专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20160005399A1 NOISE SPEED-UPS IN HIDDEN MARKOV MODELS WITH APPLICATIONS TO SPEECH RECOGNITION 审中-公开
标题翻译：噪音速度型UPS用于语音识别应用
公开(公告)号：US20160005399A1
公开(公告)日：2016-01-07
申请号：US14802760
申请日：2015-07-17
申请人： Kartik Audhkhasi , Osonde Osoba , Bart Kosko
发明人： Kartik Audhkhasi , Osonde Osoba , Bart Kosko
IPC分类号： G10L15/14 , G10L25/33 , G10L25/36 , G10L15/06
CPC分类号： G10L15/144 , G10L15/063 , G10L25/33 , G10L25/36
摘要： A learning computer system may estimate unknown parameters and states of a stochastic or uncertain system having a probability structure. The system may include a data processing system that may include a hardware processor that has a configuration that: receives data; generates random, chaotic, fuzzy, or other numerical perturbations of the data, one or more of the states, or the probability structure; estimates observed and hidden states of the stochastic or uncertain system using the data, the generated perturbations, previous states of the stochastic or uncertain system, or estimated states of the stochastic or uncertain system; and causes perturbations or independent noise to be injected into the data, the states, or the stochastic or uncertain system so as to speed up training or learning of the probability structure and of the system parameters or the states.
摘要翻译：学习计算机系统可以估计具有概率结构的随机或不确定系统的未知参数和状态。该系统可以包括数据处理系统，其可以包括具有以下配置的硬件处理器：接收数据; 产生数据的随机，混乱，模糊或其他数字扰动，一个或多个状态或概率结构; 使用数据，生成的扰动，随机或不确定系统的先前状态或随机或不确定系统的估计状态的随机或不确定系统的观测和隐藏状态的估计; 并引起扰动或独立噪声注入到数据，状态或随机或不确定系统中，以加速对概率结构和系统参数或状态的训练或学习。

2. 发明授权

US11495213B2 Noise speed-ups in hidden markov models with applications to speech recognition 有权
公开(公告)号：US11495213B2
公开(公告)日：2022-11-08
申请号：US14802760
申请日：2015-07-17
申请人： UNIVERSITY OF SOUTHERN CALIFORNIA
发明人： Kartik Audhkhasi , Osonde Osoba , Bart Kosko
IPC分类号： G10L25/36 , G10L15/14 , G10L15/06 , G10L25/33
摘要： A learning computer system may estimate unknown parameters and states of a stochastic or uncertain system having a probability structure. The system may include a data processing system that may include a hardware processor that has a configuration that: receives data; generates random, chaotic, fuzzy, or other numerical perturbations of the data, one or more of the states, or the probability structure; estimates observed and hidden states of the stochastic or uncertain system using the data, the generated perturbations, previous states of the stochastic or uncertain system, or estimated states of the stochastic or uncertain system; and causes perturbations or independent noise to be injected into the data, the states, or the stochastic or uncertain system so as to speed up training or learning of the probability structure and of the system parameters or the states.

3. 发明授权

US10468047B2 Wireless digital audio music system 有权
公开(公告)号：US10468047B2
公开(公告)日：2019-11-05
申请号：US16185786
申请日：2018-11-09
申请人： C. Earl Woolfork
发明人： C. Earl Woolfork
IPC分类号： G10L19/16 , H04R5/00 , H04R1/10 , G10L19/005 , H04B1/707 , G10L25/33 , H04R3/04 , H04L25/03
摘要： A wireless digital audio system includes a portable audio source with a digital audio transmitter operatively coupled thereto and an audio receiver operatively coupled to a headphone set. The audio receiver is configured for digital wireless communication with the audio transmitter. The digital audio receiver utilizes fuzzy logic to optimize digital signal processing. Each of the digital audio transmitter and receiver is configured for code division multiple access (CDMA) communication. The wireless digital audio system allows private audio enjoyment without interference from other users of independent wireless digital transmitters and receivers sharing the same space.

4. 发明申请

US20190098393A1 WIRELESS DIGITAL AUDIO MUSIC SYSTEM 审中-公开
公开(公告)号：US20190098393A1
公开(公告)日：2019-03-28
申请号：US16185786
申请日：2018-11-09
申请人： C. Earl Woolfork
发明人： C. Earl Woolfork
IPC分类号： H04R1/10 , G10L19/005 , H04B1/707 , G10L25/33 , H04R5/00 , H04R3/04 , G10L19/16 , H04L25/03
摘要： A wireless digital audio system includes a portable audio source with a digital audio transmitter operatively coupled thereto and an audio receiver operatively coupled to a headphone set. The audio receiver is configured for digital wireless communication with the audio transmitter. The digital audio receiver utilizes fuzzy logic to optimize digital signal processing. Each of the digital audio transmitter and receiver is configured for code division multiple access (CDMA) communication. The wireless digital audio system allows private audio enjoyment without interference from other users of independent wireless digital transmitters and receivers sharing the same space.

5. 发明授权

US09818400B2 Method and apparatus for discovering trending terms in speech requests 有权
公开(公告)号：US09818400B2
公开(公告)日：2017-11-14
申请号：US14839835
申请日：2015-08-28
申请人： Apple Inc.
发明人： Matthias Paulik , Gunnar Evermann , Laurence S. Gillick
IPC分类号： G06F17/27 , G10L15/06 , G06F17/30 , G10L15/02 , G10L25/33 , G10L15/197
CPC分类号： G10L15/063 , G06F17/30867 , G10L15/02 , G10L15/1815 , G10L15/183 , G10L15/197 , G10L25/33
摘要： Systems and processes are disclosed for discovering trending terms in automatic speech recognition. Candidate terms (e.g., words, phrases, etc.) not yet found in a speech recognizer vocabulary or having low language model probability can be identified based on trending usage in a variety of electronic data sources (e.g., social network feeds, news sources, search queries, etc.). When candidate terms are identified, archives of live or recent speech traffic can be searched to determine whether users are uttering the candidate terms in dictation or speech requests. Such searching can be done using open vocabulary spoken term detection to find phonetic matches in the audio archives. As the candidate terms are found in the speech traffic, notifications can be generated that identify the candidate terms, provide relevant usage statistics, identify the context in which the terms are used, and the like.

6. 发明申请

US20160275071A1 TRANSCRIPTION CORRECTION USING MULTI-TOKEN STRUCTURES 有权
标题翻译：使用多克隆结构进行转录校正
公开(公告)号：US20160275071A1
公开(公告)日：2016-09-22
申请号：US15171149
申请日：2016-06-02
申请人： Microsoft Technology Licensing, LLC
发明人： Michael Levit , Umut Ozertem , Sarangarajan Parthasarathy , Padma Varadharajan , Karthik Raghunathan , Issac Alphonso
IPC分类号： G06F17/27 , G10L15/187 , G10L15/01 , G06F17/28 , G10L15/30 , G10L25/33 , G10L15/22
CPC分类号： G06F17/277 , G06F17/28 , G10L15/01 , G10L15/02 , G10L15/083 , G10L15/187 , G10L15/197 , G10L15/22 , G10L15/30 , G10L25/33 , G10L2015/221
摘要： Examples of the present disclosure describe generation of a multi-arc confusion network to improve, for example, an ability to return alternatives to output generated. A confusion network comprising token representations of lexicalized hypotheses and normalized hypotheses is generated. Each arc of the confusion network represents a token of a lexicalized hypothesis or a normalized hypothesis. The confusion network is transformed into a multi-arc confusion network, wherein the transforming comprising realigning at least one token of the confusion network to span multiple arcs of the confusion network. Other examples are also described.
摘要翻译：本公开的示例描述了生成多弧混淆网络以改善例如返回产生的输出的替代物的能力。产生包含词汇化假设和归一化假设的令牌表示的混淆网络。混乱网络的每个弧代表一个词汇化假说或一个归一化假设的标志。混淆网络被转换成多弧混淆网络，其中变换包括重新排列混合网络的至少一个令牌以跨越混淆网络的多个弧。还描述了其它实例。

7. 发明申请

US20150112674A1 METHOD FOR BUILDING ACOUSTIC MODEL, SPEECH RECOGNITION METHOD AND ELECTRONIC APPARATUS 审中-公开
标题翻译：建立声学模型，语音识别方法和电子设备的方法
公开(公告)号：US20150112674A1
公开(公告)日：2015-04-23
申请号：US14490676
申请日：2014-09-19
申请人： VIA Technologies, Inc.
发明人： Guo-Feng Zhang , Yi-Fei Zhu
IPC分类号： G10L15/06 , G10L25/33 , G10L15/00 , G10L15/26
CPC分类号： G10L15/063 , G10L25/33 , G10L2015/0633
摘要： A method for building acoustic model, a speech recognition method and an electronic apparatus are provided. The speech recognition method includes the following steps. A plurality of phonetic transcriptions of a speech signal is obtained from an acoustic model. A plurality of vocabularies matching the phonetic transcriptions are obtained according to each phonetic transcription and a syllable acoustic lexicon, wherein the syllable acoustic lexicon includes the vocabularies corresponding to the phonetic transcription, and the vocabulary having at least one phonetic transcription includes a code corresponding to the phonetic transcription. A plurality of strings and a plurality of string probabilities are obtained from a language model according to the code of each of the vocabularies.
摘要翻译：提供了建立声学模型的方法，语音识别方法和电子设备。语音识别方法包括以下步骤。从声学模型获得语音信号的多个语音转录。根据每个语音转录和音节声学词典获得与语音转录匹配的多个词汇，其中，音节声学词典包括对应于语音转录的词汇，并且具有至少一个语音转录的词汇包括对应于语音转录。根据每个词汇的代码从语言模型获得多个字符串和多个字符串概率。

8. 发明授权

US11810595B2 Identification of life events for virtual reality data and content collection 有权
公开(公告)号：US11810595B2
公开(公告)日：2023-11-07
申请号：US16850716
申请日：2020-04-16
申请人： AT&T Intellectual Property I, L.P.
发明人： Brittaney Zellner , Sameena Khan , Ryan Schaub , Barrett Kreiner , Ari Craine , Robert Koch
IPC分类号： G10L15/00 , G10L25/63 , G10L25/30 , G06F17/18 , G06Q10/1093 , G10L25/33 , G10L15/22 , G10L15/30 , G10L15/18 , G10L15/183
CPC分类号： G10L25/63 , G06F17/18 , G06Q10/1093 , G10L15/22 , G10L25/30 , G10L25/33 , G10L15/183 , G10L15/1822 , G10L15/30
摘要： This disclosure describes a solution to identify that a meaningful event has occurred in a person's life. Once identified, data and content related to the event can be collected and stored in a database. This data and content can be used to offer future virtual reality (VR) experiences and content. A person can be equipped with a smart device such as a smartphone, smart watch, or other wearable that can further be equipped with a tracking app that collects data from these devices and from other sources, for instance, over the internet. The tracking app can continuously collect such data and use various algorithms to make a determination as to whether the person is experiencing a meaningful life event.

9. 发明授权

US10930286B2 Method and system for muting classified information from an audio 有权
公开(公告)号：US10930286B2
公开(公告)日：2021-02-23
申请号：US16254387
申请日：2019-01-22
申请人： Tata Consultancy Services Limited
发明人： Imran Ahamad Sheikh , Sunil Kumar Kopparapu , Bhavikkumar Bhagvanbhai Vachhani , Bala Mallikarjunarao Garlapati , Srinivasa Rao Chalamala
IPC分类号： G10L15/00 , G10L15/22 , G06F3/16 , G06N7/02 , G10L15/06 , G10L25/33 , G10L25/48 , G10L25/87
摘要： This disclosure relates generally to a method and system for muting of classified information from an audio using a fuzzy approach. The method comprises converting the received audio signal into text using a speech recognition engine to identify a plurality of classified words from the text to obtain a first set of parameters. Further, a plurality of subwords associated with each classified word are identified to obtain a second set of parameters associated with each subword of corresponding classified word. A relative score is computed for each subword associated with the classified word based on a plurality of similar pairs for the corresponding classified word. A fuzzy muting function is generated using the first set of parameters, the second set of parameters and the relative score associated with each subword. The plurality of subwords associated with each classified word is muted in accordance with the generated fuzzy muting function.

10. 发明授权

US10546062B2 Phonetic patterns for fuzzy matching in natural language processing 有权
公开(公告)号：US10546062B2
公开(公告)日：2020-01-28
申请号：US15813416
申请日：2017-11-15
申请人： International Business Machines Corporation
发明人： Sean M. Fuoco , John M. Ganci, Jr. , Craig M. Trim , Jie Zeng
IPC分类号： G10L15/00 , G10L15/26 , G10L17/00 , G06F17/27 , G10L15/02 , G10L25/33
摘要： A token is extracted from a Natural Language input. A phonetic pattern is computed corresponding to the token, the phonetic pattern including a sound pattern that represents a part of the token when the token is spoken. New data is created from data of the phonetic pattern, the new data including a syllable sequence corresponding to the phonetic pattern. A state of a data storage device is changed by storing the new data in a matrix of syllable sequences corresponding to the token. An option is selected that corresponds to the token by executing a fuzzy matching algorithm using a processor and a memory, the selecting of the option is based on a syllable sequence in the matrix.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式