Architectures and topologies for vehicle-based, voice-controlled devices

Patent metadata

Field	Value
Publication number	US-10540970-B2
Application number	US-201715838878-A
Country	US
Kind code	B2
Filing date	Dec 12, 2017
Priority date	Dec 12, 2017
Publication date	Jan 21, 2020
Grant date	Jan 21, 2020

Abstract

This disclosure describes, in part, techniques for implementing voice-enabled devices in vehicle environments to facilitate voice interaction with vehicle computing devices. Due to the differing communication capabilities of existing vehicle computing devices, the techniques described herein describe different communication topologies for facilitating voice interaction with the vehicle computing devices. In some examples, the voice-enabled device may be communicatively coupled to a user device, which may communicate with a remote speech-processing system to determine and perform operations responsive to the voice commands, such as conducting phone calls using loudspeakers of the vehicle computing device, streaming music to the vehicle computing device, and so forth. In this way, the communication topologies between the voice-enabled computing device, the vehicle computing device, and the user device provide for voice control of vehicle computing devices which may otherwise be unable to be controlled by voice commands.

First claim

What is claimed is:

1. A voice-controlled device disposed in an interior of a vehicle, the voice-controlled device comprising:
a microphone;
a first input/output (I/O) interface to communicatively couple, by a physical communication connection, the voice-controlled device to a second I/O interface of a vehicle computing device of the vehicle, the vehicle computing device coupled to one or more loudspeakers;
one or more processors; and
computer-readable media storing computer-executable instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
capturing, using the microphone, first audio representing a speech utterance;
generating first audio data representing the speech utterance;
sending, using a Bluetooth Low Energy Profile (BLE) of a Bluetooth protocol, the first audio data to a user mobile device, wherein the user mobile device sends the first audio data to a remote speech-processing system;
receiving, from the user mobile device and using an Advanced Audio Distribution Profile (A2DP) of the Bluetooth protocol, second audio data, wherein the second audio data is received by the user mobile device from a network-based music service, and wherein the remote speech-processing system determines an intent of the speech utterance is to stream the second audio data and sends a command to the user mobile device to stream the second audio data; and
sending, via the physical communication connection, the second audio data to the vehicle computing device to be output by the one or more loudspeakers of the vehicle computing device.

2. The voice-controlled device of claim 1 , further comprising a loudspeaker, and the operations further comprising:
receiving, from the user mobile device and using the BLE of the Bluetooth protocol, a control message, wherein the control message includes an instruction that the voice-controlled device output an auditory icon;
outputting, using the loudspeaker of the voice-controlled device, the auditory icon.

3. The voice-controlled device of claim 1 , further comprising multiple light sources, and the operations further comprising:
receiving, from the user mobile device and using the BLE of the Bluetooth protocol, a control message, wherein the control message includes an instruction that the voice-controlled device to output light according to a light pattern; and
causing the multiple light sources to output light according to the light pattern.

4. A method comprising:
generating, by one or more processors of a voice-enabled device, first audio data representing a speech utterance captured by a microphone of the voice-enabled device, the voice-enabled device being disposed in an interior of a vehicle and communicatively coupled to a vehicle computing device associated with the vehicle;
sending, via a personal area network (PAN) and using a first communication protocol, the first audio data to a user device disposed in the interior of the vehicle, wherein the user device sends the first audio data to a remote speech-processing system;
receiving, from the user device, via the PAN, and using a second communication protocol, second audio data associated with an intent of the speech utterance; and
sending, from the voice-enabled device and to the vehicle computing device, the second audio data.

5. The method of claim 4 , wherein:
sending the first audio data to the user device using the first communication protocol comprises sending the first audio data using a Bluetooth Low Energy Profile (BLE) of a Bluetooth protocol, wherein the user device is configured to send the first audio data over a wide area network (WAN) to a remote speech-processing system; and
receiving the second audio data from the user device using the second communication protocol comprises receiving music audio data using an Advanced Audio Distribution Profile (A2DP) of the Bluetooth protocol, wherein the music audio data is associated with an intent of the speech utterance.

6. The method of claim 4 , wherein:
sending the first audio data to the user device using the first communication protocol comprises sending the first audio data using a Bluetooth Low Energy Profile (BLE) of a Bluetooth protocol; and
receiving the second audio data from the user device using the second communication protocol comprises receiving call audio data using a Hands-Free Profile (HFP) of the Bluetooth protocol.

7. The method of claim 6 , wherein the speech utterance comprises a first speech utterance, the call audio data comprises first call audio data, and the method further comprising:
capturing, by the voice-enabled device, a second speech utterance;
generating, by the voice-enabled device, second call audio data representing the second speech utterance; and
sending, from the voice-enabled device and to the user device using the HFP of the Bluetooth protocol, the second call audio data.

8. The method of claim 4 , wherein sending, from the user device and to the vehicle computing device, the second audio data comprises at least one of:
sending, via a physical connection between the voice-enabled device and the vehicle computing device, music audio data to the vehicle computing device; or
sending, via the physical connection, call audio data to the vehicle computing device.

9. The method of claim 4 , further comprising outputting, by a loudspeaker of the voice-enabled computing device, audio represented by the second audio data, wherein the audio comprises an auditory icon indicating that voice-enabled device detected the speech utterance.

10. The method of claim 4 , wherein:
the speech utterance comprises a first speech utterance;
the user device is configured to send the first audio data over a wide area network (WAN) to a remote speech-processing system; and
receiving the second audio data from the user device using the second communication protocol comprises receiving the second audio data using an Advanced Audio Distribution Profile (A2DP) of a Bluetooth protocol, wherein the second audio data represents a second speech utterance comprising one or more machine-generated words that are responsive to the first speech utterance.

11. The method of claim 4 , further comprising, prior to sending the first audio data to the user device:
determining, using automatic speech recognition (ASR), that the speech utterance represented by the first audio data includes a wake word; and
at least partly in response to determining that the speech utterance includes the wake word, sending the first audio data to the user device using a Bluetooth Low Energy Profile (BLE) of a Bluetooth protocol.

12. A computing device comprising:
a microphone;
a loudspeaker;
one or more processors;
computer-readable media storing computer-executable instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
capturing, by the microphone, a speech utterance in an environment of the microphone, the computing device being disposed in an interior of a vehicle including a vehicle computing device, the vehicle computing device coupled to one or more loudspeakers;
generating, by the one or more processors of the computing device, first audio data representing the speech utterance;
sending, using a first communication protocol, the first audio data to a user device for sending to a remote speech-processing system, the user device being disposed in the interior of the vehicle;
receiving, from the user device and using the first communication protocol, an indication of a command included in the speech utterance, wherein the command is associated with an intent

Assignees

• Amazon Tech Inc

Inventors

• Nandy Dibyendu
• Parthasarathy Rangaprabhu
• Joshi Snehal G
• Mandhani Arvind
• Motwani Dhananjay
• Birch-Jensen Hans Edward
• Pajjuri Ambika

Classifications

• G10L15/1822

  Parsing for meaning understanding · CPC title

• G10L15/30

  Distributed recognition, e.g. in client-server systems, for mobile phones or network applications · CPC title

• H04M1/6091

  including a wireless interface · CPC title

• G10L2015/223

  Execution procedure of a spoken command · CPC title

• H04W4/40

  for vehicles, e.g. vehicle-to-pedestrians [V2P] · CPC title