公开(公告)号：WO2011008164A1

公开(公告)日：2011-01-20

申请号：PCT/SE2010/050858

申请日：2010-07-19

Applicant: MILUX HOLDING S.A. ,  FORSELL, Peter

Inventor： FORSELL, Peter

IPC: A61N1/372 ,  G10L21/02 ,  A61F2/02 ,  G10L15/06 ,  G10L15/20

CPC classification number: A61N1/3787 ,  A61F2250/0001 ,  A61N1/37217 ,  G10L15/20 ,  G10L15/26 ,  G10L21/02 ,  G10L21/0208 ,  G10L25/84 ,  G10L2015/223 ,  G10L2021/02165

Abstract: An implantable system (11) for control of and communication with an implant (17) in a body, comprising a command input device (12) and a processing device (13) coupled thereto, the processing device (13) being adapted to generate input to a command generator (16) which is comprised in the system (11) coupled to the processing device (13) and which is adapted to generate and communicate commands to the medical implant (17) in response to input received from the processing device (13), the system (11) further comprising a memory unit (15) connected to at least one of said devices in the system (11) for storing a memory bank of commands. The command input device (12) is adapted to receive commands from a user as voice commands, and the processing device (13) comprises a filter adapted to filter voice commands against high frequency losses and frequency distortion caused by the mammal body (10).

Abstract translation: 一种用于控制和与身体中的植入物（17）进行通信的可植入系统（11），包括命令输入装置（12）和耦合到其上的处理装置（13），所述处理装置（13）适于产生输入 包括在耦合到所述处理设备（13）的所述系统（11）中并且适于响应于从所述处理设备接收到的输入而向所述医疗植入物（17）产生和传达命令的命令生成器（16） 13），系统（11）还包括连接到系统（11）中的至少一个所述设备的存储单元（15），用于存储命令的存储器组。 命令输入装置（12）适于从用户接收命令作为语音命令，并且所述处理装置（13）包括滤波器，所述滤波器适于对由所述哺乳动物体（10）引起的高频损耗和频率失真的语音命令进行滤波。

公开(公告)号：WO2008080673A3

公开(公告)日：2008-09-25

申请号：PCT/EP2007061990

申请日：2007-11-07

Applicant: IBM ,  IBM UK ,  COUPER CHRISTOPHER CLIVE ,  KATZ NEIL ALAN ,  MOORE VICTOR

Inventor： COUPER CHRISTOPHER CLIVE ,  KATZ NEIL ALAN ,  MOORE VICTOR

IPC: G08B13/16 ,  G10L25/90 ,  G08B25/08 ,  G08B25/10

CPC classification number: G08B25/016 ,  G08B13/1672 ,  G08B25/08 ,  G08B25/10 ,  G10L15/00 ,  G10L15/20 ,  G10L21/00 ,  G10L21/0208 ,  H04R5/00 ,  H04R5/027 ,  H04R5/04

Abstract: A method of identifying incidents using mobile devices can include receiving a communicat ion from each of a plurality of mobile devices. Each communication can specify information about a detected sound. Spatial and temporal information can be identified from each communication as well as an indication of a sound signature matching the detected sound. The communications can be compared with a policy specifying spatial and temporal requirements relating to the sound signature indicated by the communications. A 10 notification can be selectively sent according to the comparison.

Abstract translation: 使用移动设备识别事件的方法可以包括从多个移动设备中的每一个接收通信。 每次通信都可以指定关于检测到的声音的信息 可以从每次通信中识别空间和时间信息以及与检测到的声音匹配的声音签名的指示。 通信可以与指定与通信指示的声音签名有关的空间和时间要求的策略进行比较。 根据比较，可以选择性地发送10个通知。

公开(公告)号：WO2008082793A2

公开(公告)日：2008-07-10

申请号：PCT/US2007083906

申请日：2007-11-07

Applicant: MOTOROLA INC ,  SONG JIANMING J ,  CLARK JOEL A

Inventor： SONG JIANMING J ,  CLARK JOEL A

IPC: G10L15/20 ,  H04B15/00 ,  H04M1/00

CPC classification number: G10L21/0208 ,  G10L15/142 ,  G10L15/20 ,  G10L19/00 ,  G10L19/0204 ,  G10L21/00 ,  G10L21/02 ,  G10L21/0232 ,  G10L25/78

Abstract: 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 10 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 15 the plurality of noise activity detectors detects the presence of a corresponding type of noise in the received signal.

Abstract translation: 提供了一种用于音频信号处理电路的噪声抑制电路。 噪声抑制电路包括多个不同类型的噪声活动检测器，每个噪声活动检测器都适于检测接收信号中不同类型噪声的存在。 噪声抑制电路还包括多个不同类型的噪声降低电路，每个噪声降低电路适于去除不同类型的检测到的噪声，其中每个噪声降低电路分别对应于多个噪声活动检测器中的一个。 然后，当多个噪声活动检测器中的每一个检测到接收信号中存在相应类型的噪声时，选择性地激活相应的噪声降低电路以调节接收到的信号以减少检测到的噪声类型的量。

公开(公告)号：WO2008080912A1

公开(公告)日：2008-07-10

申请号：PCT/EP2007/064529

申请日：2007-12-24

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION ,  IBM UNITED KINGDOM LIMITED ,  KANEVSKY, Dimitri ,  SICCONI, Roberto ,  NAHAMOO, David ,  VISWANATHAN, Mahesh

Inventor： KANEVSKY, Dimitri ,  SICCONI, Roberto ,  NAHAMOO, David ,  VISWANATHAN, Mahesh

IPC: G10L15/20 ,  G10L15/24 ,  G10L15/28

CPC classification number: G10L15/24 ,  G10L15/20 ,  G10L15/28

Abstract: Systems and methods for intelligent control of microphones in speech processing applications, which allows the capturing, recording and preprocessing of speech data in the captured audio in a way that optimizes speech recognition accuracy.

Abstract translation: 在语音处理应用中智能控制麦克风的系统和方法，其允许以优化语音识别精度的方式在捕获的音频中捕获，记录和预处理语音数据。

公开(公告)号：WO2007117814B1

公开(公告)日：2008-07-10

申请号：PCT/US2007063752

申请日：2007-03-12

Applicant: MOTOROLA INC ,  MA CHANGXUE C

Inventor： MA CHANGXUE C

IPC: G10L15/14

CPC classification number: G10L15/20 ,  G10L21/0216

Abstract: A system (100) and method (200) for generating a perturbed phonetic string for use in speech recognition. The method can include generating (202) a feature vector set from a spoken utterance, applying (204) a perturbation to the feature vector set for producing a perturbed feature vector set, and phonetically decoding (206) the perturbed feature vector set for producing a perturbed phonetic string. The perturbation mimics environmental variability and speaker variability for reducing the number of spoken utterances in speech recognition applications.

Abstract translation: 一种用于产生用于语音识别的扰动语音串的系统（100）和方法（200）。 该方法可以包括从语音发音生成（202）特征向量集合，将扰动应用（204）扰动到特征向量集合以产生扰动的特征向量集合，并且语音地解码（206）扰动的特征向量集合以产生 扰乱的语音字符串 扰动模拟环境变异性和说话者变异性，以减少语音识别应用中的口语话语数量。

公开(公告)号：WO2008001991A1

公开(公告)日：2008-01-03

申请号：PCT/KR2006/005831

申请日：2006-12-28

Applicant: KT CORPORATION ,  RYU, Chang-Sun ,  KIM, Jae-In ,  KIM, Hong Kook ,  YOON, Jae Sam ,  OH, Yoo Rhee

Inventor： RYU, Chang-Sun ,  KIM, Jae-In ,  KIM, Hong Kook ,  YOON, Jae Sam ,  OH, Yoo Rhee

IPC: G10L15/20 ,  G10L15/28

CPC classification number: G10L15/30 ,  G10L15/02 ,  G10L15/20

Abstract: Provided are an apparatus for extracting a speech feature vector in a distributed speech recognition terminal and a method thereof. The apparatus includes a speech coding module for transmitting coded speech signals into outside through a speech traffic channel in a speech coding mode; a speech feature vector extracting module for transmitting extracted speech feature vectors into outside in a speech recognition mode; and a speech coding/recognition pre-processing block for attenuating a noise in speech signals received from the outside, wherein speech signals inputted into the speech coding module and the speech feature vector extracting module are pre-processed in the speech coding/recognition preprocessing block.

Abstract translation: 提供一种用于在分布式语音识别终端中提取语音特征向量的装置及其方法。 该装置包括：语音编码模块，用于通过语音业务信道以语音编码模式将编码语音信号发送到外部; 语音特征向量提取模块，用于在语音识别模式中将提取的语音特征矢量发送到外部; 以及用于衰减从外部接收的语音信号中的噪声的语音编码/识别预处理块，其中输入到语音编码模块和语音特征向量提取模块的语音信号在语音编码/识别预处理块中被预处理 。

公开(公告)号：WO2007080886A1

公开(公告)日：2007-07-19

申请号：PCT/JP2007/050157

申请日：2007-01-10

Applicant: 日本電気株式会社 ,  岩沢 透

Inventor： 岩沢 透

IPC: G10L15/20

CPC classification number: G10L21/028 ,  G10L15/20

Abstract: 　利用話者が発話した発話音声と利用話者以外の妨害話者が発話した妨害音声を含む入力音声を入力するマイクロフォン１２と、入力音声として別個に入力された発話音声および妨害音声に基づき、入力音声に対する雑音重畳量を決定する重畳量決定部１４と、雑音重畳量に応じた雑音を入力音声へ重畳し、雑音重畳音声として出力する雑音重畳部１６と、雑音重畳音声を音声認識する音声認識部１８と、を備える。  

Abstract translation: 音频识别装置包括：麦克风（12），用于输入包括由用户扬声器发出的发话音频的输入音频以及由用户扬声器以外的干扰扬声器发出的干扰音频; 叠加量判定单元，用于根据作为输入音频单独输入的话音音频和干扰音频来确定输入音频的噪声叠加量; 噪声叠加单元，用于将基于噪声叠加量的噪声叠加在输入音频上，并将其作为噪声叠加音频输出; 以及用于音频识别噪声叠加音频的音频识别单元（18）。

公开(公告)号：WO2007066933A1

公开(公告)日：2007-06-14

申请号：PCT/KR2006/005154

申请日：2006-12-01

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE ,  CHO, Kwan-Hyun ,  HAN, Mun-Sung ,  PARK, Jun-Seok ,  JUNG, Young-Giu

Inventor： CHO, Kwan-Hyun ,  HAN, Mun-Sung ,  PARK, Jun-Seok ,  JUNG, Young-Giu

IPC: G10L15/20 ,  G10L15/02 ,  G10L15/28

CPC classification number: G10L15/20 ,  G10L21/0208

Abstract: A voice recognition apparatus and method are provided. The voice recognition apparatus includes: a signal processing unit for calculating a log spectrum of a vocal band signal and a log spectrum of a voice signal containing noise, the vocal band signal and the voice signal being received from an external channel; a weight calculating unit for calculating a normalization value by assigning a weight using the log spectrum of the vocal band signal and the spectrum of the voice signal, and compensating for the log spectrum of the vocal band signal to the normalization value; a feature extracting unit for extracting a feature vector from the compensated log spectrum of the vocal band signal; and a recognizing unit for leaning a recognition model using the feature vector and performing a voice recognition.

Abstract translation: 提供语音识别装置和方法。 语音识别装置包括：信号处理单元，用于计算从外部信道接收的声带信号的对数谱和包含噪声，声带信号和语音信号的语音信号的对数谱; 权重计算单元，用于通过使用声带信号的对数谱和声音信号的频谱分配权重来计算归一化值，并将声带信号的对数谱补偿到归一化值; 特征提取单元，用于从声带信号的补偿对数谱中提取特征向量; 以及识别单元，用于使用所述特征向量倾斜识别模型并执行语音识别。

公开(公告)号：WO2006089055A1

公开(公告)日：2006-08-24

申请号：PCT/US2006/005523

申请日：2006-02-15

Applicant: BBN TECHNOLOGIES CORP. ,  PREUSS, Robert David ,  FABRI, Darren Ross ,  CRUTHIRDS, Daniel Ramsay

Inventor： PREUSS, Robert David ,  FABRI, Darren Ross ,  CRUTHIRDS, Daniel Ramsay

IPC: G10L15/20 ,  G10L19/00

CPC classification number: G10L15/20 ,  G10L19/0018 ,  G10L19/12 ,  G10L19/20 ,  G10L21/0216 ,  G10L2019/0002 ,  G10L2019/0005

Abstract: Presented herein are systems and methods for generating an adaptive noise codebook for use with electronic speech systems. The noise codebook includes a plurality of entries which may be updated based on environmental noise sounds. The speech system includes a speech codebook and the adaptive noise codebook. The system identifies speech sounds in an audio signal using the speech and noise codebooks.

Abstract translation: 这里提出的是用于产生用于电子语音系统的自适应噪声码本的系统和方法。 噪声码本包括可以基于环境噪声声音来更新的多个条目。 语音系统包括语音码本和自适应噪声码本。 该系统使用语音和噪声码本识别音频信号中的语音。

公开(公告)号：WO2004102527A8

公开(公告)日：2005-04-14

申请号：PCT/US2004014498

申请日：2004-05-10

Applicant: VOICE SIGNAL TECHNOLOGIES INC ,  COHEN JORDAN ,  ROTH DANIEL L ,  GILLICK LAURENCE S

Inventor： COHEN JORDAN ,  ROTH DANIEL L ,  GILLICK LAURENCE S

IPC: G10L15/20 ,  G10L15/22

CPC classification number: G10L15/20 ,  G10L15/10

Abstract: A method of processing speech in a noisy environment includes determining, upon a wake-up command, when the environment is too noisy to yield reliable recognition of a user's spoken words, and alerting the user that the environment is too noisy. Determining when the environment is too noisy includes calculating a ratio of signal to noise. The signal corresponds to of an amount of energy in the spoken utterance, and the noise corresponds to an amount of energy in the background noise. The method further includes comparing the signal to noise to a threshold.

Abstract translation: 一种在嘈杂环境中处理语音的方法包括在唤醒命令时确定何时环境过于嘈杂以产生用户说出的话语的可靠识别并且警告用户环境过于嘈杂。 确定环境噪声太大时包括计算信噪比。 该信号对应于口头发言中的能量的量，并且该噪声对应于背景噪声中的能量的量。 该方法还包括将信号与噪声与阈值进行比较。