US 9,953,640 B2Granted

Systems and methods of interpreting speech data

AssigneeInterdev Technologies Inc.

InventorsJanet M. Rice, Peng Liang, Terence W. Kuehn

Life of this patent

Estimating the term…

Loading patent…

Abstract

Method and systems are provided for interpreting speech data. A method and system for recognizing speech involving a filter module to generate a set of processed audio data based on raw audio data; a translation module to provide a set of translation results for the raw audio data; and a decision module to select the text data that represents the raw audio data. A method for minimizing noise in audio signals received by a microphone array is also described. A method and system of automatic entry of data into one or more data fields involving receiving a processed audio data; and operating a processing module to: search in a trigger dictionary for a field identifier that corresponds to the trigger identifier; identify a data field associated with a data field identifier corresponding to the field identifier; and providing content data associated with the trigger identifier to the identified data field.

Claims17

Dependent claims

A medical response environment based speech recognition system, the system comprising:

one or more filters to each generate a set of processed audio data based on raw audio data received from one or more computing devices, the one or more filters applying filter processes to the raw audio data to generate the set of processed audio data, the one or more filters comprising at least one filter appropriate for the medical response environment;
a translator, operable by a processor, to provide a set of translation results for the raw audio data based on the set of processed audio data, each translation result being associated with at least one processed audio data and each translation result including a text data and a confidence level associated with that text data;
and
in response to receiving the set of translation results, a decision controller is automatically triggered by the processor to select the text data that represents the raw audio data, the decision control is operable to:
identify at least one translation result from the set of translation results that includes the text data associated with the confidence level that exceeds a confidence threshold;
determine whether the identified at least one translation result comprises more than one translation result;
in response to determining the identified at least one translation result comprises more than one translation result, determine an occurrence frequency for each text data of the identified at least one translation result and select the text data based on the occurrence frequency, the occurrence frequency representing a number of times that the text data appears in the set of translation results;
and
generate an output signal associated with the selection by the decision controller.

6 more elements

A computer-implemented method of recognizing speech for a medical response environment, the method comprising:

operating one or more filters to each generate a set of processed audio data based on raw audio data received from one or more computing devices, the one or more filters being operated to apply filter processes to the raw audio data to generate the set of processed audio data, wherein the one or more filters comprise at least one filter appropriate for the medical response environment;
operating a translator to provide a set of translation results for the raw audio data based on the set of processed audio data, each translation result being associated with at least one processed audio data and each translation result including a text data and a confidence level associated with that text data;
and
in response to receiving the set of translation results, automatically trigger a decision controller to select the text data that corresponds to the raw audio data, wherein the decision controller is operable to:
identify at least one translation result from the set of translation results that includes the text data associated with the confidence level that exceeds a confidence threshold,
determine whether the identified at least one translation result comprises more than one translation result;
in response to determining the identified at least one translation result comprises more than one translation result, determine an occurrence frequency for each text data of the identified at least one translation result and select the text data based on the occurrence frequency, the occurrence frequency representing a number of times that the text data appears in the set of translation results;
and
generate an output signal associated with the selection by the decision controller.

6 more elements

Dependencies are inferred from the claim text.

Facts

Application: 14/731,819Filed 5 Jun 2015 · us provisional application
Priority: 5 Jun 2014
Published: US 2015/0356968 A110 Dec 2015
Granted: 24 Apr 2018
Term ends: Not estimatedThe source records don’t support an estimate.

Classification9 codes

G10L 15/20
Speech recognition: speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech
G10L 15/08
Speech recognition: speech classification or search
G10L 15/26
Speech recognition: speech to text systems
G10L 19/26
Using predictive techniques: pre-filtering or post-filtering