公开(公告)号：US20140278391A1

公开(公告)日：2014-09-18

申请号：US13797250

申请日：2013-03-12

Applicant: INTERMEC IP CORP.

Inventor： Keith P. Braho ,  David D. Hardek

IPC: G10L15/08

CPC classification number: G10L15/20 ,  G10L25/78

Abstract: Audio frames are classified as either speech, non-transient background noise, or transient noise events. Probabilities of speech or transient noise event, or other metrics may be calculated to indicate confidence in classification. Frames classified as speech or noise events are not used in updating models (e.g., spectral subtraction noise estimates, silence model, background energy estimates, signal-to-noise ratio) of non-transient background noise. Frame classification affects acceptance/rejection of recognition hypothesis. Classifications and other audio related information may be determined by circuitry in a headset, and sent (e.g., wirelessly) to a separate processor-based recognition device.

Abstract translation: 音频帧被分类为语音，非瞬态背景噪声或瞬态噪声事件。 可以计算语音或瞬态噪声事件或其他度量的概率，以指示分类的置信度。 分类为语音或噪声事件的帧不用于非瞬态背景噪声的更新模型（例如频谱减法噪声估计，静音模型，背景能量估计，信噪比）。 框架分类影响识别假设的接受/拒绝。 分类和其它音频相关信息可以由耳机中的电路确定，并被发送（例如，无线地）到单独的基于处理器的识别装置。

公开(公告)号：US09299344B2

公开(公告)日：2016-03-29

申请号：US14789267

申请日：2015-07-01

Applicant: Intermec IP Corp.

Inventor： Keith P. Braho ,  David D. Hardek

IPC: G10L15/20 ,  G10L25/78

CPC classification number: G10L15/20 ,  G10L25/78

Abstract: Audio frames are classified as either speech, non-transient background noise, or transient noise events. Probabilities of speech or transient noise event, or other metrics may be calculated to indicate confidence in classification. Frames classified as speech or noise events are not used in updating models (e.g., spectral subtraction noise estimates, silence model, background energy estimates, signal-to-noise ratio) of non-transient background noise. Frame classification affects acceptance/rejection of recognition hypothesis. Classifications and other audio related information may be determined by circuitry in a headset, and sent (e.g., wirelessly) to a separate processor-based recognition device.

公开(公告)号：US20150302853A1

公开(公告)日：2015-10-22

申请号：US14789267

申请日：2015-07-01

Applicant: Intermec IP Corp.

Inventor： Keith P. Braho ,  David D. Hardek

IPC: G10L15/20

CPC classification number: G10L15/20 ,  G10L25/78

Abstract: Audio frames are classified as either speech, non-transient background noise, or transient noise events. Probabilities of speech or transient noise event, or other metrics may be calculated to indicate confidence in classification. Frames classified as speech or noise events are not used in updating models (e.g., spectral subtraction noise estimates, silence model, background energy estimates, signal-to-noise ratio) of non-transient background noise. Frame classification affects acceptance/rejection of recognition hypothesis. Classifications and other audio related information may be determined by circuitry in a headset, and sent (e.g., wirelessly) to a separate processor-based recognition device.

Abstract translation: 音频帧被分类为语音，非瞬态背景噪声或瞬态噪声事件。 可以计算语音或瞬态噪声事件或其他度量的概率，以指示分类的置信度。 分类为语音或噪声事件的帧不用于非瞬态背景噪声的更新模型（例如频谱减法噪声估计，静音模型，背景能量估计，信噪比）。 框架分类影响识别假设的接受/拒绝。 分类和其它音频相关信息可以由耳机中的电路确定，并且被发送（例如，无线地）到单独的基于处理器的识别装置。

公开(公告)号：US09076459B2

公开(公告)日：2015-07-07

申请号：US13797250

申请日：2013-03-12

Applicant: Intermec IP Corp.

Inventor： Keith P. Braho ,  David D. Hardek

IPC: G10L15/08 ,  G10L21/00 ,  G10L25/78 ,  G10L15/20

CPC classification number: G10L15/20 ,  G10L25/78

Abstract: Audio frames are classified as either speech, non-transient background noise, or transient noise events. Probabilities of speech or transient noise event, or other metrics may be calculated to indicate confidence in classification. Frames classified as speech or noise events are not used in updating models (e.g., spectral subtraction noise estimates, silence model, background energy estimates, signal-to-noise ratio) of non-transient background noise. Frame classification affects acceptance/rejection of recognition hypothesis. Classifications and other audio related information may be determined by circuitry in a headset, and sent (e.g., wirelessly) to a separate processor-based recognition device.

Abstract translation: 音频帧被分类为语音，非瞬态背景噪声或瞬态噪声事件。 可以计算语音或瞬态噪声事件或其他度量的概率，以指示分类的置信度。 分类为语音或噪声事件的帧不用于非瞬态背景噪声的更新模型（例如频谱减法噪声估计，静音模型，背景能量估计，信噪比）。 框架分类影响识别假设的接受/拒绝。 分类和其它音频相关信息可以由耳机中的电路确定，并被发送（例如，无线地）到单独的基于处理器的识别装置。