公开(公告)号：US09799333B2

公开(公告)日：2017-10-24

申请号：US14840089

申请日：2015-08-31

Applicant: Keith Kintzley ,  Aren Jansen ,  Hynek Hermansky ,  Kenneth Church

Inventor： Keith Kintzley ,  Aren Jansen ,  Hynek Hermansky ,  Kenneth Church

IPC: G10L15/00 ,  G10L15/22 ,  G10L15/14 ,  G10L15/08

CPC classification number: G10L15/22 ,  G10L15/14 ,  G10L2015/085 ,  G10L2015/088

Abstract: A system and method are provided for performing speech processing. A system includes an audio detection system configured to receive a signal including speech and a memory having stored therein a database of keyword models forming an ensemble of filters associated with each keyword in the database. A processor is configured to receive the signal including speech from the audio detection system, decompose the signal including speech into a sparse set of phonetic impulses, and access the database of keywords and convolve the sparse set of phonetic impulses with the ensemble of filters. The processor is further configured to identify keywords within the signal including speech based a result of the convolution and control operation the electronic system based on the keywords identified.

公开(公告)号：US20150371635A1

公开(公告)日：2015-12-24

申请号：US14840089

申请日：2015-08-31

Applicant: Keith Kintzley ,  Aren Jansen ,  Hynek Hermansky ,  Kenneth Church

Inventor： Keith Kintzley ,  Aren Jansen ,  Hynek Hermansky ,  Kenneth Church

IPC: G10L15/22

CPC classification number: G10L15/22 ,  G10L15/14 ,  G10L2015/085 ,  G10L2015/088

Abstract: A system and method are provided for performing speech processing. A system includes an audio detection system configured to receive a signal including speech and a memory having stored therein a database of keyword models forming an ensemble of filters associated with each keyword in the database. A processor is configured to receive the signal including speech from the audio detection system, decompose the signal including speech into a sparse set of phonetic impulses, and access the database of keywords and convolve the sparse set of phonetic impulses with the ensemble of filters. The processor is further configured to identify keywords within the signal including speech based a result of the convolution and control operation the electronic system based on the keywords identified.

Abstract translation: 提供了一种执行语音处理的系统和方法。 系统包括被配置为接收包括语音的信号的音频检测系统和其中存储有存储有数据库中与每个关键字相关联的过滤器的集合的关键字模型的数据库的存储器。 处理器被配置为从音频检测系统接收包括语音的信号，将包括语音的信号分解为稀疏语音脉冲集合，并访问关键字数据库，并将稀疏语音脉冲集合与滤波器组合进行卷积。 处理器还被配置为基于基于识别的关键词的卷积和控制操作电子系统的结果来识别包括语音的信号内的关键字。

公开(公告)号：US20140379347A1

公开(公告)日：2014-12-25

申请号：US13926659

申请日：2013-06-25

Applicant: Keith Kintzley ,  Aren Jansen ,  Hynek Hermansky ,  Kenneth Church

Inventor： Keith Kintzley ,  Aren Jansen ,  Hynek Hermansky ,  Kenneth Church

IPC: G10L15/02 ,  G10L15/187

CPC classification number: G10L15/22 ,  G10L15/14 ,  G10L2015/085 ,  G10L2015/088

Abstract: A system and method are provided for performing speech processing. A system includes an audio detection system configured to receive a signal including speech and a memory having stored therein a database of keyword models forming an ensemble of filters associated with each keyword in the database. A processor is configured to receive the signal including speech from the audio detection system, decompose the signal including speech into a sparse set of phonetic impulses, and access the database of keywords and convolve the sparse set of phonetic impulses with the ensemble of filters. The processor is further configured to identify keywords within the signal including speech based a result of the convolution and control operation the electronic system based on the keywords identified.

Abstract translation: 提供了一种执行语音处理的系统和方法。 系统包括被配置为接收包括语音的信号的音频检测系统和其中存储有存储有数据库中与每个关键字相关联的过滤器的集合的关键字模型的数据库的存储器。 处理器被配置为从音频检测系统接收包括语音的信号，将包括语音的信号分解为稀疏语音脉冲集合，并访问关键字数据库，并将稀疏语音脉冲集合与滤波器组合进行卷积。 处理器还被配置为基于基于识别的关键词的卷积和控制操作电子系统的结果来识别包括语音的信号内的关键字。

公开(公告)号：US20230308823A1

公开(公告)日：2023-09-28

申请号：US18042258

申请日：2020-08-26

Applicant: Manoj PLAKAL ,  Dan ELLIS ,  Shawn HERSHEY ,  Richard Channing MOORE, III ,  Aren JANSEN ,  Google LLC

Inventor： Aren Jansen ,  Manoj Plakal ,  Dan Ellis ,  Shawn Hershey ,  Richard Channing Moore, III

IPC: H04S7/00

CPC classification number: H04S7/301 ,  H04S2400/01

Abstract: A computer-implemented method for upmixing audiovisual data can include obtaining audiovisual data including input audio data and video data accompanying the input audio data. Each frame of the video data can depict only a portion of a larger scene. The input audio data can have a first number of audio channels. The computer-implemented method can include providing the audiovisual data as input to a machine-learned audiovisual upmixing model. The audiovisual upmixing model can include a sequence-to-sequence model configured to model a respective location of one or more audio sources within the larger scene over multiple frames of the video data. The computer-implemented method can include receiving upmixed audio data from the audiovisual upmixing model. The upmixed audio data can have a second number of audio channels. The second number of audio channels can be greater than the first number of audio channels.

公开(公告)号：US09177547B2

公开(公告)日：2015-11-03

申请号：US13926659

申请日：2013-06-25

Applicant: Keith Kintzley ,  Aren Jansen ,  Hynek Hermansky ,  Kenneth Church

Inventor： Keith Kintzley ,  Aren Jansen ,  Hynek Hermansky ,  Kenneth Church

IPC: G10L15/22 ,  G10L15/14 ,  G10L15/08

CPC classification number: G10L15/22 ,  G10L15/14 ,  G10L2015/085 ,  G10L2015/088

Abstract: A system and method are provided for performing speech processing. A system includes an audio detection system configured to receive a signal including speech and a memory having stored therein a database of keyword models forming an ensemble of filters associated with each keyword in the database. A processor is configured to receive the signal including speech from the audio detection system, decompose the signal including speech into a sparse set of phonetic impulses, and access the database of keywords and convolve the sparse set of phonetic impulses with the ensemble of filters. The processor is further configured to identify keywords within the signal including speech based a result of the convolution and control operation the electronic system based on the keywords identified.

Abstract translation: 提供了一种执行语音处理的系统和方法。 系统包括被配置为接收包括语音的信号的音频检测系统和其中存储有存储有数据库中与每个关键字相关联的过滤器的集合的关键字模型的数据库的存储器。 处理器被配置为从音频检测系统接收包括语音的信号，将包括语音的信号分解为稀疏语音脉冲集合，并访问关键字数据库，并将稀疏语音脉冲集合与滤波器组合进行卷积。 处理器还被配置为基于基于识别的关键词的卷积和控制操作电子系统的结果来识别包括语音的信号内的关键字。