Performance evaluation of perceptible impulsive noise detection methods based on auditory models
Abstract 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 performanc...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2025-01-01
|
| Series: | EURASIP Journal on Audio, Speech, and Music Processing |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13636-024-00389-9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832594488794546176 |
|---|---|
| author | Arda Özdoğru František Rund Karel Fliegel |
| author_facet | Arda Özdoğru František Rund Karel Fliegel |
| author_sort | Arda Özdoğru |
| collection | DOAJ |
| description | Abstract 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 ( $$A'$$ A ′ ). Evaluation criteria of the algorithms included the hit rate, false alarm rate, $$A'$$ 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 $$A'$$ 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. |
| format | Article |
| id | doaj-art-7c4bf26d030c4513b134538c9b1a2035 |
| institution | Kabale University |
| issn | 1687-4722 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EURASIP Journal on Audio, Speech, and Music Processing |
| spelling | doaj-art-7c4bf26d030c4513b134538c9b1a20352025-01-19T12:34:01ZengSpringerOpenEURASIP Journal on Audio, Speech, and Music Processing1687-47222025-01-012025111510.1186/s13636-024-00389-9Performance evaluation of perceptible impulsive noise detection methods based on auditory modelsArda Özdoğru0František Rund1Karel Fliegel2Department of Radioelectronics, Faculty of Electrical Engineering, Czech Technical University in PragueDepartment of Radioelectronics, Faculty of Electrical Engineering, Czech Technical University in PragueDepartment of Radioelectronics, Faculty of Electrical Engineering, Czech Technical University in PragueAbstract 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 ( $$A'$$ A ′ ). Evaluation criteria of the algorithms included the hit rate, false alarm rate, $$A'$$ 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 $$A'$$ 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.https://doi.org/10.1186/s13636-024-00389-9Audio processingClick detectionPerceptible clicksAuditory modelsPerformance evaluation |
| spellingShingle | Arda Özdoğru František Rund Karel Fliegel Performance evaluation of perceptible impulsive noise detection methods based on auditory models EURASIP Journal on Audio, Speech, and Music Processing Audio processing Click detection Perceptible clicks Auditory models Performance evaluation |
| title | Performance evaluation of perceptible impulsive noise detection methods based on auditory models |
| title_full | Performance evaluation of perceptible impulsive noise detection methods based on auditory models |
| title_fullStr | Performance evaluation of perceptible impulsive noise detection methods based on auditory models |
| title_full_unstemmed | Performance evaluation of perceptible impulsive noise detection methods based on auditory models |
| title_short | Performance evaluation of perceptible impulsive noise detection methods based on auditory models |
| title_sort | performance evaluation of perceptible impulsive noise detection methods based on auditory models |
| topic | Audio processing Click detection Perceptible clicks Auditory models Performance evaluation |
| url | https://doi.org/10.1186/s13636-024-00389-9 |
| work_keys_str_mv | AT ardaozdogru performanceevaluationofperceptibleimpulsivenoisedetectionmethodsbasedonauditorymodels AT frantisekrund performanceevaluationofperceptibleimpulsivenoisedetectionmethodsbasedonauditorymodels AT karelfliegel performanceevaluationofperceptibleimpulsivenoisedetectionmethodsbasedonauditorymodels |