Automated directory assistance system utilizing a heuristics model for predicting the most likely requested number

• US 5,987,408 A
• Filed: 12/16/1996
• Issued: 11/16/1999
• Est. Priority Date: 12/16/1996
• Status: Expired due to Term

• Current Assignee: Volt Delta Resources LLC (NewNet Communication Technologies LLC)
• Original Assignee: Nortel Networks Corporation
• Inventors: Gupta, Vishwa
• Primary Examiner(s): Hudspeth, David R.
• Assistant Examiner(s): SAX, ROBERT L
• Application Number:
  US08/767,503
• Time in Patent Office: 1,065 Days
• Field of Search: 704/231, 704/275
• US Class Current: 704/231
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 2015/228 of application context
• CPC Class Codes: H04M 1/271 controlled by voice recognition
• CPC Class Codes: H04M 2203/556 Statistical analysis and interpretation
• CPC Class Codes: H04M 3/4931 Directory assistance systems

Abstract

The invention relates to an automated directory assistance system that utilizes a heuristics model for predicting the most likely requested number. Each orthography link in the speech recognition dictionary pointing toward an entry in the white pages is associated with a data structure that provides a probability value of that link pointing toward the telephone number intended by the user on the basis of locality information specified by the user of the automated directory assistance system.

Claims

1. An automated directory assistance system comprising:

a speech recognition dictionary including;

a) a set of vocabulary items potentially recognizable on a basis of a spoken utterance by the user of said automated directory assistance system, each vocabulary item representing a name of an entity whose telephone number is potentially sought by the user, said set including a plurality of multi-entity vocabulary items, each of said multi-entity vocabulary items being representative of a plurality of entities having different telephone numbers;

b) a plurality of links associated with each multi-entity vocabulary item, each link being operative to derive the telephone number of a respective one of the entities represented by the multi-entity vocabulary item;

c) a plurality of data structures, each link of a multi-entity vocabulary item being associated with a respective data structure, each data structure comprising a plurality of data structure entries, each data structure entry establishing a correspondence between a locality information data element and a probability data element, said data structure permitting to derive a likelihood that the link associated to the data structure points to a telephone number sought by the user;

an input for receiving;

i) a first signal derived from a first spoken utterance spoken by a user of said automated directory assistance system, said spoken utterance being representative of a certain multi-entity vocabulary item;

ii) a second signal derived from a second spoken utterance spoken by a user of said automated directory assistance system, said second spoken utterance being representative of a certain locality data element;

a processing unit characterized by;

i) said processing unit being responsive to the first signal for selecting a certain multi-entity vocabulary item as being a match to the first spoken utterance;

ii) said processing unit being responsive to the second signal for selecting a certain locality data element as being a match to the second spoken utterance;

iii) said processing unit being operative to process the data structures associated with links of the multi-entity vocabulary item selected as being a match to the first spoken utterance to extract from the data structures the probability data elements corresponding to the certain locality data element selected as being a match to the second spoken utterance;

iv) said processing unit being operative for releasing through an output a signal representative of the telephone number derived from the link associated with the probability data element that is highest amongst the probability data elements extracted from the data structures associated with links of the multi-entity vocabulary item selected as being a match to the first spoken utterance.

2. An automated directory assistance system as defined in claim 1, wherein the locality information data elements in a given data structure are representative of localities characterized by geographical proximity.

3. A method for performing speech recognition in an automated directory assistance system, said method comprising the steps of:

providing a speech recognition dictionary, said speech recognition dictionary including;

a) a set of vocabulary items potentially recognizable on a basis of a spoken utterance by the user of said automated directory assistance system, each vocabulary item representing a name of an entity whose telephone number is potentially sought by the user, said set including a plurality of multi-entity vocabulary items, each of said multi-entity vocabulary items being representative of a plurality of entities having different telephone numbers;

b) a plurality of links associated with each multi-entity vocabulary item, each link being operative to derive the telephone number of a respective one of the entities represented by the multi-entity vocabulary item;

c) a plurality of data structures, each link of a multi-entity vocabulary item being associated with a respective data structure, each data structure comprising a plurality of data structure entries, each data structure entry establishing a correspondence between a locality information data element and a probability data element, said data structure permitting to derive a likelihood that the link associated to the data structure points to a telephone number sought by the user;

receiving a first signal derived from a first spoken utterance spoken by a user of said automated directory assistance system, said first spoken utterance being representative of a certain multi-entity vocabulary item;

receiving a second signal derived from a second spoken utterance spoken by a user of said automated directory assistance system, said second spoken utterance being representative of a certain locality data element;

processing the first signal and selecting a certain multi-entity vocabulary item as being a match to the first spoken utterance;

processing the second signal to select a certain locality data element as being a match to the second spoken utterance;

processing the data structures associated with links of the multi-entity vocabulary item selected as being a match to the first spoken utterance to extract from the data structures the probability data elements corresponding to the certain locality data element selected as being a match to the second spoken utterance;

releasing through an output a signal representative of the telephone number derived from the link associated with the probability data element that is highest amongst the probability data elements extracted from the data structures associated with links of the multi-entity vocabulary item selected as being a match to the first spoken utterance.

4. A method as defined in claim 3, further comprising the step of searching the data structure associated with each link of a given multi-entity vocabulary item to extract a likelihood and comparing the respective likelihoods of each of the links to select one of the links as being the most likely to point toward the telephone number sought by the user.

5. An automated directory assistance system as defined in claim 4, wherein the locality information data elements in a given data structure are representative of localities characterized by geographical proximity.

6. A machine readable storage medium containing a speech recognition dictionary for use in an automated directory assistance system that includes a speech recognition layer, said speech recognition dictionary including:

a set of vocabulary items potentially recognizable on a basis of a spoken utterance by a user of said automated directory assistance system, each vocabulary item representing a name of an entity whose telephone number is potentially sought by the user, said set including a plurality of multi-entity vocabulary items, each of said multi-entity vocabulary items being representative of a plurality of entities having different telephone numbers;

a plurality of links associated with each multi-entity vocabulary item, each link being operative to derive the telephone number of a respective one of the entities represented by the multi-entity vocabulary item;

a plurality of data structures, each link of a multi-entity vocabulary item being associated with a respective data structure, each data structure comprising a plurality of data structure entries, each data structure entry establishing a correspondence between a locality information data element and a probability data element, said data structure permitting to derive a likelihood that the link associated to the data structure points to a telephone number sought by the user, on a basis of a certain locality information data element.

7. An automated directory assistance system as defined in claim 6, wherein the locality information data elements in a given data structure are representative of localities characterized by geographical proximity.