Portable audio device with voice capabilities
A portable audio device includes a network card able to connect with a WLAN and a wireless modem to connect to a WWAN. The portable audio device detects a wake command via a set of microphones and, in response, selects whether to connect to the WWAN or the WLAN. The portable audio device further acquires, via the set of microphones, a voice query; generates a data request based on the voice query, transmits the data query via the selected one of the WWAN or the WLAN; receives a data response associated with the data request from the selected one of the WWAN or the WLAN; generates an audio signal based on the data response; and transmits the audio signal to one or more speakers included in the portable audio device to generate audio output.
1. A method of processing a voice query, the method comprising:
detecting, via a set of microphones of a portable audio device, a wake command;
in response to detecting the wake command, performing the steps of:
transitioning the portable audio device from a low-power state to a normal-power state, wherein in the low-power state, a first subset of microphones in the set of microphones are powered on for monitoring for the wake command and a second subset of microphones in the set of microphones are powered off, and wherein in the normal-power state, the second subset of microphones is powered on; and
selecting whether to connect to a wireless wide area network (WWAN) via a wireless modem of the portable audio device or connect to a wireless local area network (WLAN) via a network interface of the portable audio device;
acquiring, via the set of microphones, the voice query;
generating a data request based on the voice query;
transmitting the data request to the selected one of the WWAN or the WLAN;
receiving a data response associated with the data request from the selected one of the WWAN or the WLAN;
generating an audio signal based on the data response; and
transmitting the audio signal to one or more speakers included in the portable audio device to generate audio output.
2. The method of claim 1 , wherein selecting whether to connect to the WWAN or the WLAN comprises determining which of the WWAN or the WLAN has a greatest signal strength.
3. The method of claim 1 , further comprising:
detecting a trigger event; and
in response to detecting the trigger event, re-determining whether to connect to the WWAN or the WLAN.
4. The method of claim 3 , wherein the trigger event comprises at least one of an expiration of a predetermined time period, a signal strength for a currently connected network falling below a predetermined threshold level, a schedule event of a user, or movement of the portable audio device that exceeds a predetermined threshold distance.
5. The method of claim 1 , wherein, in the low-power state, the wireless modem or the network interface are powered off.
6. The method of claim 1 , wherein, in the low-power state, the one or more speakers are powered off.
7. The method of claim 1 , wherein generating the data request based on the voice query comprises processing the voice query using natural language processing techniques.
8. One or more non-transitory computer-readable media storing instructions that, when executed by one or more processors, cause the one or more processors to perform steps to process a voice query, the steps comprising:
detecting, via a set of microphones of a portable audio device, a wake command;
in response to detecting the wake command, performing the steps of:
transitioning the portable audio device from a low-power state to a normal-power state, wherein in the low-power state, a first subset of microphones in the set of microphones are powered on for monitoring for the wake command and a second subset of microphones in the set of microphones are powered off, and wherein in the normal-power state, the second subset of microphones is powered on; and
selecting whether to connect to a wireless wide area network (WWAN) via a wireless modem of the portable audio device or connect to a wireless local area network (WLAN) via a network interface of the portable audio device;
acquiring, via the set of microphones, a voice query;
generating a data request based on the voice query;
transmitting the data request to the selected one of the WWAN or the WLAN;
receiving a data response associated with the data request from the selected one of the WWAN or the WLAN;
generating an audio signal based on the data response; and
transmitting the audio signal to one or more speakers included in the portable audio device to generate audio output.
9. The one or more non-transitory computer-readable media of claim 8 , wherein selecting whether to connect to the WWAN or the WLAN comprises determining which of the WWAN or the WLAN has a greatest signal strength.
10. The one or more non-transitory computer-readable media of claim 8 , further comprising:
detecting a trigger event; and
in response to detecting the trigger event, re-determining whether to connect to the WWAN or the WLAN.
11. The one or more non-transitory computer-readable media of claim 8 , further comprising:
in response to detecting the wake command, transitioning the portable audio device from a low-power state to a normal-power state.
12. The one or more non-transitory computer-readable media of claim 11 , wherein:
in the low-power state, a first set of components of the portable audio device used for monitoring for the wake command is powered on and a second set of components of the portable audio device that are not used for monitoring for the wake command is powered off; and
in the normal-power state, at least one component of the second set of components is powered on.
13. The one or more non-transitory computer-readable media of claim 8 , wherein:
the voice query comprises a request for a media item or an information item; and
the data response comprises the media item or the information item.
14. A portable audio device, comprising:
a one or more microphones configured to acquire a wake command and a voice query;
one or more speakers;
a wireless modem configured to connect to a wireless wide area network (WWAN);
a network interface configured to connect to a wireless local area network (WLAN);
a memory that includes an audio processing application; and
a processor that is coupled to the memory and, when executing the audio processing application, is configured to:
detect the wake command;
in response to detecting the wake command, performing the steps of:
transitioning from a low-power state to a normal-power state, wherein in the low-power state, a first subset of microphones in the set of microphones are powered on for monitoring for the wake command and a second subset of microphones in the set of microphones are powered off, and wherein in the normal-power state, the second subset of microphones is powered on; and
selecting whether to connect to the WWAN via the wireless modem or to the WLAN via the network interface;
generate a data request based on the voice query;
transmit the data request to the selected one of the WWAN or the WLAN;
receive a data response associated with the data request from the selected one of the WWAN or the WLAN;
generate an audio signal based on the data response; and
transmit the audio signal to the one or more speakers to generate audio output.
15. The portable audio device of claim 14 , wherein to select whether to connect to the WWAN or the WLAN, the audio processing application is configured to determine which of the WWAN or the WLAN has a greatest signal strength.
16. The portable audio device of claim 14 , further comprising a battery for powering at least one of the one or more microphones, the one or more speakers, the wireless modem, or the network interface.
17. The portable audio device of claim 14 , further comprising a first driver for a first frequency range and a second driver for a second frequency range.
18. The portable audio device of claim 14 , further comprising a subscriber identity module (SIM) device, wherein the processor is further configured to communicate with the WWAN based on information received via the SIM device.