Mass-scale, user-independent, device-independent voice messaging system

• US 8,953,753 B2
• Filed: 10/31/2007
• Issued: 02/10/2015
• Est. Priority Date: 02/10/2006
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Doulton, Daniel Michael
• Primary Examiner(s): King, Simon
• Application Number:
  US11/931,986
• Publication Number:
  US 20080162132A1
• Time in Patent Office: 2,659 Days
• Field of Search: 704/235, 704/231, 704/9, 704/270, 369/26.01, 379/26.01, 379/88.01, 379/93.15
• US Class Current: 379/88.01
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: H04M 2201/60 Medium conversion
• CPC Class Codes: H04M 3/4936 Speech interaction details speech recognition per se G10L15/00
• CPC Class Codes: H04M 3/5183 Call or contact centers with computer-telephony arrangements
• CPC Class Codes: H04M 3/53333 Message receiving aspects

Abstract

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 optimise 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.

Claims

1. A voice messaging system for converting an audio voice message from a caller into text, the voice messaging system comprising:

a plurality of conversion resources for converting the audio voice message into the text for an intended recipient, the plurality of conversion resources comprising;

at least one automatic speech recognition (ASR) system to automatically recognize at least some of the audio voice message and generate a plurality of candidate words or phrases; and

a computer implemented lattice sub-system that generates a lattice of possible words or phrases, enabling an operator to view one or more candidate words or phrases and to either select one of the one or more candidate words or phrases, or, by entering one or more characters of a different word or phrase, to trigger the lattice sub-system to provide at least one alternative word or phrase, wherein the lattice sub-system automatically differentiates between parts of the message based on whether the lattice sub-system determines parts of the message to be important or unimportant.

2. The system of claim 1 in which the lattice sub-system receives inputs from a sub-system that handles call-pair history information.

3. The system of claim 1 in which the lattice sub-system receives inputs from conversion resources.

4. The system of claim 3 in which the conversion resources analyze a converted word or phrase against an on-line corpus of knowledge.

5. The system of claim 4 in which the automatic speech recognition system utilizes the internet, as accessed by a search engine.

6. The system of claim 5 in which the automatic speech recognition system utilizes a search engine database.

7. The system of claim 1 in which the lattice sub-system receives inputs from a context sub-system that has knowledge of the context of a message.

8. The system of claim 1 in which the lattice sub-system learns, from the human operator inputs, likely words or phrases corresponding to a sound pattern.

9. The system of claim 1 in which the operator is required to select only a single key to accept a word or phrase.

10. The system of claim 1 in which the lattice sub-system automatically provides capitalization and punctuation.

11. The system of claim 1 in which the lattice sub-system can propose candidate numbers, real nouns, web addresses, e-mail addresses, physical addresses or location information.

12. The system of claim 1 in which unimportant parts of the message are confirmed by the operator as belonging to a class proposed by the lattice sub-system and are then converted solely by a machine ASR engine.

13. The system of claim 1 in which the operator can speak the correct word to the conversion system, which then automatically transcribes it.

14. The system of claim 1 in which the audio voice message is 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 in which 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 a display on a screen.

16. The system of claim 1 in which 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 1 in which the audio voice message is converted to text format and sent as a text message.

18. The system of claim 1 in which the audio voice message is converted to text format and sent as an email message.

19. The system of claim 1 in which the audio voice message is converted to text format and sent as a note or memo, by email or text, to an originator of the message.

20. The system of claim 1 further comprising a mobile telephone network.

21. The system of claim 1 further comprising a mobile telephone for displaying the text converted from the audio voice message.

22. The system of claim 1 further comprising a computer display screen for displaying the text converted from the audio voice message.