Four Papers Accepted at INTERSPEECH 2022

The AppTek Science team is proud to announce that four papers have been accepted at the 23rd INTERSPEECH Conference.  INTERSPEECH is the world’s largest and most comprehensive conference on the science and technology of spoken language processing. The INTERSPEECH conferences emphasize interdisciplinary approaches addressing all aspects of speech science and technology, ranging from basic theory to advanced applications.

‍

Following are the accepted publications:

"Efficient Training of Neural Transducer for Speech Recognition"

Wei Zhou, Wilfried Michel, Ralf Schlüter, and Hermann Ney.

‍

"Automatic Learning of Subword Dependent Model Scales"

Felix Meyer, Wilfried Michel, Mohammad Zeineldeen, Ralf Schlüter, and Hermann Ney.

‍

"Improving the Training Recipe for a Robust Conformer-based Hybrid Model"

Mohammad Zeineldeen, Jingjing Xu, Christoph Lüscher, Ralf Schlüter and Hermann Ney

‍

"Self-Normalized Importance Sampling for Neural Language Modeling"

Zijian Yang, Yingbo Gao, Alexander Gerstenberger, Jintao Jiang, Ralf Schlüter, and Hermann Ney

‍

This year's INTERSPEECH conference will be held September 18 to 22, 2022 at Songdo ConvensiA, in Incheon, Korea, under the theme “Human and Humanizing Speech Technology”.

‍

For more information, visit the INTERSPEECH 2022 website.

‍

‍