SPEECH RECOGNITION LEARNING SYSTEM AND METHOD
First Claim
1. A speech recognition learning system for improved speech recognition comprising:
- a speech optimizing system configured to perform the following functions, not necessarily in the sequence listed;
(A) receive a first stimulus data package including one or more spoken utterances comprising at least one phoneme transmitted from a speech receiving device and contextual information relating to a state in which the one or more utterances is spoken;
(B) retrieve a plurality of first result data packages including a plurality of stored spoken utterances and stored contextual information associated with the plurality of stored spoken utterances relating to a state in which the utterance was spoken;
(C) determine whether the first stimulus data package at least partially requires improvement, based on at least one of the plurality of retrieved first result data packages;
(D) generate a second stimulus data package based on the determination of whether the first stimulus data package at least partially requires improvement;
(E) receive a plurality of first speech recognition implementation rules for implementing the second stimulus data package, the plurality of first speech recognition implementation rules being associated with the contextual information;
(F) determine whether the second stimulus data package at least partially requires further improvement based at least in part on one or more of the plurality of first speech recognition implementation rules wherein the one or more of the plurality of first speech recognition implementation rules are based on the contextual information of the second stimulus data package; and
(G) based on the determination, generate one or more second speech recognition implementation rules for improved speech recognition.
1 Assignment
0 Petitions
Accused Products
Abstract
One or more embodiments include a speech recognition learning system for improved speech recognition. The learning system may include a speech optimizing system. The optimizing system may receive a first stimulus data package including spoken utterances having at least one phoneme, and contextual information. A number of result data packages may be retrieved which include stored spoken utterances and contextual information. A determination may be made as to whether the first stimulus data package requires improvement. A second stimulus data package may be generated based on the determination. A number of speech recognition implementation rules for implementing the second stimulus data package may be received. The rules may be associated with the contextual information. A determination may be made as to whether the second stimulus data package requires further improvement. Based on the determination, one or more additional speech recognition implementation rules for improved speech recognition may be generated.
281 Citations
25 Claims
-
1. A speech recognition learning system for improved speech recognition comprising:
a speech optimizing system configured to perform the following functions, not necessarily in the sequence listed; (A) receive a first stimulus data package including one or more spoken utterances comprising at least one phoneme transmitted from a speech receiving device and contextual information relating to a state in which the one or more utterances is spoken; (B) retrieve a plurality of first result data packages including a plurality of stored spoken utterances and stored contextual information associated with the plurality of stored spoken utterances relating to a state in which the utterance was spoken; (C) determine whether the first stimulus data package at least partially requires improvement, based on at least one of the plurality of retrieved first result data packages; (D) generate a second stimulus data package based on the determination of whether the first stimulus data package at least partially requires improvement; (E) receive a plurality of first speech recognition implementation rules for implementing the second stimulus data package, the plurality of first speech recognition implementation rules being associated with the contextual information; (F) determine whether the second stimulus data package at least partially requires further improvement based at least in part on one or more of the plurality of first speech recognition implementation rules wherein the one or more of the plurality of first speech recognition implementation rules are based on the contextual information of the second stimulus data package; and (G) based on the determination, generate one or more second speech recognition implementation rules for improved speech recognition. - View Dependent Claims (2, 3, 4, 5, 6)
-
7. A speech optimizing system comprising:
-
(I) a stimulus data package receiver for receiving a first stimulus data package including one or more spoken utterances comprising at least one phoneme transmitted from a speech receiving device and contextual information relating to a state in which the one or more utterances is spoken; (II) a result data package retriever for retrieving a plurality of first result data packages including a plurality of stored spoken utterances and stored contextual information associated with the plurality of stored spoken utterances relating to a state in which the utterance was spoken; (III) at least one stimulus data package generator for; determining whether the first stimulus data package at least partially requires improvement, based on at least one of the plurality of retrieved first result data packages; and generating a second stimulus data package based on the determination of whether the first stimulus data package at least partially requires improvement; (IV) at least one speech improvement processor for; receiving a plurality of first speech recognition implementation rules for implementing the second stimulus data package, the plurality of first speech recognition implementation rules being associated with the contextual information; and determining whether the second stimulus data package at least partially requires further improvement based at least in part on one or more of the plurality of first speech recognition implementation rules, wherein the one or more of the plurality of first speech recognition implementation rules are based on the contextual information of the second stimulus data package; and (V) an implementation rules generator for generating, based on the determination from the speech improvement processor, one or more second speech recognition implementation rules for improved speech recognition. - View Dependent Claims (8, 9, 10, 11, 12, 13)
-
-
14. A speech recognition learning system for improved speech recognition comprising:
-
(a) means for receiving a first stimulus data package including one or more spoken utterances comprising at least one phoneme transmitted from a speech receiving device and contextual information relating to a state in which the one or more utterances is spoken; (b) means for retrieving a plurality of first result data packages including a plurality of stored spoken utterances and stored contextual information associated with the plurality of stored spoken utterances relating to a state in which the utterance was spoken; (c) means for determining whether the first stimulus data package at least partially requires improvement, based on at least one of the plurality of retrieved first result data packages; (d) means for generating a second stimulus data package based on the determination of whether the first stimulus data package at least partially requires improvement; (e) means for receiving a plurality of first speech recognition implementation rules for implementing the second stimulus data package, the plurality of first speech recognition implementation rules being associated with the contextual information; (f) means for determining whether the second stimulus data package at least partially requires further improvement based at least in part on one or more of the plurality of first speech recognition implementation rules wherein the one or more of the plurality of first speech recognition implementation rules are based on the contextual information of the second stimulus data package; and (g) based on the determination, means for generating one or more second speech recognition implementation rules for improved speech recognition. - View Dependent Claims (15, 16, 17, 18, 19)
-
-
20. A computer-implemented speech recognition learning method for improved speech recognition, the method comprising the following steps, not necessarily practiced in the sequence listed:
-
(1) transmitting one or more utterances comprising at least one phoneme at a speech receiving device; (2) receiving a first stimulus data package including one or more spoken utterances comprising at least one phoneme transmitted from a speech receiving device and contextual information relating to a state in which the one or more utterances is spoken; (3) retrieving a plurality of first result data packages including a plurality of stored spoken utterances and stored contextual information associated with the plurality of stored spoken utterances relating to a state in which the utterance was spoken; (4) determining whether the first stimulus data package at least partially requires improvement, based on at least one of the plurality of retrieved first result data packages; (5) generating a second stimulus data package based on the determination of whether the first stimulus data package at least partially requires improvement; (6) receiving a plurality of first speech recognition implementation rules for implementing the second stimulus data package, the plurality of first speech recognition implementation rules being associated with the contextual information; (7) determining whether the second stimulus data package at least partially requires further improvement based at least in part on one or more of the plurality of first speech recognition implementation rules wherein the one or more of the plurality of first speech recognition implementation rules are based on the contextual information of the second stimulus data package; and (8) based on the determination, generating one or more second speech recognition implementation rules for improved speech recognition. - View Dependent Claims (21, 22, 23, 24, 25)
-
Specification