System for real-time recognition and identification of sound sources
The present invention relates to a method for identifying a sound source comprising the following steps: (S1): acquisition of a sound signal; (S2): application of a frequency fitter to the acquired sound signal in order to obtain a filtered signal; (S4): extraction of a matrix of features associated with the filtered signal; (S5): identification of the source by applying a classification model to the feature matrix extracted in step (S4), the classification model having, as its output, at least one class associated with the source of the acquired sound signal.
1 . A method implemented by a data processor of a noise monitoring device, comprising the steps of:
S1: obtaining a sound signal emitted at a construction site and acquired by a sound sensor;
S2: applying a frequency filter to the obtained sound signal, thereby obtaining a filtered signal;
S4: extracting features from the filtered signal;
S5: identifying a specific sound source by applying a classification model to the features extracted in step S4 and providing at least one label associated to the specific sound source, wherein the specific sound source is a parent source as defined in a hierarchic model in which each sound source is either a parent source or a child source linked to a parent source; and
a post-processing step, subsequent to step S5, which comprises the following sub-steps:
evaluating a sound level of the obtained sound signal and comparing the evaluated sound level with a first predetermined threshold, said identifying is then considered reliable if the evaluated sound level is greater than the first predetermined threshold;
comparing a value representing a level of confidence associated with the presence of the specific sound source in the obtained sound signal with a second predetermined threshold;
based on the value representing the level of confidence associated with the presence of the specific sound source in the obtained sound signal being greater than the second predetermined threshold:
selecting, from one or more child sources linked to the specific sound source, the child source having a highest level of confidence associated with the presence of the child source in the obtained sound signal;
comparing the level of confidence associated with the presence of the selected child source in the obtained sound signal with a third predetermined threshold;
based on the level of confidence associated with the presence of the selected child source in the obtained sound signal being greater than the third predetermined threshold, the specific sound source is changed to the selected child source; and
based on the level of confidence associated with the presence of the selected child source in the obtained sound signal being lower than the third predetermined threshold, the specific sound source remains the parent source; and
based on the value representing the level of confidence associated with the presence of the specific sound source in the obtained sound signal being lower than the second predetermined threshold, said identifying is considered not reliable; and
communicating an identification signal to a client device based on the identifying being reliable, and not communicating an identification signal based on the identifying being not reliable.
2 . The method of claim 1 , wherein the frequency filter comprises a frequency weighting filter and/or a high pass filter.
3 . The method of claim 1 , wherein extracting the features comprises transforming the filtered signal into a sonogram representing sound energies associated with instants and frequencies.
4 . The method of claim 3 , further comprising converting the frequencies according to a non-linear frequency scale.
5 . The method of claim 4 , wherein the non-linear frequency scale is a Mel scale.
6 . The method of claim 4 , further comprising converting the sound energies according to a logarithmic scale.
7 . The method of claim 1 , further comprising, prior to step S5, normalizing the extracted features according to statistical moments of said extracted features.
8 . The method of claim 1 , wherein the classification model used in step S5 is one of a generative model or a discriminating model.
9 . The method of claim 1 , wherein the at least one label identifying a specific sound source comprises one of the following elements: a single label, a plurality of labels each associated with a probability.
10 . The method of claim 1 , further comprising, prior to step S4, a step S3, of detecting a sound event, the steps S4 and S5 being implemented only when a sound event is detected, the detection of a sound event depending on an indicator of an energy of the obtained sound signal and/or on a reception of a signaling of a sound event.
11 . The method of claim 10 , further comprising a step of notifying a sound event when a sound event is detected and/or when a signaling is received.
12 . A system for monitoring noise at a construction site, comprising:
a sound sensor configured to acquire a sound signal; and
a data processor configured to perform the steps of:
S1: obtaining a sound signal emitted at a construction site and acquired by a sound sensor;
S2: applying a frequency filter to the obtained sound signal, thereby obtaining a filtered signal;
S4: extracting features from the filtered signal;
S5: identifying a specific sound source by applying a classification model to the features extracted in step S4 and providing at least one label associated to the a specific sound source, wherein the specific sound source is a parent source as defined in a hierarchic model in which each sound source is either a parent source or a child source linked to a parent source; and
a post-processing step, subsequent to step S5, which comprises the following sub-steps:
evaluating a sound level of the obtained sound signal and comparing the evaluated sound level with a first predetermined threshold, said evaluating is then considered reliable if the evaluated sound level is greater than the first predetermined threshold;
comparing a value representing a level of confidence associated with the presence of the specific sound source in the obtained sound signal with a second predetermined threshold;
based on the value representing the level of confidence associated with the specific sound source being greater than the second predetermined threshold:
selecting, from one or more child sources linked to the specific sound source, the child source having a highest level of confidence associated with the presence of the child source in the obtained sound signal;
comparing the level of confidence associated with the presence of the selected child source in the obtained sound signal with a third predetermined threshold;
based on the level of confidence associated with the presence of the selected child source in the obtained sound signal being greater than the third predetermined threshold, the specific sound source is changed to the selected child source; and
based on the level of confidence associated with the presence of the selected child source in the obtained sound signal being lower than the third predetermined threshold, the specific sound source remains the parent source; and
based on the value representing the level of confidence associated with the specific sound source being lower than the second predetermined threshold, said identifying is considered not reliable;
communicating an identification signal to a client device based on the identifying is being reliable, and not communicating an identification signal based on the identifying being not reliable.
13 . The system of claim 12 , further comprising a detector configured to detect a sound event based on an indicator of an energy of the obtained sound signal and/or on the reception of a signaling of a sound event.
14 . The system of claim 13 , further comprising a mobile terminal configured to signal the sound event.