Zobrazeno 1 - 10
of 27
pro vyhledávání: '"Van Segbroeck, Maarten"'
Streaming Automatic Speech Recognition (ASR) in voice assistants can utilize prefetching to partially hide the latency of response generation. Prefetching involves passing a preliminary ASR hypothesis to downstream systems in order to prefetch and ca
Externí odkaz:
http://arxiv.org/abs/2305.13794
Autor:
Guo, Jinxi, Tiwari, Gautam, Droppo, Jasha, Van Segbroeck, Maarten, Huang, Che-Wei, Stolcke, Andreas, Maas, Roland
In this work, we propose a novel and efficient minimum word error rate (MWER) training method for RNN-Transducer (RNN-T). Unlike previous work on this topic, which performs on-the-fly limited-size beam-search decoding and generates alignment scores f
Externí odkaz:
http://arxiv.org/abs/2007.13802
Autor:
Van Segbroeck, Maarten, Mallidih, Harish, King, Brian, Chen, I-Fan, Chadha, Gurpreet, Maas, Roland
Acoustic models in real-time speech recognition systems typically stack multiple unidirectional LSTM layers to process the acoustic frames over time. Performance improvements over vanilla LSTM architectures have been reported by prepending a stack of
Externí odkaz:
http://arxiv.org/abs/2007.00131
Autor:
Van Segbroeck, Maarten, Zaid, Ahmed, Kutsenko, Ksenia, Huerta, Cirenia, Nguyen, Tinh, Luo, Xuewen, Hoffmeister, Björn, Trmal, Jan, Omologo, Maurizio, Maas, Roland
We present a speech data corpus that simulates a "dinner party" scenario taking place in an everyday home environment. The corpus was created by recording multiple groups of four Amazon employee volunteers having a natural conversation in English aro
Externí odkaz:
http://arxiv.org/abs/1909.13447
Publikováno v:
In Neuron 3 May 2017 94(3):465-485
Publikováno v:
In Computer Speech & Language March 2016 36:330-346
Publikováno v:
In Speech Communication 2009 51(11):1124-1138
Autor:
Van Segbroeck, Maarten
De mogelijkheden om spraakherkenning in ons dagelijkse leven te integrer en nemen meer en meer toe. Met de stijgende populariteit van apparaten z oals mobiele telefoons, computers, muziekspelers en navigatiesystemen, i s de laatste jaren de vraag naa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______1131::8dd526231d4906fd006064d13031a971
https://lirias.kuleuven.be/handle/123456789/253426
https://lirias.kuleuven.be/handle/123456789/253426
Missing Data Theory (MDT) has shown to improve the robustness of automatic speech recognition (ASR) systems. A crucial part in a MDT-based recogniser is the computation of the reliability masks from noisy data. For each component of the feature vecto
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______1131::ef1c726e99bcae49744869bed5354c93
https://lirias.kuleuven.be/handle/123456789/175494
https://lirias.kuleuven.be/handle/123456789/175494
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.