-
1.发明申请FRAME SKIPPING WITH EXTRAPOLATION AND OUTPUTS ON DEMAND NEURAL NETWORK FOR AUTOMATIC SPEECH RECOGNITION 审中-公开具有自动语音识别需求神经网络的外推和输出的框架
公开(公告)号：WO2016048486A1
公开(公告)日：2016-03-31
申请号：PCT/US2015/045750
申请日：2015-08-18
Applicant: INTEL CORPORATION
Inventor： BAUER, Josef , ROZEN, Piotr , STEMMER, Georg
IPC: G10L15/16
Abstract: Techniques related to implementing neural networks for speech recognition systems are discussed. Such techniques may include implementing frame skipping with approximated skip frames and/or distances on demand such that only those outputs needed by a speech decoder are provided via the neural network or approximation techniques.
Abstract translation: 讨论了与语音识别系统实现神经网络有关的技术。 这样的技术可以包括实现具有近似跳过帧和/或按需的距离的跳帧，使得仅通过神经网络或近似技术提供语音解码器所需的那些输出。
-
2.发明申请METHOD AND SYSTEM OF AUTOMATIC SPEECH RECOGNITION WITH DYNAMIC VOCABULARIES 审中-公开自动语音识别与动态VOCABULARIES的方法和系统
公开(公告)号：WO2016209493A1
公开(公告)日：2016-12-29
申请号：PCT/US2016/034059
申请日：2016-05-25
Applicant: INTEL CORPORATION
Inventor： HOFER, Joachim , STEMMER, Georg , BAUER, Josef
CPC classification number: G06F17/274 , G06F17/277 , G06F17/2775 , G10L15/083 , G10L15/19
Abstract: A system, article, and method of automatic speech recognition with dynamic vocabularies is described herein.
Abstract translation: 本文描述了具有动态词汇表的自动语音识别的系统，文章和方法。
-
Search Results
2
records
(took 0.007 seconds)
