Advances in Acoustic, Speech, and Signal Processing and Recognition

Dear Colleagues,

This is a Special Issue on the latest advancements in Acoustic, Speech, and Signal Processing and Recognition. The most important objective of this Special Issue is to bring together the latest techniques that aim at making significant improvements to accuracy, efficiency, model size, processing speed, and other practical aspects related to improving the quality of the signals of interest and to provide superior recognition techniques. Original research in preprocessing and feature extraction, as well as back-end systems such as modeling and machine learning techniques, is welcome. Of course, End-to-End systems are also entertained, if they are not treated as black-box processing. The Special Issue aims at exploring modern techniques in the listed areas, such that there is a definite theoretical and technical basis, and the justification for the improvements observed in any experiments is thoroughly discussed. Presentation of learning techniques through domain transfers is also highly encouraged.

I would like to invite you to submit your latest research results in the following or related areas. The objective is to include the most recent advancements in Acoustic, Speech, and Signal Processing and Recognition. This Special Issue concentrates on techniques designed to improve recognition through new modeling or new signal processing techniques. The overall aim is to compile a list of new approaches that address accuracy, efficiency, model size, processing speed, and other practical considerations. The following is a suggested list of topics that may be considered. However, if you believe that you have results on related topics that would fit the above objective, you are more than welcome to submit your original research.

• Automatic Speech Recognition (ASR);
• Speaker Recognition – ID, Verification, and Classification;
• Speech Synthesis and Text-to-Speech (TTS);
• Speech Enhancement and Denoising;
• Acoustic Echo Cancellation (AEC) and Active Noise Control (ANC);
• Noise Reduction and Suppression Techniques;
• Source Localization, Microphone Arrays, Beamforming;
• Far-Field Speech Processing and Recognition;
• Feature Extraction (e.g., MFCC, LPC, PLP, Wavelet Transforms);
• Modern Acoustic Modeling (e.g., SSM, Conformers, Transformers, GRU, LSTM, TDNN, PINN, new architectures);
• Language Modeling for Speech Systems;
• Keyword and Spoken Term Detection (e.g., low power, compact models);
• Emotion and Paralinguistic Recognition in Speech;
• Prosody and Intonation Analysis;
• Transfer Learning Techniques (e.g., Inter-Domain) in Acoustic and Signal Recognition;
• Music Recognition (e.g., mode recognition, voice separation, timbre transfer, automatic transcription);
• Robust Recognition in Noisy Environments;
• End-to-End Speech Recognition Systems;
• Deep Learning for Acoustic Signal Processing;
• New Machine Learning Architectures (including but not limited to new NN Architectures);
• Large Language Models (LLMs) in Speech Recognition and Diarization;
• Speaker Diarization, Audio Indexing, and Retrieval;
• Privacy and Security in Speaker Data (e.g., Voice Spoofing, Obfuscation);
• Multimodal Signal Processing (Audio-Visual);
• Code-Switching and Multilingual Speech Recognition;
• Accurate Word and Phone Alignment (timestamp estimation);
• Postprocessing (e.g., Punctuation and Case Correction, Content-Based output selection/modification);
• Real-Time and Low-Latency Signal Processing;
• Applications in Hearing Aids and Assistive Technologies;
• Medical Diagnosis through Speech Processing;
• Children’s Speech Recognition;
• Acoustic Event and Scene Classification;
• Voice Conversion and Voice Cloning;
• Signal Recognition, such as in Structural and Machine Health Monitoring, Earthquake Warning, Medical Signal Recognition, etc.

I look forward to receiving your contributions.

Prof. Dr. Homayoon Beigi
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.