AppTek - INTERSPEECH 2020

October 25, 2020
AppTek

The AppTek Science Team will be presenting the following scientific papers this week (October 25-29 2020) at the INTERSPEECH 2020 virtual conference.  Dates and times as follows:

Robust Beam Search for Encoder-Decoder Attention Based Speech Recognition without Length Bias

Wei Zhou(RWTH Aachen University), Ralf Schlüter(Lehrstuhl Informatik 6, RWTH Aachen University) and Hermann Ney(RWTH Aachen University)
Speaker: Wei Zhou
Presentation Session and Time : Search for speech recognition[Tue-1-8], Tue-1-8-1 (GMT +8)
https://interspeech2020.baai.ac.cn/poster/1958


A New Training Pipeline for an Improved Neural Transducer

Albert Zeyer(Human Language Technology and Pattern Recognition Group (Chair of Computer Science 6), Computer Science Department, RWTH Aachen University), André Merboldt(RWTH Aachen University), Ralf Schlüter (Lehrstuhl Informatik 6, RWTH Aachen University) and Hermann Ney(RWTH Aachen University)
Speaker: Albert Zeyer
Presentation Session and Time : Training strategies for ASR[Wed-2-8], Wed-2-8-6 (GMT +8)
https://interspeech2020.baai.ac.cn/poster/1855


Early Stage LM Integration Using Local and Global Log-Linear Combination

Wilfried Michel(RWTH Aachen University), Ralf Schlüter(RWTH Aachen University) and Hermann Ney(RWTH Aachen University)
Speaker: Wilfried Michel
Presentation Session and Time : ASR neural network architectures and training II[Thu-1-2], Thu-1-2-6 (GMT +8)
https://interspeech2020.baai.ac.cn/poster/2675


Investigation of Large-Margin Softmax in Neural Language Modeling

Jingjing Huo(RWTH Aachen University), Yingbo Gao(RWTH Aachen University), Weiyue Wang(RWTH Aachen University), Ralf Schlüter(Lehrstuhl Informatik 6, RWTH Aachen University) and Hermann Ney(RWTH Aachen University)
Speaker: Jingjing Huo
Presentation Session and Time : Neural networks for language modeling[Thu-1-3], Thu-1-3-5 (GMT +8)
https://interspeech2020.baai.ac.cn/poster/1849

30-Year Leaders in Speech Technology
Find us on Social Media:
ABOUT APPTEK

AppTek provides an artificial intelligence and machine learning-based automatic speech recognition, machine translation and natural language understanding platform for organizations in a variety of markets, such as media and entertainment, call centers, government, enterprise business and others across the globe. Available via the cloud or on-premise, AppTek delivers the highest quality real-time streaming and batch speech technology solutions in the industry.   Featuring scientists and research engineers who are recognized amongst the best and most experienced in the world, the company’s solutions cover a wide array of languages, dialects, and channels.

SEARCH APPTEK.COM
Copyright 2020 AppTek    |    Privacy Policy      |       Terms of Service     |      Cookie Policy