tgoop.com/openit2/3436
Last Update:
👋 Шановні колеги!
ГО "УНІТ" запрошує долучитись до чергового наукового семінару! 🌍
🧠 Advances in On-Device Speech Recognition and Natural Language Processing
✅ Abstract: In this talk, Chanwoo Kim will give an overview of recent advances in on-device end-to-end Automatic Speech Recognition (ASR) and Natural Language Processing (NLP) algorithms, especially for commercial products. Conventional speech recognition systems based on Weighted Finite State Transducers (WFSTs) require a relatively large memory footprint, making it challenging to operate them for on-device applications for large vocabulary speech recognition tasks. Recent advances in end-to-end neural network technologies have made it possible to perform almost all speech recognition tasks on-device. On-device Natural Language Understanding (NLU) can be built using the Joint Bidirectional Encoder Representations from Transformers (BERT) approach, which classifies an user intention and identifies the slot values using a single BERT-based structure. Chanwoo will also provide an overview of how generative Language Models (LMs) can be employed for various NLU tasks. Finally, Chanwoo will describe recent research directions, such as generative speech/language multimodal approaches.
👨🏫 Bio: Chanwoo Kim is a professor at the Department of Artificial Intelligence at Korea University. Till 2023, he has been a corporate Executive Vice President (EVP) at Samsung Research leading the Language and Voice Team (LVT). He joined Samsung Research as a corporate Vice President (VP) heading the speech processing Lab in Feb. 2018. He has been leading research on end-to-end speech recognition, end-to-end text-to-speech (TTS), machine translation, Natural Language Understanding (NLU), Language Modeling (LM) and Question Answering (QA), speech enhancement, key-word spotting, and so on at Samsung Research. Most of these research outcomes have been commercialized for Samsung products. He was a senior software engineer at the Google speech team between Feb. 2013 and Feb. 2018. He worked on acoustic modeling for speech recognition systems and enhancing noise robustness using deep learning techniques. While working for Google, he contributed to data-augmentation and acoustic modeling of Google speech recognition systems. He contributed to the commercialization of various Google AI speakers and Google speech recognition systems. He was a speech scientist at Microsoft from Jan. 2011 to Jan. 2013. Dr. Kim received his Ph. D. from the Language Technologies Institute of the School of Computer Science at Carnegie Mellon University in Dec. 2010. Between 2003 and 2005 Dr. Kim was a Senior Research Engineer at LG Electronics, where he worked primarily on embedded signal processing and protocol stacks for multimedia systems.
🗓 Date: August, 15, 17:00 (Kyiv time)
📍 Format: online (Zoom + live stream at https://lnkd.in/dr8U7qkB)
✍️ Registration: https://forms.gle/gLf9NRwCdMPYa4zT6
#KharkivITCluster #news_from_members
👉 IT Student — будь в курсі IT-можливостей для тебе!
BY IT Student by Kharkiv IT Cluster
Share with your friend now:
tgoop.com/openit2/3436