公开(公告)号：US10008205B2

公开(公告)日：2018-06-26

申请号：US14085382

申请日：2013-11-20

Applicant: GM Global Technology Operations LLC ,  General Motors LLC

Inventor： Xufang Zhao ,  Gaurav Talwar ,  Dipankar Pal ,  John L. Holdren

IPC: G10L15/32

CPC classification number: G10L15/32

Abstract: A method of choosing a nametag using automatic speech recognition (ASR) includes: receiving a spoken nametag via a microphone; performing a first speech recognition analysis on the spoken nametag; determining that the first speech recognition analysis outputs only handheld wireless device nametags; performing a second speech recognition analysis that excludes the handheld wireless device nametags stored at the handheld wireless device; and combining the results of the first speech recognition analysis and the second speech recognition analysis.

公开(公告)号：US20150142428A1

公开(公告)日：2015-05-21

申请号：US14085382

申请日：2013-11-20

Applicant: GENERAL MOTORS LLC ,  GM GLOBAL TECHNOLOGY OPERATIONS LLC

Inventor： Xufang Zhao ,  Gaurav Talwar ,  Dipankar Pal ,  John L. Holdren

IPC: G10L15/00

CPC classification number: G10L15/32

Abstract: According to an embodiment of the disclosure, there is provided a method of choosing a nametag using automatic speech recognition (ASR). The method includes receiving a spoken nametag via a microphone; performing a first speech recognition analysis on the spoken nametag; determining that the first speech recognition analysis outputs only handheld wireless device nametags; performing a second speech recognition analysis that excludes the handheld wireless device nametags stored at the handheld wireless device; and combining the results of the first speech recognition analysis and the second speech recognition analysis.

Abstract translation: 根据本公开的实施例，提供了一种使用自动语音识别（ASR）来选择名称的方法。 该方法包括通过麦克风接收口语名称; 对口语名词进行第一次语音识别分析; 确定第一语音识别分析仅输出手持无线设备名称; 执行第二语音识别分析，其排除存储在所述手持无线设备处的所述手持无线设备标识符; 并结合第一语音识别分析和第二语音识别分析的结果。

公开(公告)号：US09530414B2

公开(公告)日：2016-12-27

申请号：US14686042

申请日：2015-04-14

Applicant: GM Global Technology Operations LLC

Inventor： Xufang Zhao ,  Gaurav Talwar

IPC: G10L21/00 ,  G10L15/00 ,  G10L15/22 ,  B60W50/08

CPC classification number: G10L15/22 ,  B60W50/08 ,  B60W2540/02 ,  G10L15/08 ,  G10L2015/088 ,  G10L2015/223

Abstract: A system and method of controlling an automatic speech recognition (ASR) system includes: receiving speech at the ASR system from a vehicle occupant that includes a command to control a vehicle function; identifying a gate command from the speech; associating the identified gate command with the command to control the vehicle function; storing the associated gate command and vehicle command in a database; receiving additional speech at the ASR system from the vehicle occupant; detecting the gate command in the additional speech; and accessing the stored gate command and vehicle command from the database.

Abstract translation: 一种控制自动语音识别（ASR）系统的系统和方法包括：从包括控制车辆功能的命令的车辆乘员在ASR系统接收语音; 从语音识别门命令; 将所识别的门命令与用于控制车辆功能的命令相关联; 将相关联的门命令和车辆命令存储在数据库中; 在车载乘客的ASR系统接收额外的演讲; 在附加语音中检测门命令; 以及从数据库访问存储的门命令和车辆命令。

公开(公告)号：US20160268987A1

公开(公告)日：2016-09-15

申请号：US14643632

申请日：2015-03-10

Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC

Inventor： Gaurav Talwar ,  Xufang Zhao ,  MD Foezur Rahman Chowdhury ,  Eli Tzirkel-Hancock

IPC: H03G3/00 ,  G06F3/16

CPC classification number: G06F3/165 ,  G06F3/162 ,  G10L15/28 ,  G10L19/022 ,  G10L21/04

Abstract: A system and method of adjusting digital audio sampling used with wideband audio includes: performing audio sampling on an analog audio signal at an initial sampling rate and an initial bit rate over a wideband audio frequency range; generating a digital audio signal based on the audio sampling; detecting a qualitative error rate between the analog audio signal and the digital audio signal; and decreasing the initial sampling rate, the initial bit rate, or both for sampling subsequent analog audio when the qualitative error is below a threshold.

Abstract translation: 调整与宽带音频一起使用的数字音频采样的系统和方法包括：以初始采样率对模拟音频信号进行音频采样，并在宽带音频频率范围内执行初始比特率; 基于音频采样生成数字音频信号; 检测模拟音频信号和数字音频信号之间的定性错误率; 并且当定性误差低于阈值时，降低初始采样率，初始比特率或两者用于对后续模拟音频进行采样。

公开(公告)号：US09286030B2

公开(公告)日：2016-03-15

申请号：US14058060

申请日：2013-10-18

Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC

Inventor： John L. Holdren ,  Xufang Zhao ,  Gaurav Talwar

IPC: H04B1/00 ,  G06F3/16 ,  B60R11/02 ,  G10L15/22 ,  H04R1/02

CPC classification number: G06F3/167 ,  B60R11/0247 ,  G06F3/165 ,  G10L15/22 ,  G10L2015/223 ,  H04R1/02 ,  H04R2410/00 ,  H04R2499/13

Abstract: A method for processing a plurality of audio streams at a computer system onboard a vehicle is provided. The method receives the plurality of audio streams from a plurality of locations within a vehicle; prioritizes each of the plurality of audio streams to obtain a prioritization result; and completes a task associated with each of the plurality of audio streams, according to the prioritization result.

Abstract translation: 提供了一种在车辆上的计算机系统处理多个音频流的方法。 该方法从车辆内的多个位置接收多个音频流; 优先考虑多个音频流中的每一个以获得优先化结果; 并且根据优先级结果来完成与多个音频流中的每一个相关联的任务。

公开(公告)号：US09269352B2

公开(公告)日：2016-02-23

申请号：US13893088

申请日：2013-05-13

Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC

Inventor： Gaurav Talwar ,  Xufang Zhao

IPC: G10L15/08 ,  H04R3/00 ,  G10L15/00

CPC classification number: G10L15/083 ,  G10L15/005 ,  H04R3/005 ,  H04R2420/07 ,  H04R2430/03 ,  H04R2499/13

Abstract: At least first and second microphones with different frequency responses form part of a speech recognition system. The microphones are coupled to a processor that is configured to recognize a spoken word based on the microphone signals. The processor classifies the spoken word, and weights the signals from the microphones based on the classification of the spoken word.

Abstract translation: 具有不同频率响应的至少第一和第二麦克风构成语音识别系统的一部分。 麦克风被耦合到处理器，其被配置为基于麦克风信号来识别口语单词。 处理器对口语进行分类，并根据口语单词的分类对来自麦克风的信号加权。

公开(公告)号：US10255913B2

公开(公告)日：2019-04-09

申请号：US15046303

申请日：2016-02-17

Applicant: GM Global Technology Operations LLC

Inventor： Xufang Zhao ,  Gaurav Talwar

IPC: G10L15/00 ,  G10L15/22 ,  G10L15/01 ,  G10L15/19 ,  G10L25/60 ,  G10L15/10 ,  G10L15/14

Abstract: A system and method of processing disfluent speech at an automatic speech recognition (ASR) system includes: receiving speech from a speaker via a microphone; determining the received speech includes disfluent speech; accessing a disfluent speech grammar or acoustic model in response to the determination; and processing the received speech using the disfluent speech grammar.

公开(公告)号：US09609408B2

公开(公告)日：2017-03-28

申请号：US14294726

申请日：2014-06-03

Applicant: GM Global Technology Operations LLC

Inventor： Xufang Zhao ,  Robert D. Sims, III ,  Md Foezur Rahman Chowdhury ,  John J. Correia

IPC: H04R3/00 ,  H04R1/08 ,  B60R16/037

CPC classification number: H04R1/08 ,  B60R16/037 ,  H04R3/005 ,  H04R2201/025 ,  H04R2430/20 ,  H04R2499/13

Abstract: A hands-free audio system for a vehicle and method of using the system is described. The method includes controlling the directionality of a vehicle microphone. The steps of the method may include: (a) receiving a sensor value from at least one of a vehicle seat position sensor, a vehicle seat orientation sensor, or a vehicle mirror orientation sensor; (b) based on the received sensor value(s) of step (a), determining an origin of a vehicle user's speech; and (c) controlling the microphone sensitivity directionality based on the determined origin.

公开(公告)号：US09446770B2

公开(公告)日：2016-09-20

申请号：US14608776

申请日：2015-01-29

Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC

Inventor： Frank C. Valeri ,  Scott M. Reilly ,  Eli Tzirkel-Hancock ,  Gaurav Talwar ,  John L. Holdren ,  Xufang Zhao

IPC: B60W10/30 ,  G10L17/00 ,  B60W50/00 ,  B60W40/08

CPC classification number: B60W50/0098 ,  B60W2040/0881 ,  B60W2420/54 ,  G01H3/00 ,  G10K11/178 ,  G10K2210/1282 ,  G10L17/005 ,  G10L17/26 ,  G10L25/15 ,  G10L25/63

Abstract: A vehicle including a passenger compartment having a rear seating area is described. A method for monitoring the rear seating area of the passenger compartment includes monitoring a vehicle operating state comprising one of a key-on state and a key-off state and monitoring the rear seating area. A presence or absence of a passenger in the rear seating area is detected based upon the monitoring, and a control routine is executed based upon the vehicle operating state and the presence or absence of a passenger in the rear seating area.

Abstract translation: 描述了包括具有后座区的乘客舱的车辆。 一种用于监视乘客室的后座区域的方法包括监视包括按键状态和关闭状态之一的车辆操作状态并监视后座椅区域。 基于监视检测后座椅区域中的乘客的存在或不存在，并且基于车辆操作状态和后座椅区域中乘客的存在或不存在来执行控制程序。

公开(公告)号：US10008201B2

公开(公告)日：2018-06-26

申请号：US14867574

申请日：2015-09-28

Applicant: GM Global Technology Operations LLC

Inventor： Gaurav Talwar ,  Ron M. Hecht ,  Xufang Zhao

IPC: G10L15/06 ,  G10L15/04 ,  G10L15/19 ,  G10L13/06 ,  G10L19/06 ,  G06F7/00 ,  G06F17/20 ,  G06F3/16 ,  G06K9/62 ,  G06F17/30 ,  G09G5/00

CPC classification number: G10L15/19 ,  G10L15/04

Abstract: A system and method of performing automatic speech recognition (ASR) includes: receiving speech at a vehicle microphone; communicating the received speech to an ASR system; measuring an amount of time that elapses while speech is received; selecting a point-of-interest (POI) context or an address context based on the measured amount of received time; and processing the received speech using a POI context-based grammar when a POI context is selected or an address-based grammar when an address context is selected.