-
公开(公告)号：US20190103100A1
公开(公告)日：2019-04-04
申请号：US15721486
申请日：2017-09-29
申请人： PIOTR ROZEN , TOBIAS BOCKLET , JAKUB NOWICKI , MUNIR GEORGES
发明人： PIOTR ROZEN , TOBIAS BOCKLET , JAKUB NOWICKI , MUNIR GEORGES
IPC分类号： G10L15/22 , G10L15/30 , G10L15/08 , G10L15/183
摘要： Techniques are disclosed for client-side analysis of audio samples to identify one or more characteristics associated with captured audio. The client-side analysis may then allow a user device, e.g., a smart phone, laptop computer, in-car infotainment system, and so on, to provide the one or more identified characteristics as configuration data to a voice recognition service at or shortly after connection with the same. In turn, the voice recognition service may load one or more recognition components, e.g., language models and/or application modules/engines, based on the received configuration data. Thus, latency may be reduced based on the voice recognition engine having “hints” that allow components to be loaded without necessarily having to process audio samples first. The reduction of latency may reduce processing time relative to other approaches to voice recognitions systems that exclusively perform server-side context recognition/classification.
-
2.发明申请Frame Skipping With Extrapolation and Outputs On Demand Neural Network For Automatic Speech Recognition 有权框架跳过与外推和输出点播神经网络自动语音识别公开(公告)号：US20160086600A1
公开(公告)日：2016-03-24
申请号：US14493434
申请日：2014-09-23
申请人： Josef Bauer , Piotr Rozen , Georg Stemmer
发明人： Josef Bauer , Piotr Rozen , Georg Stemmer
摘要： 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.
摘要翻译： 讨论了与语音识别系统实现神经网络相关的技术。 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。
-
3.发明授权公开(公告)号：US10692492B2
公开(公告)日：2020-06-23
申请号：US15721486
申请日：2017-09-29
申请人： Piotr Rozen , Tobias Bocklet , Jakub Nowicki , Munir Georges
发明人： Piotr Rozen , Tobias Bocklet , Jakub Nowicki , Munir Georges
IPC分类号： G10L15/22 , G06N5/04 , G10L15/18 , G10L15/01 , G06F3/14 , H04W76/10 , G10L15/30 , G10L15/08 , G10L15/183 , G06F3/16 , G10L17/00 , G10L25/63 , G10L25/60 , G10L15/00
摘要： Techniques are disclosed for client-side analysis of audio samples to identify one or more characteristics associated with captured audio. The client-side analysis may then allow a user device, e.g., a smart phone, laptop computer, in-car infotainment system, and so on, to provide the one or more identified characteristics as configuration data to a voice recognition service at or shortly after connection with the same. In turn, the voice recognition service may load one or more recognition components, e.g., language models and/or application modules/engines, based on the received configuration data. Thus, latency may be reduced based on the voice recognition engine having “hints” that allow components to be loaded without necessarily having to process audio samples first. The reduction of latency may reduce processing time relative to other approaches to voice recognitions systems that exclusively perform server-side context recognition/classification.
-
-
搜索结果
3 条记录 (耗时 0.01 秒)