公开(公告)号：US20100290633A1

公开(公告)日：2010-11-18

申请号：US12376337

申请日：2007-10-18

Applicant: Yin-Shan Chen ,  Che-Ming Lin ,  Chien-Ming Wu ,  Chia-Shin Yen

Inventor： Yin-Shan Chen ,  Che-Ming Lin ,  Chien-Ming Wu ,  Chia-Shin Yen

IPC: H03G3/20

CPC classification number: H03G3/32

Abstract: A method and an apparatus for automatic noise compensation used with audio reproduction equipment are provided. The method comprises: (a) collecting a plurality of mixed audio signals, each mixed audio signal including equipment sound output by the audio reproduction equipment, and background noise; (b) removing the equipment sound from the mixed audio signals to obtain the background noise therein; (c) determining whether or not a plurality of mixed audio signals under inspection include a significant sound; and (d) adjusting the volume of the audio reproduction equipment according to whether or not a significant sound has been generated in the surrounding area and the magnitude of the background noise in the mixed audio signals under inspection to satisfy a plurality of predetermined compensation conditions.

Abstract translation: 提供了一种用于与音频再现设备一起使用的自动噪声补偿的方法和装置。 该方法包括：（a）收集多个混合音频信号，每个混合音频信号包括音频再现设备输出的设备声音和背景噪声; （b）从混合音频信号中去除设备声音，以获得其中的背景噪声; （c）确定被检查的多个混合音频信号是否包含有效声音; 以及（d）根据在周边区域是否产生有效声音以及被检查的混合音频信号中的背景噪声的大小是否满足多个预定的补偿条件来调节音频再现设备的音量。

公开(公告)号：US20100290632A1

公开(公告)日：2010-11-18

申请号：US12376637

申请日：2007-11-15

Applicant: Che-Ming Lin

Inventor： Che-Ming Lin

IPC: H04R29/00 ,  H04R25/00

CPC classification number: G01S3/8006 ,  H04R1/1083 ,  H04R5/033

Abstract: An apparatus for detecting sound includes a plurality of microphones, a sound inspecting unit, a direction estimating unit, a background noise removing unit, and an alerting unit. The microphones are used to collect sounds around a user. The sound inspecting unit is used to calculate the feature values of a background noise within a preset time interval, and to determine if a latest collected sound satisfies a preset condition. When the preset condition is satisfied, the direction estimating unit is used to estimate the occurrence direction of the latest collected sound, and to determine if the occurrence direction is within a preset range behind the user. When the preset range is satisfied, the background noise removing unit is used to remove the background noise in the latest collected sound so as to obtain a detected sound. The alerting unit is used to inform the user of the detected sound via an alert message. A method for detecting sound is also disclosed.

Abstract translation: 用于检测声音的装置包括多个麦克风，声音检查单元，方向估计单元，背景噪声去除单元和警报单元。 麦克风用于收集用户周围的声音。 声音检查单元用于在预设时间间隔内计算背景噪声的特征值，并且确定最近收集的声音是否满足预设条件。 当满足预设条件时，方向估计单元用于估计最新收集的声音的发生方向，并且确定发生方向是否在用户后面的预设范围内。 当满足预设范围时，背景噪声去除单元用于去除最新收集的声音中的背景噪声，以便获得检测到的声音。 警报单元用于通过警报消息通知用户检测到的声音。 还公开了一种用于检测声音的方法。

公开(公告)号：US08340308B2

公开(公告)日：2012-12-25

申请号：US12376337

申请日：2007-10-18

Applicant: Yin-Shan Chen ,  Che-Ming Lin ,  Chien-Ming Wu ,  Chia-Shin Yen

Inventor： Yin-Shan Chen ,  Che-Ming Lin ,  Chien-Ming Wu ,  Chia-Shin Yen

IPC: H04R29/00

CPC classification number: H03G3/32

Abstract: A method and an apparatus for automatic noise compensation used with audio reproduction equipment are provided. The method comprises: (a) collecting a plurality of mixed audio signals, each mixed audio signal including equipment sound output by the audio reproduction equipment, and background noise; (b) removing the equipment sound from the mixed audio signals to obtain the background noise therein; (c) determining whether or not a plurality of mixed audio signals under inspection include a significant sound; and (d) adjusting the volume of the audio reproduction equipment according to whether or not a significant sound has been generated in the surrounding area and the magnitude of the background noise in the mixed audio signals under inspection to satisfy a plurality of predetermined compensation conditions.

Abstract translation: 提供了一种用于与音频再现设备一起使用的自动噪声补偿的方法和装置。 该方法包括：（a）收集多个混合音频信号，每个混合音频信号包括音频再现设备输出的设备声音和背景噪声; （b）从混合音频信号中去除设备声音，以获得其中的背景噪声; （c）确定被检查的多个混合音频信号是否包含有效声音; 以及（d）根据在周边区域是否产生有效声音以及被检查的混合音频信号中的背景噪声的大小是否满足多个预定的补偿条件来调节音频再现设备的音量。

公开(公告)号：US07809560B2

公开(公告)日：2010-10-05

申请号：US11814024

申请日：2006-01-26

Applicant: Chia-Shin Yen ,  Chien-Ming Wu ,  Che-Ming Lin

Inventor： Chia-Shin Yen ,  Chien-Ming Wu ,  Che-Ming Lin

IPC: G10L21/02

CPC classification number: G10L21/0272

Abstract: In a method and system for identifying speech sound and non-speech sound in an environment, a speech signal and other non-speech signals are identified from a mixed sound source having a plurality of channels. The method includes the following steps: (a) using a blind source separation (BSS) unit to separate the mixed sound source into a plurality of sound signals; (b) storing spectrum of each of the sound signals; (c) calculating spectrum fluctuation of each of the sound signals in accordance with stored past spectrum information and current spectrum information sent from the blind source separation unit; and (d) identifying one of the sound signals that has a largest spectrum fluctuation as the speech signal.

Abstract translation: 在用于识别环境中的语音和非语音的方法和系统中，从具有多个频道的混合声源识别语音信号和其他非语音信号。 该方法包括以下步骤：（a）使用盲源分离单元将混合声源分离成多个声音信号; （b）存储每个声音信号的频谱; （c）根据从盲源分离单元发送的存储的过去的频谱信息和当前频谱信息，计算每个声音信号的频谱波动; 和（d）将具有最大频谱波动的声音信号中的一个识别为语音信号。

公开(公告)号：US20090070108A1

公开(公告)日：2009-03-12

申请号：US11814024

申请日：2006-01-26

Applicant: Chia-Shin Yen ,  Chien-Ming Wu ,  Che-Ming Lin

Inventor： Chia-Shin Yen ,  Chien-Ming Wu ,  Che-Ming Lin

IPC: G10L15/20

CPC classification number: G10L21/0272

Abstract: In a method and system for identifying speech sound and non-speech sound in an environment, a speech signal and other non-speech signals are identified from a mixed sound source having a plurality of channels. The method includes the following steps: (a) using a blind source separation (BSS) unit to separate the mixed sound source into a plurality of sound signals; (b) storing spectrum of each of the sound signals; (c) calculating spectrum fluctuation of each of the sound signals in accordance with stored past spectrum information and current spectrum information sent from the blind source separation unit; and (d) identifying one of the sound signals that has a largest spectrum fluctuation as the speech signal.

Abstract translation: 在用于识别环境中的语音和非语音的方法和系统中，从具有多个频道的混合声源识别语音信号和其他非语音信号。 该方法包括以下步骤：（a）使用盲源分离单元将混合声源分离成多个声音信号; （b）存储每个声音信号的频谱; （c）根据从盲源分离单元发送的存储的过去的频谱信息和当前频谱信息，计算每个声音信号的频谱波动; 和（d）将具有最大频谱波动的声音信号中的一个识别为语音信号。

公开(公告)号：US08037006B2

公开(公告)日：2011-10-11

申请号：US11994037

申请日：2006-06-27

Applicant: Chia-Shin Yen ,  Che-Ming Lin ,  Koichiro Mizushima

Inventor： Chia-Shin Yen ,  Che-Ming Lin ,  Koichiro Mizushima

IPC: G06F17/00 ,  G06N5/02

CPC classification number: G10L17/26 ,  G10L2015/0636

Abstract: A sound classification system for adding and correcting a sound type is disclosed. When the add/correct command processor receives a command to add or correct a sound type, the data in the first database is stored in the second database, and the type adding/correcting device adds the feature of the sound to the first database, and re-calculates the statistical values. Besides, the classifier re-classifies the sample sounds, and the precision calculator calculates a ratio of accurate classification. When the ratio is high, the type adding/correcting device stores, in the feature database, the feature of the sound for which a type is to be added or corrected. When the ratio is low, the second database restores the data back to the first database.

Abstract translation: 公开了一种用于添加和校正声音类型的声音分类系统。 当附加/正确命令处理器接收到添加或更正声音类型的命令时，第一数据库中的数据被存储在第二数据库中，并且类型添加/校正装置将声音的特征添加到第一数据库，以及 重新计算统计值。 此外，分类器重新分类样本声音，精度计算器计算准确分类的比率。 当比率高时，类型添加/校正装置在特征数据库中存储要添加或校正类型的声音的特征。 当比率低时，第二个数据库将数据恢复回第一个数据库。

公开(公告)号：US08098832B2

公开(公告)日：2012-01-17

申请号：US12376637

申请日：2007-11-15

Applicant: Che-Ming Lin

Inventor： Che-Ming Lin

IPC: H04R29/00

CPC classification number: G01S3/8006 ,  H04R1/1083 ,  H04R5/033

Abstract: An apparatus for detecting sound includes a plurality of microphones, a sound inspecting unit, a direction estimating unit, a background noise removing unit, and an alerting unit. The microphones are used to collect sounds around a user. The sound inspecting unit is used to calculate the feature values of a background noise within a preset time interval, and to determine if a latest collected sound satisfies a preset condition. When the preset condition is satisfied, the direction estimating unit is used to estimate the occurrence direction of the latest collected sound, and to determine if the occurrence direction is within a preset range behind the user. When the preset range is satisfied, the background noise removing unit is used to remove the background noise in the latest collected sound so as to obtain a detected sound. The alerting unit is used to inform the user of the detected sound via an alert message. A method for detecting sound is also disclosed.

Abstract translation: 用于检测声音的装置包括多个麦克风，声音检查单元，方向估计单元，背景噪声去除单元和警报单元。 麦克风用于收集用户周围的声音。 声音检查单元用于在预设时间间隔内计算背景噪声的特征值，并且确定最近收集的声音是否满足预设条件。 当满足预设条件时，方向估计单元用于估计最新收集的声音的发生方向，并且确定发生方向是否在用户后面的预设范围内。 当满足预设范围时，背景噪声去除单元用于去除最新收集的声音中的背景噪声，以便获得检测到的声音。 警报单元用于通过警报消息通知用户检测到的声音。 还公开了一种用于检测声音的方法。

公开(公告)号：US20090228422A1

公开(公告)日：2009-09-10

申请号：US11994037

申请日：2006-06-27

Applicant: Chia-Shin Yen ,  Che-Ming Lin ,  Koichiro Mizushima

Inventor： Chia-Shin Yen ,  Che-Ming Lin ,  Koichiro Mizushima

IPC: G06N7/02 ,  G10L17/00 ,  G06F17/30

CPC classification number: G10L17/26 ,  G10L2015/0636

Abstract: A sound classification system for adding and correcting a sound type is disclosed. When the add/correct command processor receives a command to add or correct a sound type, the data in the first database is stored in the second database, and the type adding/correcting device adds the feature of the sound to the first database, and re-calculates the statistical values. Besides, the classifier re-classifies the sample sounds, and the precision calculator calculates a ratio of accurate classification. When the ratio is high, the type adding/correcting device stores, in the feature database, the feature of the sound for which a type is to be added or corrected. When the ratio is low, the second database restores the data back to the first database.

Abstract translation: 公开了一种用于添加和校正声音类型的声音分类系统。 当附加/正确命令处理器接收到添加或更正声音类型的命令时，第一数据库中的数据被存储在第二数据库中，并且类型添加/校正装置将声音的特征添加到第一数据库，以及 重新计算统计值。 此外，分类器重新分类样本声音，精度计算器计算准确分类的比率。 当比率高时，类型添加/校正装置在特征数据库中存储要添加或校正类型的声音的特征。 当比率低时，第二个数据库将数据恢复回第一个数据库。