Modification of electronic system operation based on acoustic ambience classification
View Patent ↗Methods and systems for modification of electronic system operation based on acoustic ambience classification are presented. In an example method, at least one audio signal present in a physical environment of a user is detected. The at least one audio signal is analyzed to extract at least one audio feature from the audio signal. The audio signal is classified based on the audio feature to produce at least one classification of the audio signal. Operation of an electronic system interacting with the user in the physical environment is modified based on the classification of the audio signal.
1. A method, comprising:
detecting, using a microphone, at least one audio signal present in a physical environment while a media player is playing a song having a genre, the at least one audio signal including first audio data corresponding to the song, second audio data associated with a person exposed to the song, and third audio data associated with noise in the physical environment different than the first audio data and the second audio data;
cancelling, using the least one hardware processor, the third audio data from the at least one audio signal to generate at least one filtered audio signal;
analyzing the at least one filtered audio signal to extract at least one audio feature from the at least one audio signal;
classifying, by at least one hardware processor, the at least one filtered audio signal based on the at least one audio feature to produce a classification of the at least one filtered audio signal, the classification including a reaction of the person to the media content being played by the media player; and
based on the genre and the reaction, automatically modifying, using the least one hardware processor, operation of the media player by modifying a playlist of media content played by the media player to include more songs of the genre.
2. The method of claim 1 , wherein the modifying of the operation of the media player includes adjusting an audio volume produced by the media player.
3. The method of claim 1 , wherein the modifying of the operation of the media player includes providing, to the person via an automated speech recognition system, guidance regarding interaction of the person with the automated speech recognition system.
4. The method of claim 1 , wherein the classifying includes classifying a gender of the person.
5. The method of claim 1 , wherein the classifying includes classifying a language spoken by the person.
6. The method of claim 1 , wherein the classifying of the reaction includes detecting contact with a physical surface located in the physical environment.
7. The method of claim 1 , wherein the song being played by the media player is by a musical group; and the modifying of the operation of the media player includes altering the playlist of media content played by the media player to include more songs by the musical group.
8. The method of claim 1 , wherein the classifying of the at least one filtered audio signal includes classifying the at least one filtered audio signal as including a conversation, and the modifying of the operation of the media player in the physical environment based on the reaction includes reducing a volume of media played by the media player.
9. The method of claim 1 , wherein the classifying of the at least one filtered audio signal includes classifying a mood of the person as a negative mood, and the modifying of the operation of the media player includes adding songs to the playlist of media content played by the media player, the added songs selected to alleviate the negative mood.
10. The method of claim 1 , wherein the modifying of the operation of the media player based on the reaction and the genre is further based on rating information associated with a second song having non-explicit lyrics and includes adding the second song to the playlist of media content played by the media player.
11. The method of claim 1 , wherein the classification includes a detection of children's voices; the modifying of the operation of the media player is further based on the detection of the children's voices and rating information associated with a second song;
and the modifying of the operation of the media player includes adding the second song to the playlist of media content played by the media player.
12. The method of claim 1 , wherein the classifying of the reaction to the media content includes detecting humming by the person.
13. The method of claim 1 , wherein the classifying of the reaction to the media content includes detecting tapping by the person.
14. The method of claim 1 , wherein the classifying of the reaction to the media content includes detecting drumming by the person.
15. The method of claim 1 , further including:
determining that the third audio data is likely to disrupt an automated speech recognition system, and wherein the modifying of the operation of the media player is further based on the determination that the third audio data is likely to disrupt the speech recognition system and includes reducing a vocabulary of the automated speech recognition system to a subset of available words.
16. The method of claim 1 , wherein the microphone includes a first microphone and a second microphone and further including the identifying the third audio data as detected by the second microphone.
17. A non-transitory computer-readable storage medium comprising instructions that, when executed by at least one processor of a machine, cause the machine to perform operations including:
detecting at least one audio signal present in a physical environment while a media player is playing a song having a genre, the at least one audio signal including first audio data corresponding to the song, second audio data associated with a person exposed to the song, and third audio data associated with noise in the physical environment different than the first audio data and the second audio data;
cancelling the third audio data from the at least one audio signal to generate at least one filtered audio signal;
analyzing the at least one filtered audio signal to extract at least one audio feature from the at least one audio signal;
classifying the at least one filtered audio signal based on the at least one audio feature to produce a classification of the at least one filtered audio signal, the classification including a reaction of the person to the media content being played by the media player; and
based on the genre and the reaction, automatically modifying operation of the media player by modifying a playlist of media content played by the media player to include more songs of the genre.
18. A system comprising:
at least one microphone configured to detect at least one audio signal present in a physical environment while a media player is playing a song having a genre, the at least one audio signal including first audio data corresponding to the song, second audio data associated with a person exposed to the song, and third audio data associated with noise in the physical environment different than the first audio data and the second audio data;
at least one processor; and
memory including instructions that, when executed by the at least one processor, cause the system to perform operations including:
cancelling the third audio data from the at least one audio signal to generate at least one filtered audio signal;
analyzing the at least one filtered audio signal to extract at least one audio feature from the at least one audio signal;
classifying the at least one filtered audio signal based on the at least one audio feature to produce a classification of the at least one filtered audio signal, the classification including a reaction of the person to the media content being played by the media player; and
based on the genre and the reaction, automatically modifying operation of the media player by modifying a playlist of media content played by the media player to include more songs of the genre.