Method and System for Automatically Providing Linguistic Formulations that are Outside a Recognition Domain of an Automatic Speech Recognition System

• US 20080270129A1
• Filed: 02/17/2005
• Published: 10/30/2008
• Est. Priority Date: 02/17/2005
• Status: Active Grant

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: Loquendo SpA (Microsoft Corporation)
• Inventors: Colibro, Daniele, Vair, Claudio, Fissore, Luciano, Popovici, Cosmin
• Granted Patent: US 9,224,391 B2
• Time in Patent Office: Days
• US Class Current: 704/236
• CPC Class Codes: G10L 15/00 Speech recognition G10L17/00 takes precedence
• CPC Class Codes: G10L 15/06 Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice G10L15/14 takes precedence
• CPC Class Codes: G10L 15/187 Phonemic context, e.g. pronunciation rules, phonotactical constraints or phoneme n-grams
• CPC Class Codes: G10L 15/19 Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules

Abstract

A method for automatically providing a hypothesis of a linguistic formulation that is uttered by users of a voice service based on an automatic speech recognition system and that is outside a recognition domain of the automatic speech recognition system. The method includes providing a constrained and an unconstrained speech recognition from an input speech signal, identifying a part of the constrained speech recognition outside the recognition domain, identifying a part of the unconstrained speech recognition corresponding to the identified part of the constrained speech recognition, and providing the linguistic formulation hypothesis based on the identified part of the unconstrained speech recognition.

Claims

1-17. -17. (canceled)

18. A method for automatically providing a hypothesis of a linguistic formulation that is uttered by a user of an automatic voice service based on an automatic speech recognition system and that is outside a recognition domain of said automatic speech recognition system, comprising:

providing a constrained speech recognition and an unconstrained speech recognition from an input speech signal;

identifying a part of said constrained speech recognition outside said recognition domain;

identifying a part of said unconstrained speech recognition corresponding to said identified part of said constrained speech recognition; and

providing said linguistic formulation hypothesis based on said identified part of said unconstrained speech recognition.

19. The method as claimed in claim 18, wherein identifying a part of said constrained speech recognition outside said recognition domain comprises:

computing confidence measures for different parts of said constrained speech recognition; and

identifying said part of said constrained speech recognition outside said recognition domain based on said confidence measures.

20. The method as claimed in claim 19, wherein said confidence measures are computed for phonemes of said constrained speech recognition.

21. The method as claimed in claim 18, wherein identifying said part of said constrained speech recognition outside said recognition domain based on said confidence measures comprises:

identifying parts of said constrained speech recognition with confidence measures that meet a given criterion.

22. The method as claimed in claim 21, wherein identifying parts of said constrained speech recognition with confidence measures that meet a given criterion comprises:

computing instantaneous confidence scores as a temporal average of said confidence measures within a moving window; and

identifying parts of said constrained speech recognition with instantaneous confidence scores that meet a first relation.

23. The method as claimed in claim 22, wherein each instantaneous confidence score (C_ist(t)) is computed according to the following formula:

$C_{\mathrm{ist}}<br><br>\left(t\right)=\frac{1}{2<br><br>T+1}<br><br>\underset{t=-n-T}{\overset{n+T}{\sum <br><br>}}<br><br>\mathrm{Conf}<br><br>\left(t\right)$

wherein (Conf(t)) is said confidence measure, and 2T+1 is width of said moving window centered at time t.

24. The method as claimed in claim 23, wherein said first relation is defined by said instantaneous confidence scores being lower than a given threshold.

25. The method as claimed in claim 18, wherein identifying a part of said unconstrained speech recognition corresponding to said identified part of said constrained speech recognition comprises:

identifying a part of said input speech signal corresponding to said identified part of said constrained speech recognition; and

identifying a part of said unconstrained speech recognition corresponding to said identified part of said input speech signal.

26. The method as claimed in claim 18, further comprising:

deleting any silences at the start or at the end of the said identified part of said unconstrained speech recognition.

27. The method as claimed in claim 18, further comprising:

saving said identified part of said unconstrained speech recognition in a database of recognitions outside said recognition domain.

28. The method as claimed in claim 27, wherein said identified part of said unconstrained speech recognition is saved in said database of recognitions outside said recognition domain if its length meets a second relation.

29. The method as claimed in claim 28, wherein said second relation is defined by the length of said identified part of said unconstrained speech recognition being within a defined range.

30. The method as claimed in claim 27, further comprising:

processing said database of recognitions outside said recognition domain to provide said hypothesis of linguist formulation that is outside said recognition domain.

31. The method as claimed in claim 18, wherein said recognition domain comprises a recognition grammar and/or a language model.

32. A system for automatically providing hypothesis of linguistic formulations that are uttered by users of an automatic voice service based on an automatic speech recognition system and that are outside a recognition domain of the automatic speech recognition system, said system being configured to implement the method according to claim 18.

33. A computer program product comprising a computer program code, capable when loaded in a processing system, of implementing the method according to claim 18.

34. An automatic voice service based on an automatic speech recognition system, comprising:

receiving an input speech signal;

performing an automatic speech recognition based on said input speech signal; and

providing a hypothesis of a linguistic formulation that is uttered by a user of said automatic voice service and that is outside a recognition domain of said automatic speech recognition system, wherein said hypothesis is automatically provided by implementing the method of claim 18.