Speech technologies at Google: An overview
Pedro J. Moreno
Research Engineering Director
Friday, October 18, 2019
101 Walter Library
IEEE SPS Society Distinguished Lecture Series
NOTE: Registration (required)
Please register by emailing Sandy Jobes your names and affiliation at Sandy_Jobes@starkey.com so that we can plan for the conference room, snacks and beverage in advance.
In this talk I'll give an overview of google speech technologies with a bigger focus on speech recognition. I'll describe the genesis of speech activities at google, its evolution over the last 15 years, and where speech technologies are moving in the future. I will then spend a bit more time on the current state of the art in neural networks for speech modeling: sequence to sequence neural nets. Sequence to sequence modeling bring some interesting advantages and simplifications in speech recognition, synthesis and voice conversion. Tasks that before were hard like multi-linguality are much simplified now. I'll finish the talk describing our new work to help users with dysarthric speech, PARROTRON.
Dr. Pedro J. Moreno completed his Ph.D. degree in Electrical and Computer Engineering at Carnegie Mellon University in 1996, and his Telecommunications Engineering degree at Universidad Politecnica de Madrid, Spain in 1986. Prior to joining Google, Dr. Moreno held a research scientist position at HP Labs where he led research in audio mining and search.
Dr. Moreno leads a team of 50 engineers and scientist at the languages modeling group, part of the Speech team at Google. His team oversees the deployment of speech recognition services in all supported languages and improving their quality. His team has pioneered the use of context signals in speech recognition systems. Dr. Moreno has been involved in building the google technology behind every voice-activated application that is used by billions of users in over 100 languages every day.
Dr. Moreno’s research interests include signal processing, machine learning, statistical modeling with applications to speech processing. He has published over 100 well-cited publications in several conferences and journals and holds several patents to his name.
- "Array processing and beamforming with Kronecker products," Israel Cohen, Technion – Israel Institute of Technology Haifa, Israel., Oct. 14, 3:00 pm, 401/402 Walter Library
- "Distributed Stochastic Optimization with Variance Reduction and Gradient Tracking," Yuejie Chi, Carnegie Mellon, Oct. 15, 1:00 pm, 401/402 Walter Library
- "Speech technologies at Google: An overview," Pedro J. Moreno, Research Engineering Director Google, Oct. 18, 3:00 pm, 101 Walter Library
DTC Professer Tian He named 2018 ACM Fellow
Professor Tian He has been named a 2018 Association for Computing Machinery (ACM) Fellow. He has been selected his contributions to wireless networks, sensing systems, and Internet of Things (IoT), areas in which he has made many influential and landmark contributions. More on Tian He.
Digital Technology Center
499 Walter Library, 117 Pleasant Street SE, Minneapolis, MN 55455
P: (612) 624-9510