WO2020238703A1 - 获取语音信号的方法及装置 - Google Patents
获取语音信号的方法及装置 Download PDFInfo
- Publication number
- WO2020238703A1 WO2020238703A1 PCT/CN2020/091114 CN2020091114W WO2020238703A1 WO 2020238703 A1 WO2020238703 A1 WO 2020238703A1 CN 2020091114 W CN2020091114 W CN 2020091114W WO 2020238703 A1 WO2020238703 A1 WO 2020238703A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- voice signal
- average amplitude
- voice
- amplitude
- signal
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 20
- 230000005236 sound signal Effects 0.000 claims abstract description 54
- 238000004458 analytical method Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 abstract 1
- 238000004364 calculation method Methods 0.000 description 5
- 230000003321 amplification Effects 0.000 description 2
- 238000003199 nucleic acid amplification method Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0208—Noise filtering
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0208—Noise filtering
- G10L21/0216—Noise filtering characterised by the method used for estimating noise
Definitions
- the present invention relates to the field of audio processing, and in particular to a method and device for acquiring voice signals.
- the current voice remote control device can only recognize one type of voice signal.
- the voice remote control device cannot accurately recognize the nearest voice signal, and the performance of recognizing the voice signal is low. The user experience is poor.
- a method and device for acquiring a voice signal which aims to improve the accuracy of voice signal recognition are provided.
- the present invention provides a method for acquiring voice signals, including the following steps:
- the step of parsing the audio signal to obtain the average amplitude of each voice signal in the audio signal includes:
- the average amplitude of the sound wave amplitude of each voice signal is calculated separately.
- the step of obtaining the voice signal corresponding to the maximum average amplitude includes:
- it also includes:
- the step of performing speech recognition on the speech signal with the largest average amplitude includes:
- the voice signal is converted into text information, and semantic recognition is performed based on the text information.
- the present invention also provides a device for acquiring voice signals, including:
- Collection unit used to collect audio signals
- a parsing unit for parsing the audio signal to obtain the average amplitude of each voice signal in the audio signal
- the acquiring unit is used to acquire the voice signal corresponding to the maximum average amplitude.
- the analysis unit is configured to calculate the sound wave amplitude of each voice signal by calculating the audio signal, and calculate the average amplitude of the sound wave amplitude of each voice signal respectively.
- the acquisition unit is used to compare the average amplitude of the sound wave amplitude of each voice signal, obtain the maximum average amplitude, and filter the voice signal less than the maximum average amplitude to obtain the voice signal corresponding to the maximum average amplitude.
- it also includes:
- the recognition unit is used to perform speech recognition on the speech signal with the largest average amplitude.
- the recognition unit is configured to convert the voice signal into text information, and perform semantic recognition based on the text information.
- the average amplitude of each voice signal in the audio signal is obtained by analyzing the collected audio signal; according to the average amplitude, the noise signal in the audio signal can be filtered out to obtain the nearest voice signal (ie : The speech signal corresponding to the maximum average amplitude), thereby improving the accuracy of recognizing speech signals in the speech recognition stage.
- Fig. 1 is a method flowchart of an embodiment of the method for acquiring a voice signal according to the present invention
- FIG. 2 is a method flowchart of another embodiment of the method for acquiring a voice signal according to the present invention.
- Fig. 3 is a block diagram of an embodiment of the apparatus for acquiring a voice signal according to the present invention.
- a method for acquiring a voice signal includes the following steps:
- the collection number of array microphones can be used to collect audio signals in different spatial directions.
- step S2 of parsing the audio signal to obtain the average amplitude of each voice signal in the audio signal includes:
- an amplifier can be used to amplify the audio signal before performing step S21 to calculate the audio signal to obtain the sound wave amplitude of each voice signal (the amplification factor can be based on actual needs) Make adjustments) to facilitate subsequent calculations on the audio signal.
- the audio signal can be converted into a digital signal
- the power calculation module is used to calculate the power value of each digital sampling sequence
- the average power value is obtained by statistics. It is also possible to convert the audio signal into a digital signal, use the Fourier algorithm to obtain the sound wave amplitude of each voice signal, and obtain the average amplitude of each voice signal by statistics.
- step S3 of obtaining the voice signal corresponding to the maximum average amplitude includes:
- the energy (power or amplitude) of the sound wave is inversely proportional to the square of the distance, the larger the average value of the power or amplitude, the smaller the voice input distance.
- the average amplitude of all voice signals to obtain the maximum average amplitude, take the group of voice signals with the largest average amplitude (that is, the smaller the voice distance) as the only input voice signal, and shield other voice signals that are less than the maximum average amplitude, so as to achieve audio shielding The purpose of unnecessary noise interference in the signal.
- the average amplitude of each voice signal in the audio signal is obtained by analyzing the collected audio signal; according to the average amplitude, the noise signal in the audio signal can be filtered out to obtain the nearest voice signal ( That is: the speech signal corresponding to the maximum average amplitude), thereby improving the accuracy of recognizing the speech signal in the speech recognition stage.
- the method of acquiring a voice signal is mainly applied to a voice remote control device.
- the voice remote control device can accurately recognize short-distance voice signals and improve the voice recognition capability.
- the method for acquiring a voice signal may further include:
- step S4 of performing voice recognition on the voice signal with the maximum average amplitude may include:
- the voice signal is converted into text information, and semantic recognition is performed based on the text information.
- a hidden Markov model can be used for semantic recognition.
- an apparatus for acquiring a voice signal may include: an acquisition unit 1, an analysis unit 2, and an acquisition unit 3, wherein:
- Collecting unit 1 for collecting audio signals
- an array microphone collection number can be used to collect audio signals in different spatial directions.
- the parsing unit 2 is used to analyze the audio signal to obtain the average amplitude of each voice signal in the audio signal;
- the analysis unit 2 is configured to calculate the audio signal to obtain the sound wave amplitude of each voice signal, and calculate the average amplitude of the sound wave amplitude of each voice signal respectively.
- an amplifier can be used to amplify the audio signal in the analysis unit 2 (the amplification factor can be adjusted according to actual needs) to facilitate subsequent calculation of the audio signal.
- the analysis unit 2 may include an amplifier, an analog-to-digital converter, and a power calculation module.
- the audio signal is amplified by the amplifier, the audio signal is converted into a digital signal by the analog-to-digital converter, and the power calculation module is used to calculate the power value of each digital sampling sequence. , And statistically obtain the average power value. It is also possible to convert the audio signal into a digital signal, use the Fourier algorithm to obtain the sound wave amplitude of each voice signal, and obtain the average amplitude of each voice signal by statistics.
- the acquiring unit 3 is used for acquiring the voice signal corresponding to the maximum average amplitude.
- the acquisition unit 3 is used to compare the average amplitude of the sound wave amplitude of each voice signal, obtain the maximum average amplitude, and filter the voice signals less than the maximum average amplitude to obtain the voice signal corresponding to the maximum average amplitude.
- the energy (power or amplitude) of a sound wave is inversely proportional to the square of the distance, the larger the average value of the power or amplitude, the smaller the voice input distance.
- the average amplitude of all voice signals to obtain the maximum average amplitude, take the group of voice signals with the largest average amplitude (that is, the smaller the voice distance) as the only input voice signal, and shield other voice signals less than the maximum average amplitude, so as to achieve audio shielding The purpose of unnecessary noise interference in the signal.
- the average amplitude of each voice signal in the audio signal is obtained by analyzing the collected audio signal; according to the average amplitude, the noise signal in the audio signal can be filtered out to obtain the nearest voice signal ( That is: the speech signal corresponding to the maximum average amplitude), thereby improving the accuracy of recognizing the speech signal in the speech recognition stage.
- the device for acquiring a voice signal may further include:
- the recognition unit is used to perform speech recognition on the speech signal with the largest average amplitude.
- the recognition unit is configured to convert the voice signal into text information, and perform semantic recognition based on the text information.
- a hidden Markov model can be used for semantic recognition.
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Signal Processing (AREA)
- Circuit For Audible Band Transducer (AREA)
Abstract
获取语音信号的方法及装置,获取语音信号的方法通过对采集到的音频信号进行解析,获取音频信号中每一语音信号的平均幅度;根据平均幅度可过滤掉音频信号中的噪声信号,以获取距离最近的语音信号,从而提升在语音识别阶段对识别语音信号的准确性。
Description
本发明涉及音频处理领域,尤其涉及获取语音信号的方法及装置。
目前的语音遥控装置只能识别一种语音信号,当外界的噪音较大(如:有多个语音信号)时,语音遥控装置无法准确的识别距离最近的语音信号,识别语音信号的性能低,用户体验效果差。
发明内容
针对上述问题,现提供一种旨在可提高语音信号识别准确性的获取语音信号的方法及装置。
本发明提出了一种获取语音信号的方法,包括下述步骤:
采集音频信号;
解析所述音频信号,获取所述音频信号中每一语音信号的平均幅度;
获取最大平均幅度对应的语音信号。
优选的,解析所述音频信号,获取所述音频信号中每一语音信号的平均幅度的步骤,包括:
对所述音频信号进行计算获取每一语音信号的声波幅度;
分别计算每一语音信号的声波幅度的平均幅度。
优选的,获取最大平均幅度对应的语音信号的步骤,包括:
比较每一语音信号的声波幅度的平均幅度,获取最大平均幅度;
过滤小于最大平均幅度的语音信号,以获取最大平均幅度对应的语音信号。
优选的,还包括:
对最大平均幅度的语音信号进行语音识别。
优选的,对最大平均幅度的语音信号进行语音识别的步骤,包括:
将所述语音信号转换为文字信息,基于所述文字信息进行语义识别。
本发明还提供了一种获取语音信号的装置,包括:
采集单元,用于采集音频信号;
解析单元,用于解析所述音频信号,获取所述音频信号中每一语音信号的平均幅度;
获取单元,用于获取最大平均幅度对应的语音信号。
优选的,所述解析单元用于对所述音频信号进行计算获取每一语音信号的声波幅度,分别计算每一语音信号的声波幅度的平均幅度。
优选的,所述获取单元用于比较每一语音信号的声波幅度的平均幅度,获取最大平均幅度,过滤小于最大平均幅度的语音信号,以获取最大平均幅度对应的语音信号。
优选的,还包括:
识别单元,用于对最大平均幅度的语音信号进行语音识别。
优选的,所述识别单元用于将所述语音信号转换为文字信息,基于所述文字信息进行语义识别。
上述技术方案的有益效果:
本技术方案中,通过对采集到的音频信号进行解析,获取音频信号中每一语音信号的平均幅度;根据该平均幅度可过滤掉音频信号中的噪声信号,以获取距离最近的语音信号(即:最大平均幅度对应的语音信号),从而提升在语音识别阶段对识别语音信号的准确性。
图1为本发明所述的获取语音信号的方法的一种实施例的方法流程图;
图2为本发明所述的获取语音信号的方法的另一种实施例的方法流程图;
图3为本发明所述的获取语音信号的装置的一种实施例的模块图。
下面将结合本发明实施例中的附图,对本发明实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例仅仅是本发明一部分实施例,而不是全部的实施例。基于本发明中的实施例,本领域普通技术人员在没有作出创造性劳动的前提下所获得的所有其他实施例,都属于本发明保护的范围。
需要说明的是,在不冲突的情况下,本发明中的实施例及实施例中的特征可以相互组合。
下面结合附图和具体实施例对本发明作进一步说明,但不作为本发明的限定。
如图1所示,一种获取语音信号的方法,包括下述步骤:
S1.采集音频信号;
作为距离而非限定,可采用阵列麦克风采集号采集不同空间方向的音频信。
S2.解析所述音频信号,获取所述音频信号中每一语音信号的平均幅度;
进一步地,所述步骤S2解析所述音频信号,获取所述音频信号中每一语音信号的平均幅度的步骤,包括:
S21.对所述音频信号进行计算获取每一语音信号的声波幅度;
由于人声的声波能量(或者幅度)较小,因此在执行步骤S21对所述音频 信号进行计算获取每一语音信号的声波幅度之前,可采用放大器对音频信号进行放大(放大倍数可根据实际需要进行调整),以便于后续对音频信号进行计算。
S22.分别计算每一语音信号的声波幅度的平均幅度。
在实际应用中,可将音频信号转换为数字信号,采用功率计算模块计算每一数字采样序列的功率值,并统计获取平均功率值。还可以将音频信号转换为数字信号,采用傅里叶算法获取每一语音信号的声波幅度,并统计获取每一语音信号的平均幅度。
S3.获取最大平均幅度对应的语音信号。
进一步地,所述步骤S3获取最大平均幅度对应的语音信号的步骤,包括:
比较每一语音信号的声波幅度的平均幅度,获取最大平均幅度;
过滤小于最大平均幅度的语音信号,以获取最大平均幅度对应的语音信号。
由于,声波的能量(功率或幅度)与距离的二次方成反比,因此,功率或幅度的平均值越大,说明语音输入距离越小。对比所有语音信号的平均幅度,获得最大平均幅度,把最大平均幅度(即语音距离越小)的一组语音信号作为唯一输入的语音信号,屏蔽其他小于最大平均幅度的语音信号,从而实现屏蔽音频信号中不必要的噪声干扰的目的。
在本实施例中,通过对采集到的音频信号进行解析,获取音频信号中每一语音信号的平均幅度;根据该平均幅度可过滤掉音频信号中的噪声信号,以获取距离最近的语音信号(即:最大平均幅度对应的语音信号),从而提升在语音识别阶段对识别语音信号的准确性。
需要说明的是,获取语音信号的方法主要应用于语音遥控装置中,通过该获取语音信号的方法使语音遥控装置可以准确的识别近距离的语音信号,提升语音识别能力。
参考图2所示,在优选的实施例中,获取语音信号的方法还可包括:
S4.对最大平均幅度的语音信号进行语音识别。
进一步地,步骤S4对最大平均幅度的语音信号进行语音识别的步骤可包括:
将所述语音信号转换为文字信息,基于所述文字信息进行语义识别。
作为举例而非限定,可采用隐性马尔可夫模型进行语义识别。
如图3所示,一种获取语音信号的装置,可包括:采集单元1、解析单元2和获取单元3,其中:
采集单元1,用于采集音频信号;
作为距离而非限定,可采用阵列麦克风采集号采集不同空间方向的音频信。
解析单元2,用于解析所述音频信号,获取所述音频信号中每一语音信号的平均幅度;
进一步地,所述解析单元2用于对所述音频信号进行计算获取每一语音信号的声波幅度,分别计算每一语音信号的声波幅度的平均幅度。
由于人声的声波能量(或者幅度)较小,因此在解析单元2可采用放大器对音频信号进行放大(放大倍数可根据实际需要进行调整),以便于后续对音频信号进行计算。
解析单元2可包括放大器、模数转换器和功率计算模块,通过放大器将音频信号进行放大,通过模数转换器将音频信号转换为数字信号,采用功率计算模块计算每一数字采样序列的功率值,并统计获取平均功率值。还可以将音频信号转换为数字信号,采用傅里叶算法获取每一语音信号的声波幅度,并统计获取每一语音信号的平均幅度。
获取单元3,用于获取最大平均幅度对应的语音信号。
进一步地,所述获取单元3用于比较每一语音信号的声波幅度的平均幅度,获取最大平均幅度,过滤小于最大平均幅度的语音信号,以获取最大平均幅度对应的语音信号。
由于,声波的能量(功率或幅度)与距离的二次方成反比,因此,功率或幅度的平均值越大,说明语音输入距离越小。对比所有语音信号的平均幅度,获得最大平均幅度,把最大平均幅度(即语音距离越小)的一组语音信号作为唯一输入的语音信号,屏蔽其他小于最大平均幅度的语音信号,从而实现屏蔽音频信号中不必要的噪声干扰的目的。
在本实施例中,通过对采集到的音频信号进行解析,获取音频信号中每一语音信号的平均幅度;根据该平均幅度可过滤掉音频信号中的噪声信号,以获取距离最近的语音信号(即:最大平均幅度对应的语音信号),从而提升在语音识别阶段对识别语音信号的准确性。
在优选的实施例中,获取语音信号的装置还可包括:
识别单元,用于对最大平均幅度的语音信号进行语音识别。
进一步地,所述识别单元用于将所述语音信号转换为文字信息,基于所述文字信息进行语义识别。
作为举例而非限定,可采用隐性马尔可夫模型进行语义识别。
以上所述仅为本发明较佳的实施例,并非因此限制本发明的实施方式及保护范围,对于本领域技术人员而言,应当能够意识到凡运用本发明说明书及图示内容所作出的等同替换和显而易见的变化所得到的方案,均应当包含在本发明的保护范围内。
Claims (10)
- 一种获取语音信号的方法,其特征在于,包括下述步骤:采集音频信号;解析所述音频信号,获取所述音频信号中每一语音信号的平均幅度;获取最大平均幅度对应的语音信号。
- 根据权利要求1所述的获取语音信号的方法,其特征在于,解析所述音频信号,获取所述音频信号中每一语音信号的平均幅度的步骤,包括:对所述音频信号进行计算获取每一语音信号的声波幅度;分别计算每一语音信号的声波幅度的平均幅度。
- 根据权利要求1所述的获取语音信号的方法,其特征在于,获取最大平均幅度对应的语音信号的步骤,包括:比较每一语音信号的声波幅度的平均幅度,获取最大平均幅度;过滤小于最大平均幅度的语音信号,以获取最大平均幅度对应的语音信号。
- 根据权利要求1所述的获取语音信号的方法,其特征在于,还包括:对最大平均幅度的语音信号进行语音识别。
- 根据权利要求1所述的获取语音信号的方法,其特征在于,对最大平均幅度的语音信号进行语音识别的步骤,包括:将所述语音信号转换为文字信息,基于所述文字信息进行语义识别。
- 一种获取语音信号的装置,其特征在于,包括:采集单元,用于采集音频信号;解析单元,用于解析所述音频信号,获取所述音频信号中每一语音信号的平均幅度;获取单元,用于获取最大平均幅度对应的语音信号。
- 根据权利要求6所述的获取语音信号的装置,其特征在于,所述解析单元用于对所述音频信号进行计算获取每一语音信号的声波幅度,分别计算每一语音信号的声波幅度的平均幅度。
- 根据权利要求6所述的获取语音信号的装置,其特征在于,所述获取单元用于比较每一语音信号的声波幅度的平均幅度,获取最大平均幅度,过滤小于最大平均幅度的语音信号,以获取最大平均幅度对应的语音信号。
- 根据权利要求6所述的获取语音信号的装置,其特征在于,还包括:识别单元,用于对最大平均幅度的语音信号进行语音识别。
- 根据权利要求6所述的获取语音信号的装置,其特征在于,所述识别单元用于将所述语音信号转换为文字信息,基于所述文字信息进行语义识别。
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910453528.7A CN110189762A (zh) | 2019-05-28 | 2019-05-28 | 获取语音信号的方法及装置 |
CN201910453528.7 | 2019-05-28 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2020238703A1 true WO2020238703A1 (zh) | 2020-12-03 |
Family
ID=67718256
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2020/091114 WO2020238703A1 (zh) | 2019-05-28 | 2020-05-19 | 获取语音信号的方法及装置 |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN110189762A (zh) |
WO (1) | WO2020238703A1 (zh) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110189762A (zh) * | 2019-05-28 | 2019-08-30 | 晶晨半导体(上海)股份有限公司 | 获取语音信号的方法及装置 |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2016201595A (ja) * | 2015-04-07 | 2016-12-01 | 井上 時子 | 音源方向追従システム |
CN106255000A (zh) * | 2016-07-29 | 2016-12-21 | 维沃移动通信有限公司 | 一种音频信号采集方法及移动终端 |
US20170162205A1 (en) * | 2015-12-07 | 2017-06-08 | Semiconductor Components Industries, Llc | Method and apparatus for a low power voice trigger device |
CN106952654A (zh) * | 2017-04-24 | 2017-07-14 | 北京奇虎科技有限公司 | 机器人降噪方法、装置及机器人 |
CN107274907A (zh) * | 2017-07-03 | 2017-10-20 | 北京小鱼在家科技有限公司 | 双麦克风设备上实现指向性拾音的方法和装置 |
CN107742523A (zh) * | 2017-11-16 | 2018-02-27 | 广东欧珀移动通信有限公司 | 语音信号处理方法、装置以及移动终端 |
CN109448718A (zh) * | 2018-12-11 | 2019-03-08 | 广州小鹏汽车科技有限公司 | 一种基于多麦克风阵列的语音识别方法及系统 |
CN110189762A (zh) * | 2019-05-28 | 2019-08-30 | 晶晨半导体(上海)股份有限公司 | 获取语音信号的方法及装置 |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9037461B2 (en) * | 2012-01-19 | 2015-05-19 | SpeakWrite, LLC | Methods and systems for dictation and transcription |
CN104135619A (zh) * | 2014-08-12 | 2014-11-05 | 广东欧珀移动通信有限公司 | 一种摄像头控制方法及装置 |
CN105744439B (zh) * | 2014-12-12 | 2019-07-26 | 比亚迪股份有限公司 | 麦克风装置和具有其的移动终端 |
CN106328131A (zh) * | 2016-08-13 | 2017-01-11 | 厦门傅里叶电子有限公司 | 一种可侦测呼叫者位置的交互系统及其启动方法 |
CN107919119A (zh) * | 2017-11-16 | 2018-04-17 | 百度在线网络技术(北京)有限公司 | 多设备交互协同的方法、装置、设备及计算机可读介质 |
-
2019
- 2019-05-28 CN CN201910453528.7A patent/CN110189762A/zh active Pending
-
2020
- 2020-05-19 WO PCT/CN2020/091114 patent/WO2020238703A1/zh active Application Filing
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2016201595A (ja) * | 2015-04-07 | 2016-12-01 | 井上 時子 | 音源方向追従システム |
US20170162205A1 (en) * | 2015-12-07 | 2017-06-08 | Semiconductor Components Industries, Llc | Method and apparatus for a low power voice trigger device |
CN106255000A (zh) * | 2016-07-29 | 2016-12-21 | 维沃移动通信有限公司 | 一种音频信号采集方法及移动终端 |
CN106952654A (zh) * | 2017-04-24 | 2017-07-14 | 北京奇虎科技有限公司 | 机器人降噪方法、装置及机器人 |
CN107274907A (zh) * | 2017-07-03 | 2017-10-20 | 北京小鱼在家科技有限公司 | 双麦克风设备上实现指向性拾音的方法和装置 |
CN107742523A (zh) * | 2017-11-16 | 2018-02-27 | 广东欧珀移动通信有限公司 | 语音信号处理方法、装置以及移动终端 |
CN109448718A (zh) * | 2018-12-11 | 2019-03-08 | 广州小鹏汽车科技有限公司 | 一种基于多麦克风阵列的语音识别方法及系统 |
CN110189762A (zh) * | 2019-05-28 | 2019-08-30 | 晶晨半导体(上海)股份有限公司 | 获取语音信号的方法及装置 |
Also Published As
Publication number | Publication date |
---|---|
CN110189762A (zh) | 2019-08-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2021004345A1 (zh) | 一种基于云架构的心音采集与分析系统及方法 | |
WO2018137704A1 (zh) | 一种基于麦克风阵列的拾音方法及系统 | |
CN204390737U (zh) | 一种家庭语音处理系统 | |
CN201639751U (zh) | 基于多麦克风阵列的定向定距语音采集系统 | |
KR101902717B1 (ko) | 음성 웨이크 업 방법 및 장치 | |
JP2019191558A (ja) | 音声を増幅する方法及び装置 | |
CN111429939B (zh) | 一种双声源的声音信号分离方法和拾音器 | |
CN204482023U (zh) | 一种啸叫抑制系统 | |
CN110875056B (zh) | 语音转录设备、系统、方法、及电子设备 | |
CN113490115A (zh) | 一种基于声纹识别技术的声反馈抑制方法及系统 | |
WO2020238703A1 (zh) | 获取语音信号的方法及装置 | |
CN111526469A (zh) | 一种基于神经网络的扩声系统啸叫点检测方法 | |
CN112349291A (zh) | 基于ai降噪模型的扩声系统及方法 | |
CN112908353A (zh) | 用于助听器的边缘计算与云计算相结合的语音增强方法 | |
CN111182416B (zh) | 处理方法、装置及电子设备 | |
CN204181641U (zh) | 肺音图机 | |
CN203252651U (zh) | 一种听觉功能检测处理系统 | |
CN111862991A (zh) | 一种婴儿哭声的识别方法及系统 | |
TWI396186B (zh) | 基於盲訊號分離語音增強技術之遠距離雜訊語音辨識 | |
CN102209135A (zh) | 用于对移动终端降风噪的装置及方法 | |
US11490198B1 (en) | Single-microphone wind detection for audio device | |
CN111009259A (zh) | 一种音频处理方法和装置 | |
CN112201226B (zh) | 一种发声方式判别方法及系统 | |
TW200917231A (en) | Enhancement system for wide space voice signal | |
CN104510492A (zh) | 不可听信号的听诊方法及装置 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 20814336 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 20814336 Country of ref document: EP Kind code of ref document: A1 |