Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: López-Chilet, Álvaro, Liu, Zhaoyi, Gómez, Jon Ander, Alvarez, Carlos, Ortiz, Marivi Alonso, Mesa, Andres Orejuela, Newton, David, Wolf-Monheim, Friedrich, Michiels, Sam, Hughes, Danny
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2402.18204
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909122583068672
author López-Chilet, Álvaro
Liu, Zhaoyi
Gómez, Jon Ander
Alvarez, Carlos
Ortiz, Marivi Alonso
Mesa, Andres Orejuela
Newton, David
Wolf-Monheim, Friedrich
Michiels, Sam
Hughes, Danny
author_facet López-Chilet, Álvaro
Liu, Zhaoyi
Gómez, Jon Ander
Alvarez, Carlos
Ortiz, Marivi Alonso
Mesa, Andres Orejuela
Newton, David
Wolf-Monheim, Friedrich
Michiels, Sam
Hughes, Danny
contents This paper proposes a method for Acoustic Constrained Segmentation (ACS) in audio recordings of vehicles driven through a production test track, delimiting the boundaries of surface types in the track. ACS is a variant of classical acoustic segmentation where the sequence of labels is known, contiguous and invariable, which is especially useful in this work as the test track has a standard configuration of surface types. The proposed ConvDTW-ACS method utilizes a Convolutional Neural Network for classifying overlapping image chunks extracted from the full audio spectrogram. Then, our custom Dynamic Time Warping algorithm aligns the sequence of predicted probabilities to the sequence of surface types in the track, from which timestamps of the surface type boundaries can be extracted. The method was evaluated on a real-world dataset collected from the Ford Manufacturing Plant in Valencia (Spain), achieving a mean error of 166 milliseconds when delimiting, within the audio, the boundaries of the surfaces in the track. The results demonstrate the effectiveness of the proposed method in accurately segmenting different surface types, which could enable the development of more specialized AI systems to improve the quality inspection process.
format Preprint
id arxiv_https___arxiv_org_abs_2402_18204
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ConvDTW-ACS: Audio Segmentation for Track Type Detection During Car Manufacturing
López-Chilet, Álvaro
Liu, Zhaoyi
Gómez, Jon Ander
Alvarez, Carlos
Ortiz, Marivi Alonso
Mesa, Andres Orejuela
Newton, David
Wolf-Monheim, Friedrich
Michiels, Sam
Hughes, Danny
Sound
Audio and Speech Processing
This paper proposes a method for Acoustic Constrained Segmentation (ACS) in audio recordings of vehicles driven through a production test track, delimiting the boundaries of surface types in the track. ACS is a variant of classical acoustic segmentation where the sequence of labels is known, contiguous and invariable, which is especially useful in this work as the test track has a standard configuration of surface types. The proposed ConvDTW-ACS method utilizes a Convolutional Neural Network for classifying overlapping image chunks extracted from the full audio spectrogram. Then, our custom Dynamic Time Warping algorithm aligns the sequence of predicted probabilities to the sequence of surface types in the track, from which timestamps of the surface type boundaries can be extracted. The method was evaluated on a real-world dataset collected from the Ford Manufacturing Plant in Valencia (Spain), achieving a mean error of 166 milliseconds when delimiting, within the audio, the boundaries of the surfaces in the track. The results demonstrate the effectiveness of the proposed method in accurately segmenting different surface types, which could enable the development of more specialized AI systems to improve the quality inspection process.
title ConvDTW-ACS: Audio Segmentation for Track Type Detection During Car Manufacturing
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2402.18204