Input generation for classifier

• US 10,540,963 B2
• Filed: 02/02/2017
• Issued: 01/21/2020
• Est. Priority Date: 02/02/2017
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Itoh, Nobuyasu, Kurata, Gakuto, Tachibana, Ryuki
• Primary Examiner(s): Roberts, Shaun
• Application Number:
  US15/422,507
• Publication Number:
  US 20180218736A1
• Time in Patent Office: 1,083 Days
• Field of Search: 704235
• CPC Class Codes: G10L 15/01 Assessment or evaluation of speech recognition systems
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 15/18 using natural language modelling
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 2015/0631 Creating reference templates; Clustering

Abstract

A computer-implemented method for generating an input for a classifier. The method includes obtaining n-best hypotheses which is an output of an automatic speech recognition (ASR) for an utterance, combining the n-best hypotheses horizontally in a predetermined order with a separator between each pair of hypotheses, and outputting the combined n-best hypotheses as a single text input to a classifier.

Claims

1. A computer-implemented method for improving performance of a speech recognition system, comprising:

generating a single text data structure for a classifier of a speech recognition system, including;

obtaining first n-best hypotheses as an output of a speech recognition task performed by automatic speech recognition (ASR) for an utterance received by the speech recognition system; and

combining the first n-best hypotheses horizontally in a predetermined order with a separator between each pair of n-best hypotheses to generate the single text data structure, wherein each separator is set based on a classification algorithm of the classifier of the speech recognition system as a symbol that is usable by the classifier of the speech recognition system; and

outputting the single text data structure as an input to the classifier to perform a classification task;

wherein the classifier is trained to perform the classification task based on a single training text data structure by;

obtaining source training data including a plurality of second n-best hypotheses and a transcription for each utterance from a database;

arranging the source training data with the transcription at a head or at an end of the second n-best hypotheses depending on the predetermined order to generate the single training text data structure; and

outputting the single training text data structure to the classifier.

2. The method according to claim 1, wherein each of the first and second n-best hypotheses is associated with a corresponding confidence score, and wherein the predetermined order is determined based on the confidence scores.

3. The method according to claim 1, wherein each separator is selected from the group consisting of:

EOS and <

/s>

.

4. An apparatus comprising:

a processor; and

one or more non-transitory computer readable storage mediums collectively including instructions that, when executed by the processor, cause the processor to perform a method for improving performance of a speech recognition system, the method comprising;

generating a single text data structure for a classifier of a speech recognition system, including;

obtaining first n-best hypotheses as an output of a speech recognition task performed by automatic speech recognition (ASR) for an utterance received by the speech recognition system; and

combining the first n-best hypotheses horizontally in a predetermined order with a separator between each pair of n-best hypotheses to generate the single text data structure, wherein each separator is set based on a classification algorithm of the classifier of the speech recognition system as a symbol that is usable by the classifier of the speech recognition system; and

outputting the single text data structure as an input to the classifier to perform a classification task;

wherein the classifier is trained to perform the classification task based on a single training text data structure by;

obtaining source training data including a plurality of second n-best hypotheses and a transcription for each utterance from a database;

arranging the source training data with the transcription at a head or at an end of the second n-best hypotheses depending on the predetermined order to generate the single training text data structure; and

outputting the single training text data structure to the classifier.

5. The apparatus according to claim 4, wherein each of the first and second n-best hypotheses is associated with a corresponding confidence score, and wherein the predetermined order is determined based on the confidence scores.

6. The apparatus according to claim 4, wherein each separator is selected from the group consisting of:

EOS and <

/s>

.

7. A computer program product comprising a computer readable storage medium having program instructions embodied therewith, wherein the computer readable storage medium is not a transitory signal per se, the program instructions executable by a computer to cause the computer to perform a method for improving performance of a speech recognition system, the method comprising:

generating a single text data structure for a classifier of a speech recognition system, including;

obtaining first n-best hypotheses as an output of a speech recognition task performed by automatic speech recognition (ASR) for an utterance received by the speech recognition system; and

combining the first n-best hypotheses horizontally in a predetermined order with a separator between each pair of n-best hypotheses to generate the single text data structure, wherein each separator is set based on a classification algorithm of the classifier of the speech recognition system as a symbol that is usable by the classifier of the speech recognition system; and

outputting the single text data structure as an input to the classifier to perform a classification task;

wherein the classifier is trained to perform the classification task based on a single training text data structure by;

obtaining source training data including a plurality of second n-best hypotheses and a transcription for each utterance from a database;

arranging the source training data with the transcription at a head or at an end of the second n-best hypotheses depending on the predetermined order to generate the single training text data structure; and

outputting the single training text data structure to the classifier.

8. The computer program product according to claim 7, wherein each of the first and second n-best hypotheses is associated with a corresponding confidence score, and wherein the predetermined order is determined based on the confidence scores.

9. The computer program product according to claim 7, wherein each separator is selected from the group consisting of:

EOS and <

/s>

.