SYSTEM AND METHOD FOR DETECTING TANTRUMS
System and method for analyzing audio data are provided. The audio data, as well as input from other sensors, may be analyzed to detect tantrums. In some examples, the audio data, as well as input from other sensors, may be analyzed to predict tantrums. Feedbacks and reports may be provided based on the detected and predicted tantrums.
1 . A system for processing audio, the system comprising:
at least one processing unit configured to:
obtain audio data captured by one or more audio sensors; and
analyze the audio data to detect a tantrum.
2 . The system of claim 1 , wherein the at least one processing unit is further configured to:
analyze the audio data to obtain prosodic information; and
base the detection of the tantrum on the prosodic information.
3 . The system of claim 1 , wherein the at least one processing unit is further configured to:
analyze the audio data to obtain a textual information; and
base the detection of the tantrum on the textual information.
4 . The system of claim 1 , wherein the detection of the tantrum is based on at least one rule, the at least one rule is a result of one or more machine learning algorithms trained on training examples.
5 . The system of claim 1 , wherein the detection of the tantrum is based on an output of at least one neural network.
6 . The system of claim 1 , wherein the at least one processing unit is further configured to measure a time length associated with the tantrum.
7 . The system of claim 1 , wherein the at least one processing unit is further configured to:
determine information associated with the tantrum;
obtain additional audio data captured by the one or more audio sensors after the detection of the tantrum;
detect one or more additional tantrums in the additional audio data;
determine information associated with the one or more additional tantrums; and
provide one or more reports to a user based on at least part of the information associated with the tantrum and at least part of the information associated with the one or more additional tantrums.
8 . The system of claim 1 , wherein the one or more audio sensors are included in a wearable apparatus; wherein the system includes the wearable apparatus; and wherein the at least one processing unit is further configured to:
based on the detection of the tantrum, provide feedback to a user.
9 . The system of claim 8 , wherein the at least one processing unit is further configured to determine that the tantrum is a tantrum of the wearer; and wherein providing the feedback is further based on said determination.
10 . The system of claim 1 , wherein the at least one processing unit is further configured to:
obtain one or more tantrum prediction rules;
analyze the audio data using the one or more tantrum prediction rules to obtain tantrum prediction information; and
based on the tantrum prediction information, provide feedback to a user.
11 . A method for processing audio, the method comprising:
obtaining audio data captured by one or more audio sensors; and
analyzing the audio data to detect a tantrum.
12 . The method of claim 11 , further comprising:
analyzing the audio data to obtain prosodic information; and
basing the detection of the tantrum on the prosodic information.
13 . The method of claim 11 , further comprising:
analyzing the audio data to obtain a transcription; and
basing the detection of the tantrum on the transcription.
14 . The method of claim 11 , wherein the detection of the tantrum is based on at least one rule, the at least one rule is a result of one or more machine learning algorithms trained on training examples.
15 . The method of claim 11 , further comprising measuring a time length associated with the tantrum.
16 . The method of claim 11 , further comprising:
obtaining additional audio data captured by the one or more audio sensors after the detection of the tantrum;
detecting one or more additional tantrums in the additional audio data; and
providing one or more reports to a user based on at least part of the information associated with the tantrum and at least part of the information associated with the one or more additional tantrums.
17 . The method of claim 11 , further comprising:
determining that the tantrum is a tantrum of a wearer of a wearable apparatus that includes the one or more audio sensors; and
providing feedback to a user based on said determination.
18 . The method of claim 11 , further comprising:
based on the detection of the tantrum, providing feedback to a user.
19 . The method of claim 11 , further comprising:
obtaining one or more tantrum prediction rules;
analyzing the audio data using the one or more tantrum prediction rules to obtain tantrum prediction information; and
based on the tantrum prediction information, providing feedback to a user.
20 . A non-transitory computer readable medium storing data and computer implementable instructions for carrying out the method of claim 11 .