Speech recognition in consumer electronic products
First Claim
1. In an electronic system wherein features of spoken utterances are analyzed by a programmable pattern recognition system to provide recognition results, a method comprising the steps of:
- coupling said electronic system to a source external to said electronic system;
retrieving a first set of recognition programming information associated with a first recognition word set for said pattern recognition system from said external source;
programming said pattern recognition system with said retrieved first set of recognition programming information to recognize a first set of words in the first recognition word set, wherein said pattern recognition system provides a first set of recognition results responsive to said first set of words;
in response to the first set of recognition results, selectively retrieving from said external source a second set of recognition programming information associated with a second recognition word set for said pattern recognition system, wherein the selectively retrieved second set of recognition programming is selected based on the first set of recognition results; and
reprogramming said pattern recognition system with said selectively retrieved second set of recognition programming information to recognize a second set of words in the second recognition word set, wherein said pattern recognition system provides a second set of recognition results responsive to the second set of words.
0 Assignments
0 Petitions
Accused Products
Abstract
A method and apparatus are described that allow inexpensive speech recognition in applications where this capability is not otherwise feasible because of cost or technical reasons, or because of inconvenience to the user. A relatively simple speaker independent recognition algorithm, capable of recognizing a limited number of utterances at any one time, is associated with the base unit of an electronics product. To function, the product requires information from an external medium and this medium also provides the data required to recognize several sets of utterances pertinent to other information provided by the external medium.
312 Citations
35 Claims
-
1. In an electronic system wherein features of spoken utterances are analyzed by a programmable pattern recognition system to provide recognition results, a method comprising the steps of:
-
coupling said electronic system to a source external to said electronic system;
retrieving a first set of recognition programming information associated with a first recognition word set for said pattern recognition system from said external source;
programming said pattern recognition system with said retrieved first set of recognition programming information to recognize a first set of words in the first recognition word set, wherein said pattern recognition system provides a first set of recognition results responsive to said first set of words;
in response to the first set of recognition results, selectively retrieving from said external source a second set of recognition programming information associated with a second recognition word set for said pattern recognition system, wherein the selectively retrieved second set of recognition programming is selected based on the first set of recognition results; and
reprogramming said pattern recognition system with said selectively retrieved second set of recognition programming information to recognize a second set of words in the second recognition word set, wherein said pattern recognition system provides a second set of recognition results responsive to the second set of words. - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
-
8. In a base unit wherein features of spoken utterances are analyzed by a programmable speaker-independent pattern recognition system to provide recognition results, a method comprising the steps of:
-
retrieving a first set of recognition programming information associated with a first recognition word set for said pattern recognition system from a remote source external to said base unit;
programming said pattern recognition system with said retrieved recognition programming information to recognize a first set of words in the first recognition word set, wherein said speaker-independent pattern recognition system provides a first set of recognition results responsive to said first set of words;
in response to the first set of recognition results, selectively retrieving from said remote external source a second set of recognition programming information associated with a second recognition word set for said pattern recognition system, wherein the selectively retrieved second set of recognition programming is selected based on the first set of recognition results; and
reprogramming said pattern recognition system with said retrieved second set of recognition programming information to recognize a second set of words in the second recognition word set, wherein said speaker-independent pattern recognition system provides a second set of recognition results responsive to said second set of words. - View Dependent Claims (9, 10, 11, 12, 13, 14, 15)
-
-
16. Apparatus for performing speaker independent speech recognition comprising:
-
a programmable pattern recognition system;
an interface, the interface retrieving first recognition programming information from a remote external source for programming said programmable pattern recognition system to recognize a first selected word vocabulary and generate a first recognition result when a first input is in the first selected word vocabulary, and in response to the first recognition result, selectively retrieving second recognition programming information from the remote external source for programming said programmable pattern recognition system to recognize a second selected word vocabulary and generate a second recognition result when a second input is in the second selected word vocabulary. - View Dependent Claims (17, 18, 19)
-
-
20. A speech recognition system comprising:
-
a microphone for receiving a first speech input signal and a second speech input signal, the first input signal being within a first recognition word set and the second input signal being within a second recognition word set;
a memory;
a programmable pattern recognition system coupled to the microphone and to the memory, the programmable pattern recognition system recognizing the first input signal when the memory is loaded with first recognition programming information associated with the first recognition word set, and recognizing the second input signal when the memory is loaded with second recognition programming information associated with the second recognition word set;
an interface circuit to couple the speech recognition system to a remote external source;
a pattern recognition programming system coupled to the programmable pattern recognition system and to the interface circuit;
wherein the pattern recognition programming system signals the interface circuit to retrieve the first recognition programming information from the remote external source into the memory to recognize the first speech input signal, and in response to recognizing the first speech input signal, the pattern recognition programming system signals the interface circuit to selectively retrieve the second recognition programming information from the remote external source into the memory to recognize the second speech input signal. - View Dependent Claims (21, 22, 23, 24, 25, 26, 27, 28)
-
-
29. In a base unit including a pattern recognition system, a method of recognizing spoken utterances comprising:
-
storing a plurality of sets of recognition programming information associated with a corresponding plurality of recognition word sets on an external medium, the plurality of sets of recognition programming information including a first and second set of recognition programming information corresponding to first and second recognition word sets;
retrieving the first set of recognition programming information associated with the first recognition word set for said pattern recognition system from the external medium to said base unit during a first time period, wherein the first set is selectively retrieved from the plurality of sets stored on the external medium;
programming said pattern recognition system with said retrieved first set of recognition programming information to recognize a first set of words in the first recognition word set;
prompting a user for a first speech utterance corresponding to the first recognition word set;
generating first recognition result in response to the first speech utterance;
in response to the first recognition result, selectively retrieving the second set of recognition programming information associated with the second recognition word set for said pattern recognition system from the external medium to said base unit during a second time period;
reprogramming said pattern recognition system with said retrieved second set of recognition programming information to recognize a second set of words in the second recognition word set;
prompting a user for a second speech utterance corresponding to the second recognition word set; and
generating a second recognition result in response to the second speech utterance. - View Dependent Claims (30, 31, 32, 33, 34, 35)
-
Specification