Speech recognition incorporating a priori probability weighting factors
First Claim
Patent Images
1. A method of speech recognition comprising the steps of:
- comparing a portion of an unknown utterance with reference models to generate a measure of similarity;
repetitively comparing further portions of the unknown utterance with reference models to generate, for each of a plurality of allowable sequences of reference models defined by stored data defining such sequences, accumulated measures of similarity including contributions from previously generated measures obtained from comparison of one or more earlier portions of the utterance with a reference model or models in the respective allowable sequence; and
weighting the accumulated measures in accordance with predetermined weighting factors representing an a priori probability for each of the allowable sequences wherein the weighting step is performed by weighting each computation of a measure or accumulated measure for a partial sequence by combined values of the weighting factors for each of the allowable sequences which commences with that partial sequence, modified by any such combined values of the weighting factors applied to a measure generated in respect of a shorter sequence with which that partial sequence commences.
1 Assignment
0 Petitions
Accused Products
Abstract
A recognizer is provided with a priori probability values (e.g., from some previous recognition) indicating how likely the various words of the recognizer'"'"'s vocabulary are to occur in the particular context, and recognition "scores" are weighted by these values before a result (or results) is chosen. The recognizer also employs "pruning" whereby low-scoring partial results are discarded, so as to speed the recognition process. To avoid premature pruning of the more likely words, probability values are applied before the pruning decisions are made. A method of applying these probability values is described.
-
Citations
12 Claims
-
1. A method of speech recognition comprising the steps of:
-
comparing a portion of an unknown utterance with reference models to generate a measure of similarity; repetitively comparing further portions of the unknown utterance with reference models to generate, for each of a plurality of allowable sequences of reference models defined by stored data defining such sequences, accumulated measures of similarity including contributions from previously generated measures obtained from comparison of one or more earlier portions of the utterance with a reference model or models in the respective allowable sequence; and weighting the accumulated measures in accordance with predetermined weighting factors representing an a priori probability for each of the allowable sequences wherein the weighting step is performed by weighting each computation of a measure or accumulated measure for a partial sequence by combined values of the weighting factors for each of the allowable sequences which commences with that partial sequence, modified by any such combined values of the weighting factors applied to a measure generated in respect of a shorter sequence with which that partial sequence commences. - View Dependent Claims (2, 3)
-
-
4. Speech recognition apparatus comprising:
-
storage means for storing data relating to reference models representing utterances and data defining allowable sequences of reference models; comparing means to repetitively compare portions of an unknown utterance with reference models to generate, for each of a plurality of allowable sequences of reference models defined by stored data defining such sequences, accumulated measures of similarity including contributions from previously generated measures obtained from comparison of one or more earlier portions of the utterance with a reference model or models in the respective allowable sequence; and weighting means operable to weight the accumulated measures in accordance with predetermined weighting factors representing an a priori probability for each of the allowable sequences wherein the weighting means is operable to weight a measure or accumulated measure for a partial sequence by combined values of the weighting factors for each of the allowable sequences which commences with that partial sequence, modified by any such combined values of the weighting factors applied to a measure generated in respect of a shorter sequence with which that partial sequence commences. - View Dependent Claims (5, 6)
-
-
7. A method of assigning a weighting factor to each node of a speech recognition network representing a plurality of allowable sequences of reference models each allowable sequence having a predetermined weighting factor representing an a priori probability, said method comprising:
combining, for each node, the values of the predetermined weighting factor(s) for each of the allowable sequence(s) which commence with a partial sequence incorporating the node modified by any weighting factors applied to nodes representing a shorter sequence with which that partial sequence commences. - View Dependent Claims (8, 9, 10, 11, 12)
Specification