Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Hoffmeister, Bjorn"'
Publikováno v:
Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2019, pages 6640-6644
Conventional far-field automatic speech recognition (ASR) systems typically employ microphone array techniques for speech enhancement in order to improve robustness against noise or reverberation. However, such speech enhancement techniques do not al
Externí odkaz:
http://arxiv.org/abs/1903.05299
Publikováno v:
Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2019, page 6635-6639
The use of spatial information with multiple microphones can improve far-field automatic speech recognition (ASR) accuracy. However, conventional microphone array techniques degrade speech enhancement performance when there is an array geometry misma
Externí odkaz:
http://arxiv.org/abs/1903.06539
Language models (LM) for interactive speech recognition systems are trained on large amounts of data and the model parameters are optimized on past user data. New application intents and interaction types are released for these systems over time, imp
Externí odkaz:
http://arxiv.org/abs/1812.04647
Autor:
Kumar, Anjishnu, Gupta, Arpit, Chan, Julian, Tucker, Sam, Hoffmeister, Bjorn, Dreyer, Markus, Peshterliev, Stanislav, Gandhe, Ankur, Filiminov, Denis, Rastrow, Ariya, Monson, Christian, Kumar, Agnika
This paper presents the design of the machine learning architecture that underlies the Alexa Skills Kit (ASK) a large scale Spoken Language Understanding (SLU) Software Development Kit (SDK) that enables developers to extend the capabilities of Amazo
Externí odkaz:
http://arxiv.org/abs/1711.00549
Autor:
Haeb-Umbach, Reinhold, Watanabe, Shinji, Nakatani, Tomohiro, Bacchiani, Michiel, Hoffmeister, Bjorn, Seltzer, Michael L., Zen, Heiga, Souden, Mehrez
Publikováno v:
IEEE Signal Processing Magazine; Nov2019, Vol. 36 Issue 6, p111-124, 14p
Publikováno v:
2015 IEEE 14th International Conference on Machine Learning & Applications (ICMLA); 2015, p369-374, 6p