# US 2016/0253994 A1 · System and method for calibrating a speech recognition system to an operating environment

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2016/0253994 A1
- Document ID: US20160253994A1
- Status: Published application
- Kind: A1
- Application number: 14/634,359
- Filed: 2015-02-27
- Published: 2016-09-01
- Earliest claimed: 2015-02-27
- Assignees: Storz Endoskop Produktions GmbH
- Applicants: Storz Endoskop Produktions GmbH
- Inventors: Sankaran Panchapagesan; Matteo Contolini; Ted Applebaum
- Web page: https://patentgrep.com/patent/US20160253994A1

## CPC

- G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L 21/0316: by changing the amplitude
- G06F 3/167: {Audio in a user interface, e.g. using voice commands for navigating, audio feedback}
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A voice controlled medical system with improved speech recognition includes a microphone in an operating environment and a medical device. The voice controlled medical system further includes a controller in communication with the microphone and the medical device that operates the medical device by executing audio commands received by the microphone. The voice controlled medical system further includes a calibration signal indicative of distortion in the operating environment which is generated by comparing an audio signal played in the operating environment with a sound signal received by the microphone. The controller uses the calibration signal to interpret audio commands received by the microphone.

## Claims

### Claim 1

A voice controlled medical system with improved speech recognition, comprising:
at least one microphone in an operating environment;
a medical device;
a controller in communication with said microphone and said medical device that operates said medical device by executing audio commands received by said microphone; and
a calibration signal indicative of distortion in the operating environment, said calibration signal generated by comparing an audio signal played in the operating environment with a sound signal received by said microphone;
said controller using said calibration signal to interpret audio commands received by said microphone.

### Claim 2 (depends on 1)

The voice controlled medical system of claim 1, wherein the audio signal comprises a recording of at least one human voice.

### Claim 3 (depends on 2)

The voice controlled medical system of claim 2, wherein the audio signal comprises a recording of at least two human voices.

### Claim 4 (depends on 1)

The voice controlled medical system of claim 1, wherein the audio signal comprises a set of sounds pre-selected to give the best performance for calibrating said controller.

### Claim 5 (depends on 1)

The voice controlled medical system of claim 1, wherein said controller interprets audio commands using a hidden Markov model.

### Claim 6 (depends on 1)

The voice controlled medical system of claim 1, wherein said at least one microphone is a microphone array.

### Claim 7

A voice controlled medical system with improved speech recognition, comprising:
a first microphone in an operating environment;
a second microphone in the operating environment, said second microphone being nearer to a source of sound in the operating environment than said first microphone;
a medical device;
a controller in communication with said first microphone and said medical device that operates said medical device by executing commands received by said first microphone; and
a calibration signal generated by comparing a sound received by said first microphone and said second microphone;
said controller using said calibration signal to interpret audio commands received by said first microphone.

### Claim 8 (depends on 7)

The voice controlled medical system of claim 7, wherein said calibration signal is generated in advance and stored for later use by said controller to operate said medical device.

### Claim 9 (depends on 7)

The voice controlled medical system of claim 7, wherein said controller interprets audio commands using a hidden Markov model.

### Claim 10 (depends on 7)

The voice controlled medical system of claim 7, wherein the source moves within the operating environment while the sound is received by said first microphone and said second microphone.

### Claim 11 (depends on 7)

The voice controlled medical system of claim 7, further comprising:
voice interpreting data; and
a source calibration signal generated by comparing a sound received by said second microphone and said voice interpreting data;
wherein said calibration signal is generated by comparing said source calibration signal to the sound received by said first microphone.

### Claim 12 (depends on 7)

The voice controlled medical system of claim 7, wherein said calibration signal is generated using a Mean MLLR algorithm.

### Claim 13 (depends on 7)

The voice controlled medical system of claim 7, wherein said calibration signal is generated using a Constrained MLLR algorithm.

### Claim 14

A method of calibrating a speech recognition system in a voice controlled medical system, comprising:
(a) playing an audio sample in an operating environment;
(b) recording the audio sample using at least one microphone in an operating environment;
(c) comparing the audio sample to the recording by the microphone; and
(d) generating a calibration signal based on the comparison performed in step (c).

### Claim 15 (depends on 14)

The method of claim 14, further comprising the step of using said calibration signal to improve speech recognition for operating a medical device.

### Claim 16 (depends on 14)

The method of claim 14, wherein the audio sample comprises a recording of at least one human voice.

### Claim 17 (depends on 16)

The method of claim 16, wherein the audio sample comprises a recording of at least two human voices.

### Claim 18 (depends on 14)

The method of claim 14, wherein the audio sample comprises a set of sounds pre-selected to give the best performance for calibrating the speech recognition system.

### Claim 19 (depends on 14)

The method of claim 14, wherein the at least one microphone is a microphone array.

### Claim 20

A method of calibrating a speech recognition system in a voice controlled medical system, comprising:
(a) recording a sound in an operating environment using a first microphone and a second microphone nearer to a source of the sound than the first microphone;
(c) comparing the recording by the first microphone and the second microphone; and
(d) generating a calibration signal based on the comparison performed in step (c).

### Claim 21 (depends on 20)

The method of claim 20, further comprising:
(e) moving the source of the sound within the operating environment during step (a).

### Claim 22 (depends on 20)

The method of claim 20, wherein step (c) comprises generating a source calibration signal by comparing the recording by the second microphone to voice interpreting data, and comparing the source calibration signal to the recording by the first microphone; and
wherein step (d) comprises generating a calibration signal based on the comparison between the source calibration signal and the recording by the first microphone.

### Claim 23 (depends on 20)

The method of claim 20, wherein the calibration signal is generated using a Mean MLLR algorithm.

### Claim 24 (depends on 20)

The method of claim 20, wherein the calibration signal is generated using a Constrained MLLR algorithm.
