We work to help voiceless people regain their own, natural-sounding voice.
Our non-invasive silent speech technology will be a breakthrough in speech rehabilitation and beyond.
We are Altavo, the artificial voice company.
We are a medical device startup based in Dresden, Germany. Our guiding star: harnessing the power of machine learning and state-of-the-art sensor technology to improve the lives of people who have lost their voice.
The first group to benefit are patients who have lost their voice box because of tumor surgery, a procedure known as laryngectomy. But there are many more potential applications of our technology, both in speech rehabilitation and in non-medical fields.
We come from many different fields: medical device development & marketing, computer science, artificial intelligence, radio frequency engineering, signal processing, speech technology, linguistics & speech therapy, regulatory affairs, and quality management.
We share one passion: to turn state-of-the-art technologies into products that improve patients’ quality of life.
Rudolf is a physicist by training. Formerly with ZEISS, he has 20+ years of experience in medical device innovation and marketing. His specialty: co-creating product concepts with clinicians and patients.
Timo is a computer scientist and AI technologist. At Nvidia and ZEISS, he gathered 15+ years of experience in machine learning and the hardware it runs on. His specialty: turning AI magic into real-world products.
Falk studied computer science at TU Dresden. Having built R&D organizations at Agfa and ZEISS, he has 15+ years of experience in medical SW management. His specialty: building teams that let people thrive.
Lydia is a clinical speech scientist. As a certified therapist, she has 6+ years of experience working with patients with speech and language disorders in clinicial settings. Her specialty: putting patients first in everything we do.
Stephanie is a regulatory affairs specialist with a mechatronics background. She has built and led medical device RA teams for 12+ years. Her specialty: removing any (real or imagined) regulatory obstacle.
Dominik is an electrical engineer by training. He has 10+ year experience developing RF hardware and software at National Instruments and Konrad. His specialty: getting the design “just right”.
Ulrike is a linguist and clinical speech scientist. She has 10+ years of experience working in the medical field of ENT with hearing impaired, language and voice disordered patients. Her specialty: Translating user needs into product requirement.
Sebald is a seasoned quality manager with a degree in mathematics. He has 16+ years of QM leadership experience for medical software. His specialty: designing processes that make QM painless.
Paul is a physicist and expert in the field of deep learning. He is currently pursuing the Ph.D. degree with Technische Universität Dresden. His specialty: Articulatory and neural speech synthesis.
Martin is an electrical engineer with 10+ years of experience in RF electronics. He has developed things that fly to asteroids and things that make quantum physicists happy. His specialty: thinking “outside the box”.
Carsten is a software developer and software architect. With 20+ years of experience acquired while working at Siemens and Zeiss, he has profound knowledge and understanding of on-premise and cloud software. His specialty: Designing and implementing complex systems as well as running them smoothly.
Keith is an embedded software specialist. He has decades of experience developing the firmware layer of complex medical systems. His specialty: navigating the tricky terrain where software meets hardware.
Christoph is an electrical engineer specializing in speech technology. He has in-depth and first-hand experience in the development of several “silent speech” technologies. His specialty: bridging the gap between speech production, sensor technology and algorithms.
RF sensing lets us see inside the vocal tract.
Our non-invasive sensor technology can detect and characterize silent articulation movement. State-of-the-art deep neural networks have the power to convert these signals into audible speech in real time.
Chair of Speech Technology and Cognitive Systems
Technical University Dresden
Peter Birkholz is an expert for silent speech interfaces, speech technology, and speech production.
He is computer scientist by training and professor at the TU Dresden since 2014.
Adjunct professor, consultant, science book author, former CEO Carl Zeiss AG
Supervisory board chairman: KIT, Carl Zeiss Meditec AG (honorary)
Supervisory board member: Robert Bosch GmbH
Trustee: Robert Bosch Industrietreuhand KG
Board of Management: OttoBock SE
Department Head Phoniatrics and Pediatric Audiology,
Clinic for Ear-, Nose-, Throat Diseases, Head- and Neck Surgery
University Medicine Greifswald
Head of Department, ENT / Plastic Surgery
SRH Wald-Klinikum Gera
Expert on Laryngology, Neurolaryngology, Laryngeal Pacing
Head, Department of ENT, Head and Neck Surgery
Municipal Hospital Dresden
Staff member, laboratory for voice research
Dresden College of Music
We are collaborating closely with TU Dresden.
We have a broad technology partnership with the Chair of Speech Technology and Cognitive Systems and the Chair of Radio Frequency and Photonics Engineering at Technische Universität Dresden.
Our joint project “Promise-AI” is supported by a research grant from the German Federal Ministry of Education and Research (BMBF).
Our joint project “MUSIK” is supported by a research grant from Sächsische Aufbaubank (SAB).
and others …
We would like to hear from you.
Interested in joining our team, collaborating, or partnering with us? Send us a note.