专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明公开

US20240233752A1 CONTINUOUS DIALOG WITH A DIGITAL ASSISTANT 审中-公开
公开(公告)号：US20240233752A1
公开(公告)日：2024-07-11
申请号：US18614510
申请日：2024-03-22
申请人： Apple Inc.
发明人： Garrett L. WEINBERG , Harry J. SADDLER
IPC分类号： G10L25/78 , G06F3/01 , G10L15/08 , G10L15/18 , G10L15/22
CPC分类号： G10L25/78 , G06F3/013 , G10L15/083 , G10L15/1807 , G10L15/22 , G10L2015/088 , G10L2015/221 , G10L2015/223 , G10L2025/786
摘要： Systems and processes for operating an intelligent automated assistant are provided. For example, a first speech input directed to a digital assistant is received from a user. A first response is provided based on the first speech input. A session window is initiated, wherein the session window is associated with a variable speech threshold. A second speech input is received during the session window. In accordance with a determination that the second speech input includes speech directed to the digital assistant, a duration associated with the session window is increased. In accordance with a determination that the variable speech threshold does not exceed a predetermined speech threshold, the session window is ended.

2. 发明授权

US11955137B2 Continuous dialog with a digital assistant 有权
公开(公告)号：US11955137B2
公开(公告)日：2024-04-09
申请号：US17330145
申请日：2021-05-25
申请人： Apple Inc.
发明人： Garrett L. Weinberg , Harry J. Saddler
IPC分类号： G10L15/22 , G06F3/01 , G10L15/08 , G10L15/18 , G10L25/78
CPC分类号： G10L25/78 , G06F3/013 , G10L15/083 , G10L15/1807 , G10L15/22 , G10L2015/088 , G10L2015/221 , G10L2015/223 , G10L2025/786
摘要： Systems and processes for operating an intelligent automated assistant are provided. For example, a first speech input directed to a digital assistant is received from a user. A first response is provided based on the first speech input. A session window is initiated, wherein the session window is associated with a variable speech threshold. A second speech input is received during the session window. In accordance with a determination that the second speech input includes speech directed to the digital assistant, a duration associated with the session window is increased. In accordance with a determination that the variable speech threshold does not exceed a predetermined speech threshold, the session window is ended.

3. 发明授权

US11950057B2 Hearing device comprising a speech intelligibility estimator 有权
公开(公告)号：US11950057B2
公开(公告)日：2024-04-02
申请号：US17840172
申请日：2022-06-14
申请人： Oticon A/S
发明人： Jesper Jensen , Asger Heidemann Andersen
IPC分类号： H04R25/00 , G10L25/78
CPC分类号： H04R25/507 , G10L25/78 , G10L2025/786 , H04R2225/41
摘要： A hearing device, e.g. a hearing aid, comprises a) an input unit configured to provide at least one time-variant electric input signal representing sound, the at least one electric input signal comprising target signal components and optionally noise signal components, the target signal components originating from a target sound source; b) a signal processing unit for processing the at least one electric input signal and providing a processed signal; c) an output unit for creating output stimuli configured to be perceivable by the user as sound based on the processed signal from the signal processing unit; d) a speech presence probability prediction unit for repeatedly providing a measure of a predicted speech presence probability of the at least one electric input signal, or of a signal originating therefrom; and e) a speech intelligibility prediction unit for repeatedly providing a current measure of a predicted speech intelligibility of the at least one electric input signal, or of a signal originating therefrom. The speech intelligibility prediction unit is configured to determine said current measure of the predicted speech intelligibility in dependence of said measure of the predicted speech presence probability. A method of operating a hearing device is further disclosed. The invention may e.g. be used in hearing aids, headsets, earpieces (ear buds), etc.

4. 发明公开

US20230317100A1 Method of Detecting Speech Using an in Ear Audio Sensor 审中-公开
公开(公告)号：US20230317100A1
公开(公告)日：2023-10-05
申请号：US18127131
申请日：2023-03-28
申请人： Harman International Industries, Incorporated
发明人： Ruiting Yang , Linwei SHI , Yiyuan WANG , Xiang DENG , Shaomin Sharon Peng
IPC分类号： G10L25/84 , G10L15/22 , G10L15/02
CPC分类号： G10L25/84 , G10L15/22 , G10L15/02 , G10L2025/786
摘要： The present disclosure provides a method for detecting voice using an in-ear audio sensor, including performing the following processing on each frame of input signals collected by the in-ear audio sensor: calculating a count change value based on at least one feature of an input signal of a current frame, wherein the at least one feature includes at least one of an estimated signal-to-noise ratio, a spectral centroid, a spectral flux, a spectral flux difference value, spectral flatness, energy distribution, and spectral correlations between adjacent frames; adding the calculated count change value with a previous count value of a previous frame to obtain a current count value; comparing the obtained current count value with a count threshold; and determining the category of the input signal of the current frame based on the comparison result and feature attributes, wherein the category includes noise, voiced sound, or unvoiced sound.

5. 发明授权

US11646026B2 Information processing system, and information processing method 有权
公开(公告)号：US11646026B2
公开(公告)日：2023-05-09
申请号：US17364545
申请日：2021-06-30
申请人： SONY GROUP CORPORATION
发明人： Akihiro Komori
IPC分类号： H04M1/64 , G10L15/22 , G06N3/00 , G06F16/00 , G06F16/332 , G06F3/16 , G10L15/30 , G10L25/78
CPC分类号： G10L15/22 , G06F3/16 , G06F16/00 , G06F16/3329 , G06N3/00 , G10L15/30 , G10L25/78 , G10L2025/786
摘要： The present disclosure provides an information processing system and an information processing method capable of auditing the utterance data of an agent more flexibly. In one example, an information processing system includes: a storage section that stores utterance data of an agent; a communication section that receives request information transmitted from a client terminal and requesting utterance data of a specific agent from a user; and a control section that, when the request information is received through the communication section, replies to the client terminal with corresponding utterance data, and in accordance with feedback from the user with respect to the utterance data, updates an utterance probability level expressing a probability that the specific agent will utter utterance content indicated by the utterance data, and records the updated utterance probability level in association with the specific agent and the utterance content in the storage section.

6. 发明申请

US20180315443A1 METHOD AND APPARATUS FOR VOICE ACTIVITY DETECTION 审中-公开
公开(公告)号：US20180315443A1
公开(公告)日：2018-11-01
申请号：US15498560
申请日：2017-04-27
申请人： MOTOROLA SOLUTIONS, INC
发明人： CHEAH HENG TAN , THEAN HAI OOI , WEI QING ONG , ALAN WEE CHIAT TAN
IPC分类号： G10L25/84 , G10L25/21 , G10L25/18
CPC分类号： G10L25/84 , G10L25/03 , G10L25/18 , G10L2025/786
摘要： A voice activity detection system (100) filters audio input frames (102), on a frame=by-frame basis through a gammatone filterbank (104) to generate filtered gammatone output signals (106). A signal energy calculator (108) takes the filtered gammatone output signals and generates a plurality of energy envelopes. Weighting factors are constructed (112) are applied to each of the energy envelopes thereby producing normalized weighted signal (116), in which voice regions are emphasized and noise regions are minimized. An entropy measurement (118) is taken to extract information from the normalized weighted signals (116) and generate an entropy signal (120). The entropy signal (120) is averaged and compared to an adaptive entropy threshold (122), indicative of a noise floor. Decision logic (124) is used to identifying speech and noise from the comparison of the averaged entropy signal to the adaptive entropy threshold.

7. 发明授权

US09978398B2 Voice activity detection method and device 有权
公开(公告)号：US09978398B2
公开(公告)日：2018-05-22
申请号：US14915246
申请日：2014-05-16
申请人： ZTE CORPORATION
发明人： Changbao Zhu , Hao Yuan
IPC分类号： G10L25/78 , G10L25/84 , G10L17/06 , G10L25/48
CPC分类号： G10L25/84 , G10L17/06 , G10L25/48 , G10L25/78 , G10L2025/786
摘要： Disclosed are a voice activity detection method and device, wherein the method includes: obtaining a combined VAD judgment result according to the number of continuous active frames, an average total SNR of all sub-bands, a tonal signal flag, and at least two existing VAD judgment results (107). The method and device are suitable for voice service, solve the problem of inaccurate VAD detection and realize highly accurate VAD judgment.

8. 发明授权

US09964433B2 Acoustic sensor with an acoustic object detector for reducing power consumption in front-end circuit 有权
公开(公告)号：US09964433B2
公开(公告)日：2018-05-08
申请号：US13984786
申请日：2011-11-10
申请人： Dingkun Du , Kofi Odame
发明人： Dingkun Du , Kofi Odame
IPC分类号： G01H11/00 , G01H11/06 , G10L25/78
CPC分类号： G01H11/06 , G10L25/78 , G10L2025/786
摘要： An acoustic object detector for detecting presence of an acoustic signal is provided. The acoustic object detector includes a number of bandpass filters. Each bandpass filter is configured to convert an input signal into an analog signal within a frequency band. The acoustic object detector also includes a number of spike generating circuits each coupled to the respective bandpass filter. Each spike generating circuit is configured to generate a series of spike signals based upon an adaptive threshold for the analog signal. The acoustic object detection further includes a decision circuit configured to generate a digital signal at a time-frequency point from the series of spike signals.

9. 发明授权

US09940949B1 Dynamic adjustment of expression detection criteria 有权
公开(公告)号：US09940949B1
公开(公告)日：2018-04-10
申请号：US14578097
申请日：2014-12-19
申请人： Amazon Technologies, Inc.
发明人： Shiv Naga Prasad Vitaladevuni , Philip Ryan Hilmes
IPC分类号： G10L25/78 , H04R3/00
CPC分类号： G10L25/78 , G10L15/22 , G10L2021/02166 , G10L2025/786 , H04R3/005 , H04R2430/20
摘要： In a speech-based system, a wake word or other trigger expression is used to preface user speech that is intended as a command. The system receives multiple directional audio signals, each of which emphasizes sound from a different direction. The trigger expression is detected in an individual directional audio signal by comparing a confidence score with a confidence threshold. An individual confidence threshold is specified for each directional audio signal. The confidence thresholds are adjusted during operation of the system based on performance information that is generated during operation of the system. As an example, performance information may include the number of times that the trigger expression has been detected in each of the directional audio signals.

10. 发明申请

US20180090127A1 ADAPTIVE SPEECH ENDPOINT DETECTOR 审中-公开
公开(公告)号：US20180090127A1
公开(公告)日：2018-03-29
申请号：US15277164
申请日：2016-09-27
申请人： Intel Corporation
发明人： Joachim HOFER , Munir GEORGES
IPC分类号： G10L15/04 , G10L25/87 , G10L15/07 , G10L15/22
CPC分类号： G10L15/04 , G10L15/07 , G10L15/22 , G10L25/87 , G10L2025/786
摘要： An embodiment of a speech endpoint detector apparatus may include a speech detector to detect a presence of speech in an electronic speech signal, a pause duration measurer communicatively coupled to the speech detector to measure a duration of a pause following a period of detected speech, an end of utterance detector communicatively coupled to the pause duration measurer to detect if the pause measured following the period of detected speech is greater than a pause threshold corresponding to an end of an utterance, and a pause threshold adjuster to adaptively adjust the pause threshold corresponding to an end of an utterance based on stored pause information. Other embodiments are disclosed and claimed.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式