Back to results
US 12,394,430 B2Granted
Method and apparatus with decoding in neural network for speech recognition
AssigneeSamsung Electronics Co., Ltd.
InventorsJinwoo Park, Min-Joong Lee, Jihyun Lee, Hoshik Lee
Life of this patent
Estimating the term…
Abstract
A decoding method includes receiving an input sequence corresponding to an input speech at a current time; and in a neural network (NN) for speech recognition, generating an encoded vector sequence by encoding the input sequence, determining reuse tokens from candidate beams of two or more previous times by comparing the candidate beams of the previous times, and decoding one or more tokens subsequent to the reuse tokens based on the reuse tokens and the encoded vector sequence.
Claims22
A decoding method, the method comprising:
- receiving an input sequence corresponding to an input speech at a current time;
- and
- in a neural network (NN) for speech recognition,
- generating an encoded vector sequence by encoding the input sequence,
- determining reuse tokens by determining whether substrings included in candidate beams of two or more previous times match, wherein the candidate beams of two or more previous times comprise different numbers of tokens, and
- decoding one or more tokens subsequent to the reuse tokens based on the reuse tokens and the encoded vector sequence,
- wherein the determining of the reuse tokens comprises:
- determining a reuse time of tokens at a current time n, being the current time, subsequent to a previous time n−1 subsequent to a previous time n−2 based on a comparison result between a candidate beam of the previous time n−2 and a candidate beam of the previous time n−1, wherein n is a natural number greater than or equal to “3”;
- and
- determining candidate beams accumulated up to the reuse time to be the reuse tokens.
7 more elements
A non-transitory computer-readable storage medium storing instructions that, when executed by a processor, configure the processor to execute a decoding method, the decoding method comprising:
- receiving an input sequence corresponding to an input speech at a current time;
- and
- in a neural network (NN) for speech recognition,
- generating an encoded vector sequence by encoding the input sequence,
- determining reuse tokens by determining whether substrings included in candidate beams of two or more previous times match, wherein the candidate beams of two or more previous times comprise different numbers of tokens, and
- decoding one or more tokens subsequent to the reuse tokens based on the reuse tokens and the encoded vector sequence,
- wherein the determining of the reuse tokens comprises:
- determining a reuse time of tokens at a current time n, being the current time, subsequent to a previous time n−1 subsequent to a previous time n−2 based on a comparison result between a candidate beam of the previous time n−2 and a candidate beam of the previous time n−1, wherein n is a natural number greater than or equal to “3”;
- and
- determining candidate beams accumulated up to the reuse time to be the reuse tokens.
7 more elements
A decoding apparatus with a neural network (NN) for speech recognition, the decoding apparatus comprising:
- a communication interface configured to receive an input sequence corresponding to an input speech at a current time;
- and
- a processor configured to use the NN to:
- generate an encoded vector sequence by encoding the input sequence;
- determine reuse tokens by determining whether substrings included in candidate beams of two or more previous times match, wherein the candidate beams of two or more previous times comprise different numbers of tokens;
- and
- decode one or more tokens subsequent to the reuse tokens based on the reuse tokens and the encoded vector sequence,
- wherein, for the determining of the reuse tokens, the processor is configured to
- determine a reuse time of tokens at a current time n, being the current time, subsequent to a previous time n−1 subsequent to a previous time n−2 based on a comparison result between a candidate beam of the previous time n−2 and a candidate beam of the previous time n−1, wherein n is a natural number greater than or equal to “3”, and
- determine candidate beams accumulated up to the reuse time to be the reuse tokens.
7 more elements
A decoding method, the method comprising:
- in a neural network (NN) for speech recognition,
- generating an encoded vector sequence by encoding an input sequence corresponding to an input speech at a current decoding time step,
- determining reuse tokens by determining a largest sequence of tokens matching between candidate beams of previous time steps and based on candidate beams having highest probabilities among the candidate beams, wherein the candidate beams of two or more previous times comprise different numbers of tokens, and
- decoding one or more tokens subsequent to the reuse tokens based on the reuse tokens and the encoded vector sequence,
- wherein the determining of the reuse tokens comprises:
- determining a reuse time of tokens at a current time n, being the current decoding time step, subsequent to a previous time n−1 subsequent to a previous time n−2 based on a comparison result between a candidate beam of the previous time n−2 and a candidate beam of the previous time n−1, wherein n is a natural number greater than or equal to “3”;
- and
- determining candidate beams accumulated up to the reuse time to be the reuse tokens.
5 more elements
Dependencies are inferred from the claim text.