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. 发明授权

EP4057277B1 METHOD AND APPARATUS FOR NOISE REDUCTION, ELECTRONIC DEVICE, AND STORAGE MEDIUM 有权
公开(公告)号：EP4057277B1
公开(公告)日：2024-09-25
申请号：EP22160855.7
申请日：2022-03-08
IPC分类号： G10K11/178 , G10L21/0216 , G10L15/14 , G10L15/16 , G10L21/0272 , G10L15/08
CPC分类号： G10L2015/08820130101 , G10L21/0216 , G10L15/16 , G10L15/142 , G10L2021/0216620130101 , G10L21/0272 , G10K11/17837 , G10K11/17823 , G10K2210/108120130101 , G10K2210/11120130101 , G10K11/17881

2. 发明公开

EP3353766A1 METHODS FOR THE AUTOMATED GENERATION OF SPEECH SAMPLE ASSET PRODUCTION SCORES FOR USERS OF A DISTRIBUTED LANGUAGE LEARNING SYSTEM, AUTOMATED ACCENT RECOGNITION AND QUANTIFICATION AND IMPROVED SPEECH RECOGNITION 审中-公开
公开(公告)号：EP3353766A1
公开(公告)日：2018-08-01
申请号：EP16847648.9
申请日：2016-09-22
申请人： Vendome Consulting Pty Ltd
发明人： CASSAGNE, Gregory , SCHAPOTSCHNIKOW, Philipp
IPC分类号： G09B19/06 , G09B5/04 , G06F15/18 , G06F17/28
CPC分类号： G10L15/063 , G06F15/18 , G06N99/005 , G09B5/04 , G09B19/04 , G09B19/06 , G10L15/005 , G10L15/142 , G10L15/16 , G10L15/22 , G10L15/32 , G10L25/60
摘要： Methods for automated generation of speech sample asset production scores for users of a distributed language learning system, automated accent recognition and quantification and improved speech recognition. Utilising a trained supervised machine learning module which is trained utilising a training set comprising a plurality of production speech sample asset recordings, associated production scores generated by system users performing perception exercises and user background information. The trained supervised machine learning module may be configured for automated accent recognition, by feeding a candidate production speech sample asset so as to automate the generation of a speech sample asset production score and user background information. As such, the user background information may be translated into an accent type categorisation and the speech sample asset production score may be translated into an accent strength. In further embodiments, the accent type categorisation generated using the trained system may be utilised for improved speech recognition.

3. 发明公开

EP3300075A1 SPEECH RECOGNITION DEVICE AND COMPUTER PROGRAM 审中-公开
标题翻译：语音识别设备和计算机程序
公开(公告)号：EP3300075A1
公开(公告)日：2018-03-28
申请号：EP16799785.7
申请日：2016-05-10
申请人： NATIONAL INSTITUTE OF INFORMATION AND COMMUNICATIONS TECHNOLOGY
发明人： KANDA, Naoyuki
IPC分类号： G10L15/16 , G10L15/14 , G10L15/193
CPC分类号： G10L15/142 , G10L15/16 , G10L15/193 , G10L15/22
摘要： [Object] An object is to provide a speech recognition device with improved recognition accuracy using characteristics of a neural network.
[Solution] A speech recognition device includes: an acoustic model 308 implemented by a RNN (recurrent neural network) for calculating, for each state sequence, the posterior probability of a state sequence in response to an observed sequence consisting of prescribed speech features obtained from a speech; a WFST 320 based on S -1 HCLG calculating, for each word sequence, posterior probability of a word sequence in response to a state sequence; and a hypothesis selecting unit 322, performing speech recognition of the speech signal based on a score calculated for each hypothesis of a word sequence corresponding to the speech signal, using the posterior probabilities calculated by the acoustic model 308 and the WFST 320 for the input observed sequence.
摘要翻译：本发明的目的是提供一种利用神经网络的特性提高识别精度的语音识别装置。 [解决方案]语音识别设备包括：由RNN（递归神经网络）实现的声学模型308，用于针对每个状态序列计算状态序列的后验概率以响应于观察到的序列，该序列由从一个演讲; 基于S-1HCLG的WFST 320针对每个单词序列计算单词序列响应于状态序列的后验概率; 以及假设选择单元322，使用由声学模型308和WFST 320计算的后验概率，基于针对与语音信号相对应的单词序列的每个假设计算的分数来对语音信号执行语音识别序列。

4. 发明授权

EP2897076B8 Tamper-resistant element for use in speaker recognition 有权转让
标题翻译：用于扬声器识别的防篡改元件
公开(公告)号：EP2897076B8
公开(公告)日：2018-02-07
申请号：EP14151638.5
申请日：2014-01-17
申请人： Cirrus Logic International Semiconductor Ltd.
发明人： Vaquero Avilés-Casco, Carlos , Buera Rodríguez, Luis , García Gomar, Marta
IPC分类号： G06F21/32 , G10L17/00
CPC分类号： G10L17/02 , G06F21/32 , G06F21/34 , G06F21/72 , G10L15/14 , G10L15/142 , G10L17/00 , G10L17/005 , G10L17/06 , G10L17/08 , G10L17/16 , G10L19/018 , H04L9/3231
摘要： A tamper-resistant element for use in speaker recognition, the tamper-resistant element being adapted for storing data representing speaker information based on speaker recognition enrollment data and for checking whether information based on a speaker recognition testing signal matches the speaker information, characterized in that the tamper-resistant element is also adapted for carrying out a data integrity check, a system comprising such a tamper-resistant element and method for speaker recognition.

5. 发明授权

EP2923634B1 MULTI-USER VOICE CONTROL SYSTEM FOR MEDICAL DEVICES 有权
标题翻译：语音控制系统，用于医疗设备的多个用户
公开(公告)号：EP2923634B1
公开(公告)日：2017-02-01
申请号：EP15161090.4
申请日：2015-03-26
申请人： Storz Endoskop Produktions GmbH
发明人： Contolini, Matteo , Applebaum, Ted
IPC分类号： A61B5/00 , A61B1/00
CPC分类号： G10L17/22 , A61B1/00041 , A61B5/00 , A61B5/7405 , A61B5/749 , G10L15/00 , G10L15/08 , G10L15/142 , G10L15/32 , G10L17/00

6. 发明公开

EP2826261A4 SPATIAL AUDIO SIGNAL FILTERING 有权转让
标题翻译： RÄUMLICHEAUDIOSIGNALFILTERUNG
公开(公告)号：EP2826261A4
公开(公告)日：2015-10-21
申请号：EP12871453
申请日：2012-03-14
申请人： NOKIA TECHNOLOGIES OY
发明人： JARVINEN ROOPE OLAVI , JARVINEN KARI JUHANI , ARRASVUORI JUHA HENRIK , VILERMO MIIKKA
IPC分类号： H04R27/00 , G06F3/16 , G10L15/08 , G10L15/14 , H04N21/233 , H04S1/00 , H04S7/00
CPC分类号： H04R5/00 , G06F3/16 , G06F3/165 , G10L15/142 , G10L17/18 , G10L2015/088 , H04N21/233 , H04R27/00 , H04R2227/003 , H04R2420/01 , H04R2430/01 , H04R2499/11 , H04S1/007 , H04S7/30 , H04S2400/13 , H04S2420/01
摘要： An apparatus comprising means for analysing at least one speech input to determine one or more expressions within the at least one speech input: and controlling at least one audio output signal dependent upon the one or more expression, wherein the at least one speech input is independent of the at least one audio output signal and wherein the controlling of the at least one audio output signal is dependent upon determining the expression within the at least one speech input.
摘要翻译：一种装置，包括：分析器，被配置为分析至少一个输入以确定所述至少一个输入内的一个或多个表达; 以及控制器，被配置为根据所述一个或多个表达式的确定来控制与所述至少一个输入相关联的至少一个音频信号。

7. 发明公开

EP2569681A2 ELECTRONIC PERSONAL INTERACTIVE DEVICE 审中-公开
标题翻译： ELEKTRONISCHE个人运动VORRICHTUNG
公开(公告)号：EP2569681A2
公开(公告)日：2013-03-20
申请号：EP11781329.5
申请日：2011-05-13
申请人： Poltorak, Alexander
发明人： Poltorak, Alexander
IPC分类号： G06F3/01 , G06F3/048 , G06F17/30 , G10L15/00
CPC分类号： G10L15/22 , G06F3/017 , G06F3/167 , G06F17/30029 , G06K9/00302 , G06K9/00355 , G06T13/205 , G10L13/00 , G10L13/033 , G10L15/142 , G10L15/16 , G10L15/1815 , G10L15/30 , G10L25/63 , G10L2015/223 , H04L12/2818 , H04M1/0202 , H04M2250/10 , H04W84/12 , H04W84/18
摘要： An interface device and method of use, comprising audio and image inputs; a processor for determining topics of interest, and receiving information of interest to the user from a remote resource; an audiovisual output for presenting an anthropomorphic object conveying the received information, having a selectively defined and adaptively alterable mood; an external communication device adapted to remotely communicate at least a voice conversation with a human user of the personal interface device. Also provided is a system and method adapted to receive logic for, synthesize, and engage in conversation dependent on received conversational logic and a personality.
摘要翻译：一种接口装置和使用方法，包括音频和图像输入; 用于确定感兴趣的主题并从远程资源接收用户感兴趣的信息的处理器; 用于呈现传达所接收信息的拟人对象的视听输出，具有选择性定义且可自适应地改变的心情; 外部通信设备，其适于远程地与个人接口设备的人类用户通信至少语音对话。还提供了一种系统和方法，其适于接收依赖于所接收的对话逻辑和个性的用于，合成和参与对话的逻辑。

8. 发明公开

EP2100295A4 A METHOD AND NOISE SUPPRESSION CIRCUIT INCORPORATING A PLURALITY OF NOISE SUPPRESSION TECHNIQUES 有权转让
标题翻译：具有多降噪技术方法和降噪电路
公开(公告)号：EP2100295A4
公开(公告)日：2012-02-08
申请号：EP07871389
申请日：2007-11-07
申请人： MOTOROLA MOBILITY INC
发明人： SONG JIANMING J , CLARK JOEL A
IPC分类号： G10L15/20 , G10L11/02 , G10L21/02 , H04B15/00 , H04M1/00
CPC分类号： G10L21/0208 , G10L15/142 , G10L15/20 , G10L19/00 , G10L19/0204 , G10L21/00 , G10L21/02 , G10L21/0232 , G10L25/78
摘要： A noise suppression circuit for use in an audio signal processing circuit is provided. The noise suppression circuit includes a plurality of different types of noise activity detectors, which are each adapted for detecting the presence of a different type of noise in a received signal. The noise suppression circuit further includes a plurality of different types of noise reduction circuits, which are each adapted for removing a different type of detected noise, where each noise reduction circuit respectively corresponds to one of the plurality of noise activity detectors. The respective noise reduction circuit is then selectively activated to condition the received signal to reduce the amount of the detected types of noise, when each one of the plurality of noise activity detectors detects the presence of a corresponding type of noise in the received signal.

9. 发明授权

EP1850324B1 Voice recognition system using implicit speaker adaption 有权
标题翻译：隐式扬声器适应的手段语音识别系统
公开(公告)号：EP1850324B1
公开(公告)日：2011-09-21
申请号：EP07014802.8
申请日：2002-03-22
申请人： Qualcomm, Incorporated
发明人： Malayath, Narendranath , Dejaco, Andrew P. , Chang, Chienchung , Jalil, Suhail , Bi, Ning , Garudadri, Harinath
IPC分类号： G10L15/06 , G10L15/14 , G10L15/12
CPC分类号： G10L15/142 , G10L15/07 , G10L15/10 , G10L15/12 , G10L15/144 , G10L15/32

10. 发明授权

EP2161718B1 Speech recognition 有权转让
标题翻译：语音识别
公开(公告)号：EP2161718B1
公开(公告)日：2011-08-31
申请号：EP08015561.7
申请日：2008-09-03
申请人： Harman Becker Automotive Systems GmbH
发明人： Herbig, Tobias , Raab, Martin , Brueckner, Raymond , Gruhn, Rainer
IPC分类号： G10L15/06 , G10L15/02
CPC分类号： G10L15/02 , G10L15/06 , G10L15/142 , G10L2015/025
摘要： The present invention relates to a method for speech recognition of a speech signal comprising the steps of providing at least one codebook comprising codebook entries, in particular, multivariate Gaussians of feature vectors, that are frequency weighted such that higher weights are assigned to entries corresponding to frequencies below a predetermined level than to entries corresponding to frequencies above the predetermined level and processing the speech signal for speech recognition comprising extracting at least one feature vector from the speech signal and matching the feature vector with the entries of the codebook.

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