Speech control of a medical apparatus

Patent metadata

Field	Value
Publication number	US-12478360-B2
Application number	US-202217949371-A
Country	US
Kind code	B2
Filing date	Sep 21, 2022
Priority date	Sep 23, 2021
Publication date	Nov 25, 2025
Grant date	Nov 25, 2025

Abstract

One or more example embodiments provides a method for speech control of a medical apparatus, the method comprising capturing an audio signal containing operator speech input directed at controlling the apparatus; first analyzing the audio signal for a first speech analysis result; recognizing a first speech command based on the first speech analysis result; assigning the first speech command to a safety class, the safety class being provided for safety-critical speech commands; ascertaining a verification signal to confirm the first speech command; generating a control signal for controlling the medical apparatus, the generating being based on the first speech command and the verification signal, wherein the control signal is for controlling the medical apparatus according to the first speech command; and inputting the control signal into the medical apparatus.

First claim

We claim:

1 . A method for speech control of a medical apparatus, the method comprising:
capturing an audio signal containing operator speech input directed at controlling the apparatus; first analyzing the audio signal for a first speech analysis result; recognizing a first speech command based on the first speech analysis result; assigning the first speech command to a safety class, the safety class being provided for safety-critical speech commands; ascertaining a verification signal to confirm the first speech command; generating a control signal for controlling the medical apparatus, the generating being based on the first speech command and the verification signal, wherein the control signal is for controlling the medical apparatus according to the first speech command; and inputting the control signal into the medical apparatus.

2 . The method of claim 1 , wherein the ascertaining the verification signal includes the first speech command and the method further comprises:
issuing a prompt to confirm the first speech command to the operator.

3 . The method of claim 2 , wherein the ascertaining the verification signal comprises:
capturing user input directed at the confirmation of the first speech command from the operator.

4 . The method of claim 3 , wherein
outputting an audio signal based on the first speech command, or the capturing captures the user input as an audio signal.

5 . The method of claim 4 , wherein the ascertaining the verification signal comprises:
outputting a prompt for the user input to the operator and capturing the user input, the user input comprising speech control information.

6 . The method of claim 3 , wherein the verification signal confirms the first speech command if the operator the user input satisfies at least one of:
a predefined time criterion, or a predefined content criterion.

7 . The method of claim 6 , wherein the time criterion is adjustable based on the first speech command.

8 . The method of claim 3 , wherein the ascertaining the verification signal comprises:
analyzing the audio signal to provide a second speech analysis result, recognizing a second speech command based on the second speech analysis result, and comparing the first speech command and the second speech command, wherein the verification signal confirms the first speech command if the first speech command and the second speech command satisfy a conformity criterion.

9 . The method of claim 3 , wherein the first analyzing comprises:
applying a first computational linguistics algorithm, the first computation linguistics algorithm comprising a first trained function to the audio signal.

10 . The method of claim 2 , wherein the first analyzing comprises:
applying a first computational linguistics algorithm, the first computation linguistics algorithm comprising a first trained function to the audio signal.

11 . The method of claim 1 , wherein the first analyzing comprises:
applying a first computational linguistics algorithm, the first computation linguistics algorithm comprising a first trained function to the audio signal.

12 . The method of claim 11 , wherein the first analyzing comprises:
applying a second computational linguistics algorithm, the second computational linguistics algorithm comprising a second trained function to the audio signal, wherein the first trained function and the second trained function are different from one another.

13 . The method of claim 12 , wherein the second trained function is configured only to identify safety-critical speech commands in the audio signal.

14 . The method of claim 1 , wherein the ascertaining the verification signal comprises:
analyzing the audio signal to provide a second speech analysis result, recognizing a second speech command based on the second speech analysis result, and comparing the first speech command and the second speech command, wherein the verification signal confirms the first speech command if the first speech command and the second speech command satisfy a conformity criterion.

15 . The method of claim 1 , wherein the first analyzing the audio signal comprises at least one of:
tokenizing for at least one of segmenting letters, words or sentences within the audio signal, and at least one of the first speech command or a second speech command are recognized based on at least one of first tokenization information or second tokenization information, or recognizing semantic analysis of the audio signal and the first speech command and the second speech command are recognized based on first semantic information and second semantic information.

16 . A speech control apparatus for speech control of a medical apparatus comprising:
at least one first interface configured to capture an audio signal containing operator speech input directed at controlling the apparatus;
at least one evaluation unit configured to analyze the audio signal and provide a first speech analysis result,
recognize a first speech command based on the first speech analysis result,
assign the first speech command to a safety class, wherein a safety class is provided for safety-critical speech commands,
ascertain a verification signal to confirm the first speech command;
a control unit configured to
generate a control signal for controlling the medical apparatus based on the first speech command and the verification signal provided that the first speech command has been based on the verification signal, wherein the control signal is suitable for controlling the medical apparatus according to the first speech command; and
a second interface configured to input the control signal into the medical apparatus.

17 . A medical system comprising:
the speech control apparatus of claim 16 ; and the medical apparatus, the medical apparatus configured to perform a medical procedure.

18 . A non-transitory computer-readable storage medium storing readable and executable program that, when executed by a programmable computing unit, cause the programmable computing unit to perform the method of claim 1 .

Assignees

• Siemens Healthineers Ag

Inventors

• Rothbauer Stefan
• Kuhrt Soeren
• Kilian Lennart

Classifications

• G10L15/22 Primary

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title

• G10L25/51

  for comparison or discrimination · CPC title

• G10L15/1815

  Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning · CPC title

• A61B2017/00203

  with speech control or speech recognition · CPC title

• G10L2015/223

  Execution procedure of a spoken command · CPC title