people

Mark C. Beutnagel

Beutnagel, Mark C.
1 AT&T Way
Bedminster, NJ
Subject matter expert in AT&T Natural Voices®, text to speech, SSML, text markup, text normaliztion, unit selection

Started at Bell Labs in 1986 in the text-to-speech group.  Initially handled system administration for the group.  Did DSP32 programming for synthesis and TTS software support.  Projects included programmable phone call automation with TTS responses, TTS on a DOS laptop (with no floating point or built-in audio device), and conversion of Email to Audix messages using TTS.

In 1996 became part of the new text to speech research group at AT&T Labs.   Merging old and new technologies, helped create and commercialize AT&T Natural Voices®.  Up to NV 3.0, worked with development groups to hand off research inprovments.  Since NV 4.0 have been responsible for releases and updates.  Also work with organizations using NV within AT&T and provide tier-3 support for Wizzard Software, which handles much of the external sales and licensing for NV.

For many years now, have monitored and maintained the heavily-used Natural Voices public demo, which demonstrates, educates and promotes our technology. 

Most recently, I'm working with the TTS Research team to productize a new release of Natural Voices TTS which is reimplimented within Watson: a framework that already supports Recognition, Dialog Management and many other core technologies.

Projects
AT&T Natural VoicesTM Text-to-Speech, Natural Voices is AT&T's state-of-the-art text-to-speech product, taking text and producing natural-sounding, synthesized speech in a variety of voices and languages.

Technical Documents

Automatic Assessment of American English Lexical Stress using Machine Learning Algorithms
Yeon Kim, Mark Beutnagel
SLaTE-2011 workshop (Speech and Language Technology in Education),  2011.  [BIB]

Speech acts and dialog TTS
Ann Syrdal, Alistair Conkie, Yeon Kim, Mark Beutnagel
Seventh ISCA Speech Synthesis Workshop,  2010.  [BIB]

Patents

Speech Synthesis From Acoustic Units With Default Values Of Concatenation Cost, July 22, 2014
System And Method For Improving Synthesize Speech Interactions Of A Spoken Dialog System, October 22, 2013
Methods And Apparatus For Rapid Acoustic Unit Selection From A Large Speech Corpus, November 20, 2012
Methods And Apparatus For Rapid Acoustic Unit Selection From A Large Speech Corpus, December 27, 2011
Method And System For Aligning Natural And Synthetic Video To Speech Synthesis, November 30, 2010
Methods And Apparatus For Rapid Acoustic Unit Selection From A Large Speech Corpus, July 20, 2010
Methods and apparatus for rapid acoustic unit selection from a large speech corpus, May 6, 2008
Method and system for aligning natural and synthetic video to speech synthesis, April 29, 2008
Method and system for aligning natural and synthetic video to speech synthesis, September 19, 2006
Methods and apparatus for rapid acoustic unit selection from a large speech corpus, July 25, 2006
Advance TTS for facial animation, July 11, 2006
Employing Speech Models In Concatenative Speech Synthesis, September 27, 2005
Method and system for aligning natural and synthetic video to speech synthesis, March 1, 2005
Integration Of Talking Heads And Text-To-Speech Synthesizers For visual TTS, January 4, 2005
Methods and apparatus for rapid acoustic unit selection from a large speech corpus, March 2, 2004
Method and apparatus for rapid acoustic unit selection from a large speech corpus, February 24, 2004
Method And System For Aligning Natural And Synthetic Video To Speech Synthesis, May 20, 2003
Verbal, Fully Automatic Dictionary Updates By End-Users Of Speech Synthesis And Recognition Systems, June 20, 2000
graphviz

Connections

Graphviz