Future Speech Interfaces with Sensors and Machine Intelligence (Volume II)

Dear Colleagues,

Speech is the most spontaneous and natural means of communication—all the more so today, with the reality of instantaneous spoken communication to anywhere in the world. Speech is also becoming the preferred modality for interacting with mobile or fixed electronic devices. However, speech has certain drawbacks:

• Lack of privacy: speech can be easily captured by a third party;
• Lack of inclusivity: speech communication is problematic for the speech-impaired;
• Lack of robustness: speech understanding degrades rapidly in noisy conditions, both for humans and for machines;
• It is difficult to create high-performance speech-based human–machine interfaces.

The past decade has seen an increased interest in expanding the capabilities of speech interfaces, using solutions such as multi-modal input, novel acoustic and non-acoustic speech sensors, and sophisticated machine-learning techniques for speech recognition, speech synthesis, and natural language processing. This Special Issue, “Future Speech Interfaces with Sensors and Machine Intelligence”, strives to assemble, in a single volume, contributions from a wide range of speech-related fields, in order to broaden the scope of research in future speech interfaces and profit from the cross-fertilization yielded by bringing together ideas from disparate domains.

Contributions are solicited in the fields of:

• Multimodal and silent speech interfaces;
• Articulatory-to-acoustic mapping via “direct synthesis” or “recognition and synthesis”;
• Lip-reading applications;
• Novel acoustic and non-acoustic sensors for speech processing;
• Interfaces for enhanced speech inclusivity;
• Advanced machine learning techniques for future speech interfaces;
• Generative adversarial networks in speech research;
• Neural vocoders for future speech interfaces;
• Current state of the art in speech-based human–machine interfaces.

Prof. Dr. Bruce Denby
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 100 words) can be sent to the Editorial Office for announcement on this website.

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. Sensors 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 2600 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.

• multimodal speech
• silent speech interfaces
• lip reading
• speech sensors
• generative adversarial networks
• neural vocoders