. The system of claim 19 , further comprising program instructions to receive an input from one or more of the plurality of participants to assist in tagging the non-speech sound.

22. A method for playing recorded content, the method comprising the steps of:

a computer receiving a descriptive term or phrase associated with a searchable tag, wherein the searchable tag corresponds to a point-in-time at which a non-speech sound occurred during the recording of recorded content of a communication between a plurality of participants, wherein the descriptive term includes an automatically generated phonetic translation of the non-speech sound, wherein the non-speech sound was transmitted to the plurality of participants during the recording;

the computer navigating to a location in the recorded content corresponding to the point-in-time at which the non-speech sound occurred; and

the computer playing at least a portion of the recorded content starting at the point-in-time.

23. The method of claim 22 , wherein the step of receiving a descriptive term or phrase associated with the searchable tag comprises the computer receiving a selection of a displayed term, wherein the displayed term provides a reference to the location corresponding to the point-in-time.

24. The method of claim 22 , further comprising:

prior to the step of navigating to the location, the computer identifying the searchable tag and the point-in-time.

25. The method of claim 22 , wherein the step of receiving a descriptive term or phrase associated with the searchable tag comprises:

the computer receiving a search query including the descriptive term or phrase; and

the computer searching the recorded content for a match between the descriptive term or phrase and a term or phrase included in the searchable tag.