公开(公告)号：WO2017116532A1

公开(公告)日：2017-07-06

申请号：PCT/US2016/057441

申请日：2016-10-18

Applicant: GOOGLE INC.

Inventor： BUCHNER, Herbert ,  GODSILL, Simon J. ,  SKOGLUND, Jan

IPC: G10L21/0216 ,  G10L21/0232

CPC classification number: G10L19/26 ,  G10L21/0208 ,  G10L21/0216 ,  G10L21/0224 ,  G10L21/0232 ,  G10L21/028 ,  G10L2021/02161 ,  G10L2021/02165 ,  H04R2410/05

Abstract: Provided are methods and systems for acoustic keystroke transient cancellation/suppression for user communication devices using a semi-blind adaptive filter model. The methods and systems are designed to overcome existing problems in transient noise suppression by taking into account some less-defective signal as side information on the transients and also accounting for acoustic signal propagation, including the reverberation effects, using dynamic models. The methods and systems take advantage of a synchronous reference microphone embedded in the keyboard of the user device, and utilize an adaptive filtering approach exploiting the knowledge of this keybed microphone signal.

Abstract translation: 提供了用于使用半盲自适应滤波器模型的用于用户通信设备的声学击键瞬态消除/抑制的方法和系统。 这些方法和系统被设计用于通过考虑一些较少缺陷的信号作为瞬变的辅助信息来克服在瞬态噪声抑制中存在的问题，并且还使用动态模型考虑声信号传播，包括混响效应。 该方法和系统利用嵌入在用户设备的键盘中的同步参考麦克风，并利用利用该键控麦克风信号的知识的自适应滤波方法。

公开(公告)号：WO2017044964A1

公开(公告)日：2017-03-16

申请号：PCT/US2016/051352

申请日：2016-09-12

Applicant: ZERO LABS, INC.

Inventor： PRADHAN, Rajesh ,  PRADHAN, Amit

IPC: G06F17/20 ,  G06F17/27 ,  G06F17/28 ,  G06F17/30 ,  G10L21/00

CPC classification number: G06F17/2795 ,  G06F17/2775 ,  G06F17/2785 ,  G06F17/30743 ,  G10L15/26 ,  G10L21/0208 ,  G10L2015/025 ,  G10L2021/02161 ,  H04R3/005

Abstract: The invention provides a computer system for interacting with a user. A set of concepts initially forms a target set of concepts. An input module receives a language input from the user. An analysis system executes a plurality of narrowing cycles until a concept packet having at least one concept has been identified. Each narrowing cycle includes identifying at least one portion of the language and determining a subset of concepts from the target set of concepts to form a new target subset. An action item identifier identifies an action item from the action items based on the concept packet. An action executer that executes an action based on the action item that has been identified.

Abstract translation: 本发明提供了一种用于与用户交互的计算机系统。 一组概念最初形成了一组目标概念。 输入模块从用户接收语言输入。 分析系统执行多个缩小周期，直到具有至少一个概念的概念分组已经被识别为止。 每个缩小周期包括识别语言的至少一部分并且从目标概念集确定概念的子集以形成新的目标子集。 动作项目标识符基于概念分组识别来自动作项目的动作项目。 基于已识别的动作项执行动作的动作执行器。

公开(公告)号：WO2014143448A1

公开(公告)日：2014-09-18

申请号：PCT/US2014/014759

申请日：2014-02-05

Applicant: MOTOROLA MOBILITY LLC

Inventor： ZUREK, Robert A. ,  CLARK, Joel A. ,  DWYER, Joseph C. ,  GARCIA, Juan C. ,  IVANOV, Plamen A. ,  OLIVEIRA, Rivanaldo S. ,  SINGARAJU, Snehitha ,  WU, Jincheng

IPC: G10L25/48 ,  G10L21/02 ,  G10L15/22 ,  G10L15/06 ,  G10L15/20 ,  G10L15/065 ,  G10L21/0208 ,  G10L21/0316 ,  G10L21/0216

CPC classification number: H04M1/6041 ,  G01S15/08 ,  G10L15/06 ,  G10L15/063 ,  G10L15/065 ,  G10L15/20 ,  G10L15/22 ,  G10L21/02 ,  G10L21/0316 ,  G10L25/48 ,  G10L2015/228 ,  G10L2021/02082 ,  G10L2021/02161 ,  H03G3/32 ,  H04M1/271

Abstract: A method and apparatus for adapting acoustic processing in a communication device (102), and capturing (302) at least one acoustic signal using acoustic hardware (218, 224) of the communication device (102), characterizing (304) an acoustic environment external to the communication device (102) using the at least one captured acoustic signal, adapting (306) acoustic processing within the communication device (102) based on the characterized acoustic environment.

Abstract translation: 一种用于在通信设备（102）中适配声学处理的方法和装置，以及使用所述通信设备（102）的声学硬件（218,224）捕获（302）至少一个声学信号，表征（304）声学环境外部 使用所述至少一个捕获的声音信号将所述通信设备（102）发送到所述通信设备（102），基于所述特征的声学环境来适配（306）所述通信设备（102）内的声学处理。

公开(公告)号：WO2012161555A3

公开(公告)日：2013-01-24

申请号：PCT/KR2012004213

申请日：2012-05-29

Applicant: MIGHTYWORKS CO LTD ,  SHIN HO JOON ,  KIM SE UNG

Inventor： SHIN HO JOON ,  KIM SE UNG

IPC: G10L15/20

CPC classification number: H04R3/005 ,  G10L21/028 ,  G10L2021/02161

Abstract: Disclosed are a signal-separation system using a directional microphone array and a method for providing same. The signal-separation system comprises: a signal-receiving unit which receives a mixture signal, in which a first audio signal and a second audio signal are mixed, using a microphone array comprising: at least one first microphone installed in a first direction, and at least one second microphone installed in a direction different from the first direction, and then receives a reference signal through said at least one second microphone; and an audio-signal separation unit for canceling out the second audio signal in the mixture signal received by the signal-receiving unit. The audio-signal separation unit cancels out the second audio signal using the reference signal input through said at least one second microphone.

Abstract translation: 公开了使用定向麦克风阵列的信号分离系统及其提供方法。 信号分离系统包括：信号接收单元，其使用麦克风阵列接收其中混合了第一音频信号和第二音频信号的混合信号，所述麦克风阵列包括：安装在第一方向上的至少一个第一麦克风，以及 安装在与第一方向不同的方向上的至少一个第二麦克风，然后通过所述至少一个第二麦克风接收参考信号; 以及音频信号分离单元，用于消除由信号接收单元接收的混合信号中的第二音频信号。 音频信号分离单元使用通过所述至少一个第二麦克风输入的参考信号来取消第二音频信号。

公开(公告)号：WO2012161555A2

公开(公告)日：2012-11-29

申请号：PCT/KR2012/004213

申请日：2012-05-29

Applicant: 주식회사 마이티웍스 ,  신호준 ,  김세웅

Inventor： 신호준 ,  김세웅

IPC: G10L15/20

CPC classification number: H04R3/005 ,  G10L21/028 ,  G10L2021/02161

Abstract: 방향성 마이크 어레이를 이용한 신호 분리시스템 및 그 제공방법이 개시된다. 상기 제1방향을 향하도록 설치되는 적어도 하나의 제1마이크 및 상기 제1방향과는 다른 방향을 향하도록 설치되는 적어도 하나의 제2마이크를 포함하는 마이크 어레이를 이용하여 제1음성신호와 제2음성신호가 혼합된 혼합신호를 수신하고, 상기 적어도 하나의 제2마이크를 통해 레퍼런스 신호를 수신하기 위한 신호수신부, 상기 신호수신부에 의해 수신된 혼합신호에서 상기 제2음성신호를 상쇄하기 위한 음성신호 분리부를 포함하며, 상기 음성신호 분리부는 상기 적어도 하나의 제2마이크를 통해 입력된 상기 레퍼런스 신호를 이용하여 상기 제2음성신호를 상쇄하는 것을 특징으로 한다.

Abstract translation: 公开了使用定向麦克风阵列的信号分离系统及其提供方法。 信号分离系统包括：信号接收单元，其使用麦克风阵列接收其中混合了第一音频信号和第二音频信号的混合信号，所述麦克风阵列包括：安装在第一方向上的至少一个第一麦克风，以及 安装在与第一方向不同的方向上的至少一个第二麦克风，然后通过所述至少一个第二麦克风接收参考信号; 以及音频信号分离单元，用于消除由信号接收单元接收的混合信号中的第二音频信号。 音频信号分离单元使用通过所述至少一个第二麦克风输入的参考信号来取消第二音频信号。

公开(公告)号：WO03036614A2

公开(公告)日：2003-05-01

申请号：PCT/SG0200149

申请日：2002-07-02

Applicant: BITWAVE PRIVATE LTD ,  HUI SIEW KOK ,  LOH KOK HENG ,  LAU YEAN MING

Inventor： HUI SIEW KOK ,  LOH KOK HENG ,  LAU YEAN MING

IPC: G10L15/20 ,  G10L21/0208 ,  G10L21/0216 ,  H04M1/27 ,  H04M1/60 ,  H04M1/725 ,  G10L

CPC classification number: H04M1/6033 ,  G10L15/20 ,  G10L21/0208 ,  G10L2021/02161 ,  G10L2021/02168 ,  H04M1/271

Abstract: A headset system is proposed including a headset unit to be worn by a user and having two or more microphones, and a base unit in wireless communication with the headset. Signals received from the microphones are processed using a first adaptive filter to enhance a target signal, and then divided and supplied to a second adaptive filter arranged to reduce interference signals and a third filter arranged to reduce noise. The outputs of the second and third filters are combined, and are be subject to further processing in the frequency domain. The results are transmitted to a speech recognition engine.

Abstract translation: 提出一种耳机系统，其包括要由用户佩戴并具有两个或更多个麦克风的头戴耳机单元以及与耳机无线通信的基座单元。 使用第一自适应滤波器处理从麦克风接收的信号以增强目标信号，然后被分频并提供给布置成减少干扰信号的第二自适应滤波器和布置成降低噪声的第三滤波器。 第二和第三滤波器的输出被组合，并且在频域中被进一步处理。 结果被传送到语音识别引擎。

公开(公告)号：WO2017048375A1

公开(公告)日：2017-03-23

申请号：PCT/US2016/044558

申请日：2016-07-28

Applicant: QUALCOMM INCORPORATED

Inventor： KIM, Lae-Hoon ,  VISSER, Erik ,  PERI, Raghuveer

IPC: G10L21/0216 ,  G10L21/0232 ,  H04R3/00 ,  G07C9/00 ,  G10L17/00

CPC classification number: G10L21/0216 ,  G10L17/00 ,  G10L21/0232 ,  G10L2021/02161 ,  H04R3/00 ,  H04R2410/05

Abstract: A method of performing noise reduction includes capturing a first audio signal at a first microphone of a first device. The method also includes receiving, at the first device, audio data representative of a second audio signal from a second device. The second audio signal is captured by a second microphone of the second device. The method further includes performing noise reduction on the first audio signal based at least in part on the audio data representative of the second audio signal.

Abstract translation: 执行降噪的方法包括在第一设备的第一麦克风处捕获第一音频信号。 该方法还包括在第一设备处接收表示来自第二设备的第二音频信号的音频数据。 第二音频信号由第二设备的第二麦克风捕获。 该方法还包括至少部分地基于表示第二音频信号的音频数据对第一音频信号执行噪声降低。

公开(公告)号：WO2016099077A1

公开(公告)日：2016-06-23

申请号：PCT/KR2015/013535

申请日：2015-12-10

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： LIM, Ho-Yeong ,  LEE, Gi-Hoon

IPC: H04R1/04 ,  H04R1/08

CPC classification number: H04R1/406 ,  G10L21/0216 ,  G10L2021/02161 ,  H04M1/035 ,  H04R1/04 ,  H04R1/08 ,  H04R1/2853 ,  H04R1/326 ,  H04R1/342 ,  H04R3/005 ,  H04R2205/022 ,  H04R2499/11

Abstract: An acoustic input module and an electronic device including the same are provided. The acoustic input module of the electronic device includes a plurality of transducers mounted on one surface of a circuit board, a control module mounted on the circuit board for controlling the transducers, and a plurality of sound input holes formed in a housing of the electronic device. A first transducer receives a sound along a first directional path through a first sound input hole and converts the received sound into an electrical signal, and a second transducer receives a sound along a second directional path through a second sound input hole and converts the received sound into an electrical signal. Since the transducers detect sounds originating along different paths, the electronic device can include a multi-channel recording function with an ability to reinforce sound of a specific object and attenuate other sound.

Abstract translation: 提供声输入模块和包括该声输入模块的电子设备。 电子设备的声音输入模块包括安装在电路板的一个表面上的多个换能器，安装在用于控制换能器的电路板上的控制模块，以及形成在电子设备的壳体中的多个声音输入孔 。 第一传感器通过第一声音输入孔接收沿着第一定向路径的声音，并将接收到的声音转换成电信号，并且第二换能器通过第二声音输入孔接收沿着第二方向路径的声音，并转换所接收的声音 变成电信号。 由于换能器检测沿着不同路径发出的声音，所以电子设备可以包括具有加强特定对象的声音并衰减其他声音的能力的多声道记录功能。

公开(公告)号：WO2015012594A1

公开(公告)日：2015-01-29

申请号：PCT/KR2014/006705

申请日：2014-07-23

Applicant: 한국전자통신연구원

Inventor： 백승권 ,  성종모 ,  이태진 ,  강경옥 ,  서정일 ,  김진웅 ,  장대영

IPC: G10L19/008

CPC classification number: G10L19/008 ,  G10L2021/02082 ,  G10L2021/02161

Abstract: 잔향 신호를 이용한 다채널 오디오 신호의 디코딩 방법 및 디코더가 개시된다. 일실시예에 따른 디코딩 방법은 다채널 오디오 신호에 대해 엘리먼트 단위로 서로 다른 잔향 신호를 적용함으로써, 다채널 오디오 신호의 품질을 유지할 수 있다.

Abstract translation: 公开了一种通过使用混响信号来解码多声道音频信号的方法和解码器。 根据一个实施例，解码方法通过在多声道音频信号的元素单元中应用不同的混响信号来实现多声道音频信号的质量。

公开(公告)号：WO2014132167A1

公开(公告)日：2014-09-04

申请号：PCT/IB2014/059057

申请日：2014-02-18

Applicant: KONINKLIJKE PHILIPS N.V.

Inventor： SRINIVASAN, Sriram

IPC: G10L21/0208 ,  G10L19/083 ,  H04R1/40

CPC classification number: G10L21/0208 ,  G10L25/51 ,  G10L2021/02082 ,  G10L2021/02161 ,  H04R1/025 ,  H04R1/406 ,  H04R3/005 ,  H04R2201/023 ,  H04R2420/07

Abstract: An apparatus comprises microphone receivers (101) which receive microphone signals from a plurality of microphones (103). A comparator (105) determines a speech similarity indication indicative of a similarity between the microphone signal and non-reverberant speech for each microphone signal. The determination is in response to a comparison of a property derived from the microphone signal to a reference property for non- reverberant speech. In some embodiments, the comparator (105) determines the similarity indication by comparing to reference properties for speech samples of a set of non- reverberant speech samples. A generator (107) generates a speech signal by combining the microphone signals in response to the similarity indications. In many embodiments, the apparatus may be distributed over a plurality of devices each containing a microphone, and the approach may determine the most suited microphone for generating the speech signal.

Abstract translation: 一种装置包括从多个麦克风（103）接收麦克风信号的麦克风接收器（101）。 比较器（105）确定指示每个麦克风信号的麦克风信号和非混响语音之间的相似性的语音相似性指示。 该确定是响应于从麦克风信号导出的属性与非混响语音的参考属性的比较。 在一些实施例中，比较器（105）通过与一组非混响语音样本的语音样本的参考属性进行比较来确定相似性指示。 发生器（107）通过响应于相似性指示组合麦克风信号来产生语音信号。 在许多实施例中，设备可以分布在每个包含麦克风的多个设备上，并且该方法可以确定用于生成语音信号的最适合的麦克风。