Abstract
BackgroundQualitative self- or parent-reports used in assessing children’s behavioral disorders are often inconvenient to collect and can be misleading due to missing information, rater biases, and limited validity. A data-driven approach to quantify behavioral disorders could alleviate these concerns. This study proposes a machine learning approach to identify screams in voice recordings that avoids the need to gather large amounts of clinical data for model training.ObjectiveThe goal of this study is to evaluate if a machine learning model trained only on publicly available audio data sets could be used to detect screaming sounds in audio streams captured in an at-home setting.MethodsTwo sets of audio samples were prepared to evaluate the model: a subset of the publicly available AudioSet data set and a set of audio data extracted from the TV show Supernanny, which was chosen for its similarity to clinical data. Scream events were manually annotated for the Supernanny data, and existing annotations were refined for the AudioSet data. Audio feature extraction was performed with a convolutional neural network pretrained on AudioSet. A gradient-boosted tree model was trained and cross-validated for scream classification on the AudioSet data and then validated independently on the Supernanny audio.ResultsOn the held-out AudioSet clips, the model achieved a receiver operating characteristic (ROC)–area under the curve (AUC) of 0.86. The same model applied to three full episodes of Supernanny audio achieved an ROC-AUC of 0.95 and an average precision (positive predictive value) of 42% despite screams only making up 1.3% (n=92/7166 seconds) of the total run time.ConclusionsThese results suggest that a scream-detection model trained with publicly available data could be valuable for monitoring clinical recordings and identifying tantrums as opposed to depending on collecting costly privacy-protected clinical data for model training.
Highlights
One of the challenges in studying and diagnosing children with behavioral disorders is the relative unreliability of the information available
The same model applied to three full episodes of Supernanny audio achieved an receiver operating characteristic (ROC)-area under the curve (AUC) of 0.95 and an average precision of 42% despite screams only making up 1.3% (n=92/7166 seconds) of the total run time
We present an approach for detecting screams in home audio recordings with the aim of segmenting those recordings to review clinically relevant portions
Summary
One of the challenges in studying and diagnosing children with (potential) behavioral disorders is the relative unreliability of the information available. A quantitative, data-driven approach for evaluating behavioral problems would alleviate the need to rely on these potentially inaccurate reports. With this goal in mind, our study focuses on detecting human screaming within continuous audio recording from inside a family’s home. Segmenting home audio to capture screams, with some postprocessing, could eventually allow researchers to use the scream as a proxy for temper tantrums or negative interactions between family members [8] Analyzing these interactions would allow clinicians to assess family relationships in a more objective manner than direct self-report [9], but identifying the segments manually would be tedious and time intensive. This study proposes a machine learning approach to identify screams in voice recordings that avoids the need to gather large amounts of clinical data for model training
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
