About this Research Topic
Processing audio signals to extract speech, remove noise and reverberation, separate multiple talkers experiences a large amount of attention, even after being decades old research topic. Recently, the number of applications for such technologies is growing rapidly with the emerging market of smart devices, wearables, and augmented reality devices, which creates acoustic use cases for remote communication and voice control applications, where obtaining speech signals with high intelligibility and quality is challenging.
The advent of deep learning in audio processing created a significant additional boost in performance of speech and audio processing techniques. Nowadays, this research field experiences an interesting transition, where deep learning-based, as well as traditional statistical model-based techniques, are welcome, show different properties and can be used separately, in a hybrid way, or should be carefully evaluated against each other. This Research Topic will comprise advances of state-of-the-art and novel audio and speech processing algorithms.
In this Research Topic, we are seeking submissions in the following areas, but not limited to:
• Single- and multi-channel speech enhancement
• Speech and sound source separation
• Deep learning for speech enhancement
• Intelligibility enhancement for normal hearing, hearing impaired, or machine listeners
• Sound source localization and tracking
• Speech activity detection
• Detection or classification of speech or signal-related parameters like reverberation time, signal-to-noise ratio, etc.
Topic editor Sebastian Braun is employed by Microsoft. All other Topic Editors declare no competing interests with regards to the Research Topic subject.
The advent of deep learning in audio processing created a significant additional boost in performance of speech and audio processing techniques. Nowadays, this research field experiences an interesting transition, where deep learning-based, as well as traditional statistical model-based techniques, are welcome, show different properties and can be used separately, in a hybrid way, or should be carefully evaluated against each other. This Research Topic will comprise advances of state-of-the-art and novel audio and speech processing algorithms.
In this Research Topic, we are seeking submissions in the following areas, but not limited to:
• Single- and multi-channel speech enhancement
• Speech and sound source separation
• Deep learning for speech enhancement
• Intelligibility enhancement for normal hearing, hearing impaired, or machine listeners
• Sound source localization and tracking
• Speech activity detection
• Detection or classification of speech or signal-related parameters like reverberation time, signal-to-noise ratio, etc.
Topic editor Sebastian Braun is employed by Microsoft. All other Topic Editors declare no competing interests with regards to the Research Topic subject.
Keywords: speech enhancement, noise reduction, dereverberation, echo cancellation, beamforming, speech separation
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
