Search

Reference-free audio quality assessment is a valuable tool in many areas, such as audio recordings, vinyl production, and communication systems. Therefore, evaluating the reliability and performance of such tools is crucial. This paper builds on previous research by analyzing the performance of four additional algorithms in detecting perceptible impulsive noise (clicks) based on auditory models. We compared the results of eight algorithms, hypothesizing that computationally simpler algorithms could perform as well as more complex ones. We obtained a set of audio signals, with and without clicks, annotated by human subjects from a publicly available dataset. Audio signal sets are categorized based on the obtained annotation results to train the algorithms for different levels of the experiments. Experiments containing cross-validation are done for multiple parameters of algorithms. The algorithm training is based on maximizing a discriminability metric ( A ′ ). Evaluation criteria of the algorithms included the hit rate, false alarm rate, A ′ , and computational time. Our findings indicate that computationally simpler auditory models have performed as well as computationally more complex ones, while conventional models exhibit lower performance. Conclusively, the ERBlet transform based algorithm demonstrated superior performance in terms of A ′ and robustness. This paper provides insights into the capabilities of auditory models in a practical use case of perceptible click detection. The results presented here can help research and develop such algorithms for vinyl production, audio archiving, podcasting, music production, and telecommunications. [ABSTRACT FROM AUTHOR]

This article reports an unsupervised approach for estimation of the tool condition in precision machining processes. Three campaigns of run-to-failure experiments were conducted on different machines of varying capabilities to develop a generalized solution that is independent of machine intricacies and settings. The proposed approach uses real-time sensory information, such as vibration and spindle power, to infer the tool condition. The proposed approach utilizes distance metrics, Mahalanobis and Euclidean, determined from the sensory information as health indicators of tool wear, which are shown to be strongly correlated with the tool condition. The health indicators have a high correlation coefficient of 0.94 with tool wear measurements, across machines. Unsupervised approaches, such as Jenks Natural Breaks and K-means clustering, use these health indicators to estimate the tool condition. The developed unsupervised approach is also benchmarked using the IEEE PHM 2010 data. A Goodness of Variance Fit of 0.95 and 0.96 is achieved in classifying tool wear across the machining tests conducted in the three campaigns and IEEE PHM 2010 data, respectively. We highlight the explainability of the methods which improve the ease of deployment and engender trust. [ABSTRACT FROM AUTHOR]