Automatic construction of unique signatures and confusable sets for database access
AssigneeIBM Corporation
InventorsBenoit Maison, Geoffrey G. Zweig
Life of this patent
Estimating the term…
Abstract
Methods and arrangements for facilitating database access in speech recognition. A plurality of possible subsequences corresponding to a database entry are ascertained, a record of such subsequences and their correspondence to database entries is created, and either or both of the following are carried out: unique signatures are ascertained via determining whether a subsequence corresponding to a given database entry does not also correspond to at least one other database entry; and/or multiple occurrences of a given subsequence are found, with corresponding database entries being grouped into a confusion set.
Claims19
A method of facilitating database access in speech recognition, said method comprising the steps of:
- ascertaining a plurality of possible subsequences corresponding to a database entry;
- creating a record of such subsequences and their correspondence to database entries;
- and
- at least one of:
- ascertaining unique signatures via determining whether a subsequence corresponding to a given database entry does not also correspond to at least one other database entry;
- and
- finding multiple occurrences of a given subsequence and grouping corresponding database entries into a confusion set.
An apparatus for facilitating database access in speech recognition, said apparatus comprising:
- an arrangement for ascertaining a plurality of possible subsequences corresponding to a database entry;
- an arrangement for creating a record of such subsequences and their correspondence to database entries;
- and
- at least one of:
- an arrangement for ascertaining unique signatures via determining whether a subsequence corresponding to a given database entry does not also correspond to at least one other database entry;
- and
- an arrangement for finding multiple occurrences of a given subsequence and grouping corresponding database entries into a confusion set.
A program storage device readable by machine, tangibly embodying a program of instructions executable by the machine to perform method steps for facilitating database access in speech recognition, said method comprising the steps of:
- ascertaining a plurality of possible subsequences corresponding to a database entry;
- creating a record of such subsequences and their correspondence to database entries;
- and
- at least one of:
- ascertaining unique signatures via determining whether a subsequence corresponding to a given database entry does not also correspond to at least one other database entry;
- and
- finding multiple occurrences of a given subsequence and grouping corresponding database entries into a confusion set.
Dependencies are inferred from the claim text.