Mass-scale, user-independent, device-independent voice messaging system
View Patent ↗A mass-scale, user-independent, device-independent, voice messaging system that converts unstructured voice messages into text for display on a screen is disclosed. The system comprises (i) computer implemented sub-systems and also (ii) a network connection to human operators providing transcription and quality control; the system being adapted to optimize the effectiveness of the human operators by further comprising 3 core sub-systems, namely (i) a pre-processing front end that determines an appropriate conversion strategy; (ii) one or more conversion resources; and (iii) a quality control sub-system.
1. A voice messaging system for converting an audio voice message from a caller to text, the voice messaging system comprising:
at least one automatic speech recognition (ASR) resource; and
a computer implemented context sub-system configured to:
use context information about the context of the audio voice message or a part of the audio voice message to limit the vocabulary used by the at least one ASR resource to improve conversion accuracy of the at least one ASR resource in converting at least a portion of the audio voice message to text; and
a text output device that outputs the text to the intended recipient.
2. The system of claim 1 , wherein the context information comprises a caller ID or a recipient ID.
3. The system of claim 1 , wherein the context information comprises a call-pair history.
4. The system of claim 1 , wherein the context information comprises a time or day associated with the audio voice message.
5. The system of claim 1 , wherein the context information comprises location data associated with the caller or the intended recipient.
6. The system of claim 1 , wherein the context information comprises personal information management data of the caller or the intended recipient.
7. The system of claim 1 , wherein the context information comprises a message type.
8. The system of claim 1 , wherein the context information comprises information from an online corpus of knowledge.
9. The system of claim 1 , wherein the context information comprises presence data.
10. The system of claim 1 , wherein the context information comprises a speech density of the audio voice message.
11. The system of claim 1 , wherein the context information is a speech quality of the audio voice message.
12. The system of claim 1 , wherein the context information of the audio voice message is extracted by the context sub-system and fed-forward to a downstream sub-system that uses the context information to improve conversion accuracy.
13. The system of claim 12 , wherein the downstream sub-system is a quality monitoring and control sub-system.
14. The system of claim 1 , wherein the audio voice message is a voicemail intended for a mobile telephone and the audio voice message is converted to text and sent to that mobile telephone.
15. The system of claim 1 , wherein the audio voice message is intended for an instant messaging service and the audio voice message is converted to text and sent to an instant messaging service for display on a screen.
16. The system of claim 1 , wherein the audio voice message is intended for a web service and the audio voice message is converted to text and sent to a server for display as part of the web service.
17. The system of claim 7 , wherein the message type is a voice mail, a spoken text, an instant message, a blog entry, an email, a memo or a note.
18. A method for converting an audio voice message from a caller to text using at least one automatic speech recognition (ASR) resource, the method comprising:
using context information about the context of the audio voice message or a part of the audio voice message to limit a vocabulary used by the at least one ASR resource to improve conversion accuracy of the at least one ASR resource in converting at least a portion of the audio voice message to text; and
outputting the text to an intended recipient.
19. The method of claim 18 , wherein the context comprises a caller ID or a recipient ID.
20. The method of claim 18 , wherein the context information comprises a call-pair history.
21. The method of claim 18 , wherein the context information comprises location data associated with the caller or intended recipient.
22. The method of claim 18 , wherein the context information comprises personal information management data of the caller or intended recipient.
23. The method of claim 18 , wherein the context information comprises a message type.
24. The method of claim 18 , wherein the context information comprises information from an online corpus of knowledge.