Voice synthesis is a complex technical challenge requiring expertise spanning across linguistics, mathematics, signal processing, statistics, acoustics, and machine learning. The decades-long struggle to build human-sounding voices is testament to the enormous amount of effort required. Choose to work with the enormously talented team that includes not one, but two of the world's leading authorities on speech synthesis, creators of the industry-standard development platform for voice. If you hear a speech synthesis demo, it's almost certain that it was built on the foundation created by Cepstral's leaders. The work of Cepstral's team of programmers, speech scientists, support and development has led to the development of the first small footprint TTS system to produce unique, human sounding voices.



Kevin A. Lenzo
Chief Executive Officer and Co-founder

Kevin is ABD in the Ph.D. program in Robotics at Carnegie Mellon University, and is taking leave from his faculty position in the Institute for Software Research International (ISRI) at Carnegie Mellon in order to spend his full energy on Cepstral. He holds a Master of Science in Robotics from Carnegie Mellon University and a BSc in Computer and Information Science from The Ohio State University, summa cum laude, Phi Beta Kappa, with Distinction in CIS and Honors in the Liberal Arts.

In 1994, Kevin received a National Science Foundation Graduate Fellowship for his thesis work on prosody in speech synthesis. He has published over thirty articles on speech science and technology in conferences, journals, and books, and is on the editorial board of the International Journal of Speech Technology. He is co-author of the forthcoming book, "Building Synthetic Voices," on O'Reilly and Associates. He is the president and founder of the Perl Foundation and the Yet Another Society, successful non-profit organization for collaborative efforts in computer and information sciences, and the originator of the international Yet Another Perl Conferences. Kevin held a research position at Advanced Telecommunications Laboratories (ATR) Interpreting Telephony Lab (ITL) in Kyoto, Japan after graduating from Ohio State.



Alan W Black
Chief Scientist and Co-Founder

Alan W Black holds a BSc (Honors, first class) degree in Computer Science from Coventry University, a MSc in Knowledge Based Systems from University of Edinburgh and a PhD in Artificial Intelligence also from University of Edinburgh. He has published over 75 refereed conference papers, journal papers and books in the areas of lexicons, natural language processing and speech synthesis, and today is recognized by many as a key leader in the field of speech synthesis.

Dr. Black is a principal author of University of Edinburgh's Festival Speech Synthesis System. Festival is a multi-language, multi-platform speech synthesis workbench and text-to-speech delivery engine. Since its creation in 1996 it has grown to be the most prominent speech synthesis system in the field and becoming an integral part of almost all of the new breed of unit selection synthesizers developed in recent years. AT&T's NextGen was built around both the core of Festival and also work done by Dr. Black while he was working at ATR, in Japan. NextGen is licensed to SpeechWorks International, and further licensed to Microsoft as the synthesizer for their speech.net project. In addition he has also had appointments in IBM UK Research.