System and method for automatically transcribing voicemail
View Patent ↗Disclosed herein are systems, computer-implemented methods, and tangible computer-readable media for automatically transcribing voicemail. The method includes receiving a plurality of voicemail messages from callers, identifying for each voicemail message in the plurality of voicemail messages a first frequency with which the respective caller leaves voicemails, identifying for each voicemail message in the plurality of voicemail messages a second frequency with which a user requests transcription of each voicemail, assigning a priority ranking to each voicemail message in the plurality of voicemail messages based on the respective first frequency and the respective second frequency, and transcribing untranscribed voicemail messages with a highest priority ranking. The method can include establishing a priority ranking threshold and repeatedly transcribing a next highest ranking untranscribed voicemail message until no further untranscribed voicemail messages remain above the priority ranking threshold.
1. A method comprising:
assigning, via a processor, a priority to each voicemail in a plurality of voicemails, wherein the priority is based on a transcription request frequency, to yield prioritized voicemails;
establishing a priority ranking threshold; and
repeatedly transcribing a next highest priority voicemail message from the prioritized voicemails until no further untranscribed voicemail messages remain above the priority ranking threshold.
2. The method of claim 1 , wherein the transcription request frequency is a frequency of transcription requests made by a recipient of the plurality of voicemails.
3. The method of claim 1 , further comprising building a voice model of a respective caller while transcribing voicemail messages.
4. The method of claim 1 , wherein assigning the priority to each voicemail message is further based on a user profile.
5. The method of claim 1 , further comprising generating speaker-specific syllable libraries while repeatedly transcribing the prioritized voicemails.
6. The method of claim 5 , further comprising:
receiving a text-based message from a speaker associated with a generated speaker-specific syllable library; and
generating an audible version of the text-based message based on the generated speaker-specific syllable library.
7. The method of claim 1 , wherein the transcribing of the next highest priority voicemail message occurs within a user-defined transcription window.
8. The method of claim 1 , wherein the priority which is assigned increases for voicemails older than a set amount of time.
9. A system comprising:
a processor; and
a computer-readable storage medium having instructions stored which, when executed by the processor, cause the processor to perform operations comprising:
assigning a priority to each voicemail in a plurality of voicemails, wherein the priority is based on a transcription request frequency, to yield prioritized voicemails;
establishing a priority ranking threshold; and
repeatedly transcribing a next highest priority voicemail message from the prioritized voicemails until no further untranscribed voicemail messages remain above the priority ranking threshold.
10. The system of claim 9 , wherein the transcription request frequency is a frequency of transcription requests made by a recipient of the plurality of voicemails.
11. The system of claim 9 , the computer-readable storage medium having additional instructions stored which, when executed by the processor, cause the processor to perform operations comprising building a voice model of a respective caller while transcribing voicemail messages.
12. The system of claim 9 , wherein assigning the priority to each voicemail message is further based on a user profile.
13. The system of claim 9 , the computer-readable storage medium having additional instructions stored which, when executed by the processor, cause the processor to perform operations comprising generating speaker-specific syllable libraries while repeatedly transcribing the prioritized voicemails.
14. The system of claim 13 , the computer-readable storage medium having additional instructions stored which, when executed by the processor, cause the processor to perform operations comprising:
receiving a text-based message from a speaker associated with a generated speaker-specific syllable library; and
generating an audible version of the text-based message based on the generated speaker-specific syllable library.
15. The system of claim 9 , wherein the transcribing of the next highest priority voicemail message occurs within a user-defined transcription window.
16. The system of claim 9 , wherein the priority which is assigned increases for voicemails older than a set amount of time.
17. A computer-readable storage device having instructions stored which, when executed by a computing device, cause the computing device to perform operations comprising:
assigning a priority to each voicemail in a plurality of voicemails, wherein the priority is based on a transcription request frequency, to yield prioritized voicemails;
establishing a priority ranking threshold; and
repeatedly transcribing a next highest priority voicemail message from the prioritized voicemails until no further untranscribed voicemail messages remain above the priority ranking threshold.
18. The computer-readable storage device of claim 17 , wherein the transcription request frequency is a frequency of transcription requests made by a recipient of the plurality of voicemails.
19. The computer-readable storage device of claim 17 , having additional instructions stored which, when executed by the computing device, cause the computing device to perform operations comprising building a voice model of a respective caller while transcribing voicemail messages.
20. The computer-readable storage device of claim 17 , wherein assigning the priority to each voicemail message is further based on a user profile.