Ultrasonic speech recognition

Patent metadata

Field	Value
Publication number	US-11323800-B2
Application number	US-202016842241-A
Country	US
Kind code	B2
Filing date	Apr 7, 2020
Priority date	Apr 25, 2019
Publication date	May 3, 2022
Grant date	May 3, 2022

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for analyzing ultrasonic signals to recognize mouthed articulations. One of the methods includes generating an ultrasonic carrier signal and coupling the ultrasonic carrier signal to a person's vocal tract. The method includes detecting a modulated ultrasonic signal, the modulated ultrasonic signal corresponding to the ultrasonic carrier signal modulated by the person's vocal tract to include information about articulations mouthed by the person; analyzing, using a data processing apparatus, the modulated ultrasonic signal to recognize the articulations mouthed by the person from the information in the modulated ultrasonic signal; and generating, using the data processing apparatus, an output in response to the recognized articulations.

First claim

What is claimed is:

1. A method, comprising:
generating, by an ultrasonic transducer, an ultrasonic carrier signal;
coupling, by the ultrasonic transducer, the ultrasonic carrier signal to a person's vocal tract, wherein a frequency of the ultrasonic carrier signal varies according to a transmit time of the ultrasonic carrier signal;
detecting, by a microphone, a modulated ultrasonic signal, the modulated ultrasonic signal corresponding to the ultrasonic carrier signal modulated by the person's vocal tract to comprise information about articulations mouthed by the person, wherein detecting the modulated ultrasonic signal comprises:
receiving acoustic energy at a receiving time; and
filtering the acoustic energy to remove portions of the acoustic energy having a frequency outside of a first range of frequencies, the first range of frequencies varying with a corresponding range of transmit times, each of the transmit times occurring during a time window that precedes the receiving time by a first time interval corresponding to a travel time of the ultrasonic carrier signal from the ultrasonic transducer to the microphone through the vocal tact;

analyzing, using a data processing apparatus, the modulated ultrasonic signal to recognize the articulations mouthed by the person from the information in the modulated ultrasonic signal; and
generating, using the data processing apparatus, an output in response to the recognized articulations.

2. The method of claim 1 , wherein generating the ultrasonic carrier signal comprises:
receiving, from an electronic device, an electromagnetic waveform; and
converting the electromagnetic waveform to the ultrasonic carrier signal.

3. The method of claim 1 , wherein analyzing the modulated ultrasonic signal comprises performing speech recognition on the articulations mouthed by the person, wherein the articulations mouthed by the person comprise one or more of a phoneme, word, command, phrase, sentence, or non-word articulation.

4. The method of claim 1 , wherein detecting the modulated ultrasonic signal comprises:
filtering the received acoustic energy to remove portions of the received acoustic energy at frequencies outside of an operative frequency band of the ultrasonic carrier signal.

5. The method of claim 1 , wherein generating the output comprises generating a text of the recognized articulations or an audio signal of the recognized articulations.

6. The method of claim 1 , wherein generating the output comprises generating output data indicating a prosody of the recognized articulations or executing a command in response to the recognized articulations.

7. The method of claim 1 , wherein detecting the modulated ultrasonic signal comprises sensing acoustic vibrations of a surface of the person's body.

8. A system, comprising:
an ultrasonic transducer module configured to generate an ultrasonic carrier signal and couple the ultrasonic carrier signal to a person's vocal tract, wherein a frequency of the ultrasonic carrier signal varies according to a transmit time of the ultrasonic carrier signal;
a microphone module configured to be coupled to the person's vocal tract to detect a modulated ultrasonic signal, the modulated ultrasonic signal corresponding to the ultrasonic carrier signal modulated by the person's vocal tract to comprise information about articulations mouthed by the person, wherein detecting the modulated ultrasonic signal comprises:
receiving acoustic energy at a receiving time; and
filtering the acoustic energy to remove portions of the acoustic energy having a frequency outside of a first range of frequencies, the first range of frequencies varying with a corresponding range of transmit times, each of the transmit times occurring during a time window that precedes the receiving time by a first time interval corresponding to a travel time of the ultrasonic carrier signal from the ultrasonic transducer module to the microphone module through the vocal tract; and

a data processing apparatus in communication with the microphone module programmed to analyze the modulated ultrasonic signal to recognize the articulations mouthed by the person from the information in the modulated ultrasonic signal and generate an output in response to the recognized articulations.

9. The system of claim 8 , wherein detecting the modulated ultrasonic signal comprises:
filtering the received acoustic energy to remove portions of the received acoustic energy at frequencies outside of an operative frequency band of the ultrasonic carrier signal.

10. The system of claim 8 , wherein the ultrasonic transducer module is configured to be placed in the person's mouth.

11. The system of claim 8 , wherein the ultrasonic transducer module is configured to be placed on a surface of the person's body.

12. The system of claim 8 , wherein one or more of the ultrasonic transducer module or the microphone module is integrated into a clothing article or an accessory.

13. The system of claim 8 , wherein the ultrasonic transducer module is integrated into dental equipment.

14. The system of claim 8 , wherein the microphone module is configured to contact a surface of the person's neck to detect the modulated ultrasonic signal.

15. The system of claim 8 , wherein generating the ultrasonic carrier signal comprises:
receiving, by the ultrasonic transducer module and from an electronic device, an electromagnetic waveform; and
converting the electromagnetic waveform to the ultrasonic carrier signal.

16. The system of claim 8 , wherein analyzing the modulated ultrasonic signal comprises performing speech recognition on the articulations mouthed by the person.

17. The system of claim 8 , wherein the microphone module is configured to contact a surface of the person's face to detect the modulated ultrasonic signal.

18. The system of claim 8 , wherein detecting the modulated ultrasonic signal comprises sensing acoustic vibrations of a surface of the person's body.

Assignees

• X Dev Llc

Inventors

• Hunt Thomas Peter

Classifications

• G10L15/28 Primary

  Constructional details of speech recognition systems · CPC title

• H04R1/46 Primary

  Special adaptations for use as contact microphones, e.g. on musical instrument, on stethoscope (throat mountings H04R1/14) · CPC title

• H04R17/02

  Microphones · CPC title

• H04R2217/03

  Parametric transducers where sound is generated or captured by the acoustic demodulation of amplitude modulated ultrasonic waves · CPC title

• H04R1/14

  Throat mountings for microphones · CPC title