Method and system for voice based media search
Voice-based input is used to operate a media device and/or to search for media content. Voice input is received by a media device via one or more audio input devices and is translated into a textual representation of the voice input. The textual representation of the voice input is used to search one or more cache mappings between input commands and one or more associated device actions and/or media content queries. One or more natural language processing techniques may be applied to the translated text and the resulting text may be transmitted as a query to a media search service. A media search service returns results comprising one or more content item listings and the results may be presented on a display to a user.
1 . A method comprising:
storing personalized command word data;
receiving an audio signal;
generating non-textual data representing the received audio signal;
processing the generated non-textual data, based at least in part on the audio signal, wherein the processing comprises comparing the generated non-textual data with the personalized command word data; and
based at least in part on the processing:
generating a textual representation of the received audio signal, wherein the textual representation is generated based at least in part on a speech-to-text transformation of the audio signal;
determining whether the textual representation corresponds to an electronic device action; and
based at least in part on determining that the textual representation corresponds to the electronic device action, executing a command of the electronic device action that corresponds to the textual representation.
2 . The method of claim 1 , wherein comparing the generated non-textual data with the personalized command word data further comprises:
receiving a voice input;
generating a voice profile based at least in part on the received voice input;
determining the personalized command word data based at least in part on the voice profile; and
comparing the generated non-textual data with the determined personalized command word data.
3 . The method of claim 2 , wherein the voice input received is based at least in part on a user speaking into a microphone of a electronic device.
4 . The method of claim 1 , further comprising determining a spatial location of a user based at least in part on the audio signal received.
5 . The method of claim 4 , wherein the spatial location is determined by applying a beam forming technique.
6 . The method of claim 4 , further comprising, identifying the user based at least in part on a closest match between the determined spatial location and a voice input received subsequent to receiving the audio signal.
7 . The method of claim 1 , further comprising filtering out ambient noise while the audio signal is being received.
8 . The method of claim 7 , wherein the ambient noise is generated by an audio output of a electronic device.
9 . The method of claim 1 , further comprising receiving a second audio signal subsequent to receiving the audio signal.
10 . The method of claim 9 , further comprising associating back-to-back receipt of the audio signal and the second audio signal with multiple electronic device actions.
11 . The method of claim 9 , wherein the audio signal is received from a first user and the second audio signal is received from a second user.
12 . The method of claim 9 , wherein the audio signal and the second audio signal is received from a same user.
13 . A system comprising:
control circuitry configured to:
store personalized command word data;
receive an audio signal;
generate non-textual data representing the received audio signal;
process the generated non-textual data, based at least in part on the audio signal, wherein the processing comprises comparing the generated non-textual data with the personalized command word data; and
based at least in part on the processing:
generate a textual representation of the received audio signal, wherein the textual representation is generated based at least in part on a speech-to-text transformation of the audio signal;
determine whether the textual representation corresponds to an electronic device action; and
based at least in part on determining that the textual representation corresponds to the electronic device action, execute a command of the electronic device action that corresponds to the textual representation.
14 . The system of claim 13 , wherein comparing the generated non-textual data with the personalized command word data further comprises, the control circuitry configured to:
receive a voice input;
generate a voice profile based at least in part on the received voice input;
determine the personalized command word data based at least in part on the voice profile; and
compare the generated non-textual data with the determined personalized command word data.
15 . The system of claim 14 , wherein the voice input received is based at least in part on a user speaking into a microphone of a electronic device.
16 . The system of claim 13 , further comprising, the control circuitry configured to determine a spatial location of a user based at least in part on the audio signal received.
17 . The system of claim 16 , further comprising, the control circuitry configured to identify the user based at least in part on a closest match between the determined spatial location and a voice input received subsequent to receiving the audio signal.
18 . The system of claim 13 , further comprising, the control circuitry configured to filter out ambient noise while the audio signal is being received.
19 . The system of claim 13 , further comprising, the control circuitry configured to receive a second audio signal subsequent to receiving the audio signal.
20 . The system of claim 19 , further comprising, the control circuitry configured to associate back-to-back receipt of the audio signal and the second audio signal with multiple electronic device actions.