公开(公告)号：US10394518B2

公开(公告)日：2019-08-27

申请号：US15450005

申请日：2017-03-05

Applicant: MEDIATEK INC.

Inventor： Xin-Wei Shih ,  Chia-Ying Li ,  Chao-Ling Hsu ,  Yiou-Wen Cheng ,  Shen-Kai Chang

IPC: G06F17/00 ,  G06F3/16 ,  G11B20/10 ,  G11B27/10 ,  H04R29/00

Abstract: An audio synchronization method includes: receiving a first audio signal from a first recording device; receiving a second audio signal from a second recording device; performing a correlation operation upon the first audio signal and the second audio signal to align a first pattern of the first audio signal and the first pattern of the second audio signal; after the first patterns of the first audio signal and the second audio signal are aligned, calculating a difference between a second pattern of the first audio signal and the second pattern of the second audio signal; and obtaining a starting-time difference between the first audio signal and the second audio signal for audio synchronization according to the difference between the second pattern of the first audio signal and the second pattern of the second audio signal.

公开(公告)号：US10176793B2

公开(公告)日：2019-01-08

申请号：US15653506

申请日：2017-07-18

Applicant: MEDIATEK INC.

Inventor： Chao-Ling Hsu ,  Yiou-Wen Cheng

IPC: G10K11/178 ,  H04R3/00 ,  H04R1/10

Abstract: A method for performing active noise control upon a target zone includes: using an adaptive filtering circuit to receive at least one microphone signal obtained from a microphone; and, dynamically compensating at least one coefficient of the adaptive filtering circuit to adjust a frequency response of the adaptive filtering circuit according to an energy distribution of the at least one microphone signal, so as to make the adaptive filtering circuit receive the at least one microphone signal to generate a resultant anti-noise signal to the target zone based on the dynamically adjusted frequency response.

公开(公告)号：US09756421B2

公开(公告)日：2017-09-05

申请号：US15003954

申请日：2016-01-22

Applicant: MediaTek Inc.

Inventor： Chao-Ling Hsu ,  Yiou-Wen Cheng ,  Liang-Che Sun

IPC: H04R3/00 ,  G06F3/16 ,  G06T7/20

CPC classification number: H04R3/005 ,  G06F3/165 ,  G06T7/246 ,  H04R1/406 ,  H04R2201/401 ,  H04R2430/20 ,  H04R2430/25 ,  H04S2400/11 ,  H04S2400/15

Abstract: An audio refocusing method includes receiving an indication signal indicating which sound source in a recorded signal has to be refocused on; determining a direction of the sound source or a location of the sound source; and enhancing sound generated by the sound source in the recorded signal according to the direction or the location of the sound source to generate a processed signal.

公开(公告)号：US09747894B2

公开(公告)日：2017-08-29

申请号：US14166881

申请日：2014-01-29

Applicant: MEDIATEK Inc.

Inventor： Chao-Ling Hsu ,  Yiou-Wen Cheng ,  Liang-Che Sun ,  Yuanyuan Wang

IPC: G10L15/08 ,  G10L15/22

CPC classification number: G10L15/08 ,  G10L15/22 ,  G10L2015/228

Abstract: The invention provides a system for speech keyword detection and associated method. The system includes a speech keyword detector, an activity predictor and a decision maker. The activity predictor obtains sensor data provided by a plurality of sensors, and processes the sensor data to provide an activity prediction result indicating a probability for whether a user is about to give voice keyword. The decision maker processes the activity prediction result and a preliminary keyword detection result of the speech keyword detection to provide a keyword detection result.

公开(公告)号：US09691382B2

公开(公告)日：2017-06-27

申请号：US14078551

申请日：2013-11-13

Applicant: MEDIATEK INC.

Inventor： Chao-Ling Hsu ,  Yiou-Wen Cheng ,  Xin-Wei Shih ,  Jyh-Horng Lin

IPC: G10L15/22 ,  G06F3/01

CPC classification number: G10L15/22 ,  G06F3/017 ,  G10L2015/223

Abstract: A voice control device has a speech command recognizer, a sensor data processor and a decision making circuit. The speech command recognizer is arranged for performing speech command recognition to output a recognized speech command. The sensor data processor is arranged for processing sensor data generated from at least one auxiliary sensor to generate a detection output. The decision making circuit is arranged for deciding a response of the voice control device according to the recognized speech command and the detection output. The same speech command is able to trigger difference responses according to the detection output (e.g., detected motion). Besides, an adaptive training process may be employed to improve the accuracy of the sensor data processor. Hence, the voice control device may have improved performance of the voice control feature due to a reduce occurrence probability of miss errors and false alarm errors.

公开(公告)号：US20140249820A1

公开(公告)日：2014-09-04

申请号：US14078551

申请日：2013-11-13

Applicant: MEDIATEK INC.

Inventor： Chao-Ling Hsu ,  Yiou-Wen Cheng ,  Xin-Wei Shih ,  Jyh-Horng Lin

IPC: G10L15/06

CPC classification number: G10L15/22 ,  G06F3/017 ,  G10L2015/223

Abstract: A voice control device has a speech command recognizer, a sensor data processor and a decision making circuit. The speech command recognizer is arranged for performing speech command recognition to output a recognized speech command. The sensor data processor is arranged for processing sensor data generated from at least one auxiliary sensor to generate a detection output. The decision making circuit is arranged for deciding a response of the voice control device according to the recognized speech command and the detection output. The same speech command is able to trigger difference responses according to the detection output (e.g., detected motion). Besides, an adaptive training process may be employed to improve the accuracy of the sensor data processor. Hence, the voice control device may have improved performance of the voice control feature due to a reduce occurrence probability of miss errors and false alarm errors.

Abstract translation: 语音控制装置具有语音指令识别器，传感器数据处理器和决策电路。 语音指令识别器被配置为执行语音命令识别以输出识别的语音命令。 传感器数据处理器被布置用于处理从至少一个辅助传感器生成的传感器数据以产生检测输出。 决定电路被配置为根据识别的语音命令和检测输出来决定语音控制装置的响应。 相同的语音命令能够根据检测输出（例如，检测到的运动）触发差异响应。 此外，可以采用自适应训练过程来提高传感器数据处理器的精度。 因此，语音控制装置可能由于错误错误和错误警报错误的发生概率的降低而具有改进的语音控制特征的性能。