In the last century, the medium used to record audio evolved from mechanical and magnetic, to digital. Over the same period, the number of recordings drastically increased, capturing significant private and public history and culture (oral sources, concerts, radio broadcasting, etc.). Nowadays, we ubiquitously produce audio recordings, (e.g., by using social media, instant messaging, etc.) that may become part of our heritage. While the preservation of these massive datasets of audio recordings is a significant challenge, it also presents an opportunity both for scientific communities (computer scientists, musicologists, linguistics, etc.) and creative and cultural industries. Audio Signal Processing (ASP) opens new possibilities for preserving, analyzing, assessing, and valorizing audio recordings. Moreover, the availability of these large collections can facilitate the advancement of the ASP field itself, by providing complex real problems, new challenges as well as consistent training datasets.
The overall objective of this article collection is to explore recent developments in ASP for preserving, analyzing, and exploiting analog or digital audio archives or large music and speech collections. Despite the long tradition in this field, the recent advancement in artificial intelligence and human-computer interaction, new standards, and drastically enhanced computational power, open new opportunities for valorizing and exploiting this precious and valuable data. Furthermore, new challenges must be faced such as environmental and sustainability issues, gender equality, respect for ethnic and religious minorities, as well as fairness. Original research, perspective papers, reviews as well as technology and case study reports will delineate the state of the art, provide further perspective, and draw together new opportunities for cultural and creative industries, academia, and citizens.
The scope of this Research Topic covers all audio signal processing topics aimed to preserve, exploit, and valorize analog and digital audio recordings. This includes, but is not limited to:
• ASP for:
- creative and cultural industrial applications
- analog and digital audio (music, speech, and other sounds) archives
- live performance and multimedia installations
- web audio applications
• ASP from creation to perception
• Audio content analysis
• Audio restoration and enhancement
• Audio detection, recognition, classification, and diarization
• Artificial intelligence for analog and digital audio recordings
• Computational musicology
• Ethics, gender innovation, and fairness in audio archives
• Human-computer interaction and audio archives
• Music information retrieval
• Perception models, quality assessment, and aesthetics
• Standards including ASP
• Sustainability and environmental aspects in audio archives
• Web and cloud technologies for audio archives
Sergio Canazza is Founding Member and CEO of Audio Innova srl. All other Topic Editors declare no competing interests with regards to the Research Topic subject.
In the last century, the medium used to record audio evolved from mechanical and magnetic, to digital. Over the same period, the number of recordings drastically increased, capturing significant private and public history and culture (oral sources, concerts, radio broadcasting, etc.). Nowadays, we ubiquitously produce audio recordings, (e.g., by using social media, instant messaging, etc.) that may become part of our heritage. While the preservation of these massive datasets of audio recordings is a significant challenge, it also presents an opportunity both for scientific communities (computer scientists, musicologists, linguistics, etc.) and creative and cultural industries. Audio Signal Processing (ASP) opens new possibilities for preserving, analyzing, assessing, and valorizing audio recordings. Moreover, the availability of these large collections can facilitate the advancement of the ASP field itself, by providing complex real problems, new challenges as well as consistent training datasets.
The overall objective of this article collection is to explore recent developments in ASP for preserving, analyzing, and exploiting analog or digital audio archives or large music and speech collections. Despite the long tradition in this field, the recent advancement in artificial intelligence and human-computer interaction, new standards, and drastically enhanced computational power, open new opportunities for valorizing and exploiting this precious and valuable data. Furthermore, new challenges must be faced such as environmental and sustainability issues, gender equality, respect for ethnic and religious minorities, as well as fairness. Original research, perspective papers, reviews as well as technology and case study reports will delineate the state of the art, provide further perspective, and draw together new opportunities for cultural and creative industries, academia, and citizens.
The scope of this Research Topic covers all audio signal processing topics aimed to preserve, exploit, and valorize analog and digital audio recordings. This includes, but is not limited to:
• ASP for:
- creative and cultural industrial applications
- analog and digital audio (music, speech, and other sounds) archives
- live performance and multimedia installations
- web audio applications
• ASP from creation to perception
• Audio content analysis
• Audio restoration and enhancement
• Audio detection, recognition, classification, and diarization
• Artificial intelligence for analog and digital audio recordings
• Computational musicology
• Ethics, gender innovation, and fairness in audio archives
• Human-computer interaction and audio archives
• Music information retrieval
• Perception models, quality assessment, and aesthetics
• Standards including ASP
• Sustainability and environmental aspects in audio archives
• Web and cloud technologies for audio archives
Sergio Canazza is Founding Member and CEO of Audio Innova srl. All other Topic Editors declare no competing interests with regards to the Research Topic subject.
