WO2016184096A1 - 一种音频解锁方法及装置 - Google Patents
一种音频解锁方法及装置 Download PDFInfo
- Publication number
- WO2016184096A1 WO2016184096A1 PCT/CN2015/098023 CN2015098023W WO2016184096A1 WO 2016184096 A1 WO2016184096 A1 WO 2016184096A1 CN 2015098023 W CN2015098023 W CN 2015098023W WO 2016184096 A1 WO2016184096 A1 WO 2016184096A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- audio signal
- audio
- unlocking
- module
- verification
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 230000005236 sound signal Effects 0.000 claims abstract description 292
- 230000007613 environmental effect Effects 0.000 claims abstract 6
- 238000012795 verification Methods 0.000 claims description 68
- 238000001914 filtration Methods 0.000 claims description 9
- 238000000926 separation method Methods 0.000 claims description 9
- 230000033764 rhythmic process Effects 0.000 claims description 8
- 239000000284 extract Substances 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 4
- 230000001755 vocal effect Effects 0.000 description 4
- 241001465754 Metazoa Species 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 230000003111 delayed effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
- H04W12/02—Protecting privacy or anonymity, e.g. protecting personally identifiable information [PII]
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
- H04L9/32—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/725—Cordless telephones
Definitions
- the present invention relates to the field of electronic technologies, and in particular, to an audio unlocking method and apparatus.
- the embodiment of the invention provides an audio unlocking method and device, which solves the problem that the existing audio unlocking scheme is not high in security.
- the embodiment of the present invention adopts the following technical solutions:
- An audio unlocking method includes: collecting an audio signal; separating a first audio signal and a second audio signal from the audio signal; when the first audio signal matches a preset verification audio signal, and second The audio signal is matched to the preset unlocked audio signal and unlocked.
- the first audio signal and the second audio signal are different frequency bands
- separating the first audio signal and the second audio signal from the audio signal comprises: pairing the audio signal according to a preset frequency band range. Performing a filtering process to extract the first audio signal or the second audio signal in the audio signal, and the other portion of the audio signal is used as the second audio signal or the first audio signal.
- the separated first audio signal matches at least one of the following characteristic information of the preset verification audio signal, the two are considered to match: play start time point, frequency, bearer content , melody, rhythm, tone.
- At least one of the preset verification audio signals is randomly generated information.
- the preset verification audio signal is: a verification audio signal that is played by itself or authorized by an external device during the process of acquiring the audio signal.
- An audio unlocking device includes: an acquisition module configured to collect an audio signal; and a separation module configured to separate the first audio signal and the second audio signal from the audio signal collected by the acquisition module; and the unlock processing module is configured to be The first audio signal separated by the separation module matches the preset verification audio signal, and the second audio signal is matched with the preset unlocked audio signal, and then unlocked.
- the separation module includes: a filtering module configured to perform filtering processing on the audio signal according to a preset frequency band range, and extract the first audio signal or the second audio signal in the audio signal And the other part of the audio signal is the second audio signal or the first audio signal; the first audio signal and the second audio signal are different frequency bands.
- the unlock processing module includes a first matching module configured to determine that if the separated first audio signal matches at least one of the following characteristic information of the preset verification audio signal Match: play start time, frequency, bearer content, melody, rhythm, tone.
- the audio unlocking device further includes:
- a playback module configured to play the verification audio signal in the process of collecting the audio signal by the acquisition module, as the preset verification audio signal
- control module is configured to authorize the external device to play the verification audio signal as the preset verification audio signal during the process of collecting the audio signal by the collection module.
- the audio unlocking apparatus further includes: a generating module configured to generate a random information; an encoding module configured to encode the random information according to a preset encoding rule; and a conversion module configured to be encoded The content is converted into the verification audio signal according to a preset frequency, and the verification audio signal is transmitted to the sound reproduction module.
- the first audio signal and the second audio signal are separated from the collected audio signal, the first audio signal is matched with the preset verification audio signal, and the second audio signal is unlocked with a preset.
- the unlocking is performed.
- the present invention improves the security of the audio unlocking by matching specific audio signals when the audio is unlocked.
- the preset verification audio signal may be a verification audio signal played by the device itself or an authorized external device during the process of acquiring the audio signal, so that the collected audio signal contains the verification audio signal, when the ulterior is useful
- unlocking by means of recording sound playback the first audio signal separated from the collected audio signal and the process of acquiring the audio signal
- the played check audio signal does not match, and the unlock fails, which greatly improves the security.
- FIG. 1 is a flowchart of an audio unlocking method according to an embodiment of the present invention
- FIG. 2 is a schematic diagram of an audio unlocking apparatus according to an embodiment of the present invention.
- the present invention provides an idea to improve the security of audio unlocking by matching specific audio signals when performing audio unlocking.
- a flowchart of an audio unlocking method according to an embodiment of the present invention mainly includes the following steps:
- the device itself or the authorized external device plays the verification audio signal, and the played verification audio signal is used as the preset verification audio signal.
- the device itself plays the check audio signal or authorizes the external device to play the check audio signal, it is necessary to verify the audio signal before playing the check audio signal.
- the played check audio signals are different, so that the check audio signals played during each acquisition process are unique.
- the check audio signal has the following characteristic information: play start time point, frequency, bearer content, melody, rhythm, timbre, and the like.
- the difference in any one of the feature information indicates that the corresponding check audio signal is different.
- at least one of the above feature information of the played verification audio signal is randomly generated during each acquisition process to ensure that the verification audio signal played during each acquisition process is unique.
- the frequency of the calibrated audio signal is stronger, and the frequency band that is difficult to reach by the vocal is preferred.
- the frequency of the vocal is usually between 1000hz and 2000hz.
- the frequency of the audio signal can be below 1000hz, or above 2000hz.
- 10khz and 15khz can be used to obtain a clear signal and distinguish it from the human voice.
- the frequency of the audio signal is verified to use a frequency band that the sound cannot reach.
- the unique check audio signal can be generated by the following steps: Generating a random information, encoding the random information according to a preset encoding rule, converting the encoded content into a verification audio signal according to a fixed frequency, and then starting at a fixed time (for example, with an audio signal collection) The check audio signal is played when the start time point is the same, or the fixed time period is delayed.
- the encoding rule includes, but is not limited to, a Moss cryptographic rule, for example, generating a random information: GG, converting the GG into "--.--.” according to the Moss cryptographic rule, and generating the verification audio by using 10khz frequency modulation. signal.
- a Moss cryptographic rule for example, generating a random information: GG, converting the GG into "--.--.” according to the Moss cryptographic rule, and generating the verification audio by using 10khz frequency modulation. signal.
- the unique check audio signal can be generated by the following steps. Generating a random information; encoding the random information according to a preset encoding rule; randomly determining a frequency in a preset frequency range, converting the encoded content into a verification audio signal according to the frequency, and then fixing the frequency
- the check audio signal is played at the time start point.
- the unique check audio signal may be generated by generating the following: Random information; encoding the random information according to a preset encoding rule; randomly determining a frequency in a preset frequency range, converting the encoded content into a verification audio signal according to the frequency, and then collecting the audio signal The check audio signal starts playing at a random point in time.
- the first audio signal is used for matching with a preset verification audio signal
- the preset verification audio signal includes, but is not limited to, a verification audio signal that is played by itself or authorized by an external device during the process of acquiring the audio signal. Only the check audio signal that is not played is stored; the second audio signal is used to match the preset unlocked audio signal.
- the second audio signal includes, but is not limited to, human voice, animal sound, water flow sound, and the like.
- the frequency of the first audio signal is different from the frequency of the second audio signal.
- the signal belonging to the frequency band of the audio signal may be extracted as the first audio signal according to the frequency range, and other frequency bands are used. As the second audio signal.
- the matching of the first audio signal with the preset verification audio signal means that at least one of the feature information matches.
- the first audio signal matches the check audio signal when the playback start time point, the frequency, and the bearer content match. If the person with ulterior motive uses the method of recording sound playback to unlock, since there is also the playback of the verification audio signal during recording, the recorded sound contains a verification audio signal played at the recording time point, when the recorded sound is used.
- the collected audio signal contains the check audio signal played at the recording time point, and the check audio signal does not match the check audio signal played during the process of collecting the audio signal, so the unlocking fails, thereby making the security Huge improvements.
- Matching the second audio signal with the preset unlocked audio signal means that at least one of frequency, bearer content, melody, rhythm, and timbre match.
- the bearer content may be a keyword or keyword in a person's words.
- the unlocking is prohibited, and the user may be prompted to unlock.
- the verification audio signal may include one or more audio signals.
- the characteristic information of the audio signals may be different, such as a multi-frequency, multi-sound source manner, to further improve security.
- FIG. 2 is a schematic diagram of an audio unlocking apparatus according to an embodiment of the present invention, where the audio unlocking apparatus includes:
- the acquisition module 21 is configured to collect an audio signal; the acquisition module may be, for example, a microphone.
- the separation module 22 is configured to separate the first audio signal and the second audio signal from the audio signal collected by the acquisition module 21;
- the unlock processing module 23 is configured to be unlocked when the first audio signal separated by the separation module 22 matches the preset verification audio signal, and the second audio signal matches the preset unlocked audio signal.
- the separation module 22 includes:
- the filtering module 221 is configured to perform filtering processing on the audio signal according to a preset frequency band range, and extract the first audio signal or the second audio signal in the audio signal, where other parts of the audio signal serve as The second audio signal or the first audio signal; the first audio signal and the second audio signal are different frequency bands.
- the unlock processing module 23 includes:
- the first matching module 231 is configured to: if the separated first audio signal and the preset verification audio signal If at least one of the following feature information matches, the two are considered to match:
- Play start time point frequency
- bearer content melody
- rhythm tone
- the second matching module 232 is configured to match the two audio signals if they match at least one of the following characteristic information of the preset unlocked audio signal:
- the unlocking module 233 is configured to match the matching results of the first matching module 231 and the second matching module 232, and then unlock.
- the audio unlocking device further includes a sound emitting module 24 configured to play the verification audio signal as the preset verification audio signal during the process of acquiring the audio signal by the acquisition module 21.
- the playback module may be, for example, a speaker; and/or a control module (not shown), configured to allow the external device to play the verification audio signal during the process of acquiring the audio signal by the acquisition module 21 as the preset verification. audio signal.
- the control module can notify the external device to start playing the check audio signal by sending a wireless signal command.
- the audio unlocking device further includes a verification audio signal generating module, including:
- the generating module 25 is configured to generate a random information
- the encoding module 26 is configured to encode the random information according to a preset encoding rule
- the conversion module 27 is configured to convert the encoded content into the verification audio signal according to a preset frequency, and transmit the verification audio signal to the sound reproduction module 24.
- the above embodiment provides an audio unlocking device, and the corresponding function can be realized by using the hardware of the mobile phone itself.
- the following uses a mobile phone as an example to further explain the embodiment of the present invention:
- the voice unlocking module on the mobile phone is started, and the main control module starts the entire voice unlocking process; the main control module calls the verification audio signal generating module, and the verification audio signal generating module generates random information, such as “GG”, and then according to the preset encoding rule.
- the random information is encoded, for example, by referring to the Morse code rule, converting "GG" into "--.--.”; and then selecting a special frequency band, for example, 10khz, generating a verification audio signal, and saving;
- the main control module calls the microphone to start recording the unlocking sound of the user, and simultaneously extracts the stored verification audio signal and sends it to the speaker for playing; the speaker plays the verification audio signal, and the microphone picks up the audio signal containing the user voice and the verification audio signal;
- the main control module filters the audio signal picked up by the microphone, extracts the first audio signal and the second audio signal, respectively, and respectively passes the first matching module and the second matching module; the first matching module plays the first audio signal and the speaker The verification audio signal is matched, the result is returned to the unlocking module, and the second matching module is to be the second audio signal. The number is matched with the preset unlocked audio signal, and the result is returned to the unlocking module.
- the unlocking module unlocks, if one of the two does not match, The speech recognition process is terminated by the main control module.
- the present invention enhances the security of audio unlocking by matching specific audio signals when performing audio unlocking.
- the specific audio signal may be a verification audio signal that is played by itself or authorized to be played by an external device during the process of collecting the audio signal.
- the ulterior motive person uses the method of recording sound playback to unlock, it may be separated from the collected audio signal.
- the first audio signal does not match the verification audio signal played during the acquisition of the audio signal, and the unlocking fails, so that the security is greatly improved.
- the above functions can be realized by using the hardware of the mobile phone itself, and there is no need to improve on the hardware.
- the technical solution provided by the embodiment of the present invention is applied to an audio unlocking process, in which a first audio signal and a second audio signal are separated from the collected audio signal, and the first audio signal and the preset verification audio are separated. The signal is matched, and the second audio signal is matched with the preset unlocked audio signal. When the two matching results are passed, the unlocking is performed.
- the present invention enhances the audio unlocking by matching the specific audio signal when the audio is unlocked. safety.
- the preset verification audio signal may be a verification audio signal played by the device itself or an authorized external device during the process of acquiring the audio signal, so that the collected audio signal contains the verification audio signal, when the ulterior is useful
- unlocking by means of recording sound playback the first audio signal separated from the collected audio signal does not match the verification audio signal played during the acquisition of the audio signal, and the unlocking fails, thereby greatly improving the security.
Landscapes
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (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)
- Telephone Function (AREA)
Abstract
本发明公开一种音频解锁方法及装置，该方法包括：采集环境音频信号；从所述环境音频信号中分离第一音频信号和第二音频信号；如果分离出的第一音频信号与采集所述环境音频信号过程中自身播放或授权外部设备播放的校验音频信号相匹配，且第二音频信号与预设的解锁音频信号相匹配，则解锁。本发明在进行音频解锁时通过播放特定音频信号的方式来提升音频解锁的安全性，当别有用心之人采用录制声音回放的方式进行解锁时，会因为从采集的环境音频信号中分离出的第一音频信号与采集该环境音频信号过程中播放的校验音频信号不匹配，而解锁失败，使得安全性大大提升。
Description
本发明涉及电子技术领域，尤其涉及一种音频解锁方法及装置。
随着技术的不断进步和安全意识的不断提高，人们对于个人隐私的保护已经愈发看重。移动终端设备作为大量个人信息的存储设备，对其安全性的保障已被广大用户重点关注，应运而生的诸如指纹识别、眼纹识别以及声纹识别等安全技术都不断在提高以求达到更佳的效果。
利用个人声纹技术来解锁移动终端设备已基本普及，声纹因为其特殊性很难被破译并制造，同时用户只要定期修改声纹识别时使用的关键字，就可以进一步提升其安全性。然而当用户通过读关键字解锁时，由于声音本身的特性会向四周传播，可以很容易的被他人知道。别有用心之人通过高保真麦克风采取定向录音的方式，在用户朗读关键字时录取其声音，采用录制声音回放，进而解锁的方式令声纹系统的安全性大大降低。
发明内容
本发明实施例提供一种音频解锁方法及装置，解决现有音频解锁方案安全性不高的问题。
为解决上述技术问题，本发明实施例采用以下技术方案:
一种音频解锁方法，包括：采集音频信号；从所述音频信号中分离第一音频信号和第二音频信号；当所述第一音频信号与预设的校验音频信号相匹配，且第二音频信号与预设的解锁音频信号相匹配，则解锁。
在一些实施例中，所述第一音频信号、第二音频信号为不同频段，从所述音频信号中分离第一音频信号和第二音频信号包括：根据预设的频段范围对所述音频信号进行滤波处理，提取所述音频信号中的所述第一音频信号或第二音频信号，所述音频信号中的其他部分作为所述第二音频信号或第一音频信号。
在一些实施例中，如果分离出的第一音频信号与预设的校验音频信号的以下特征信息中的至少一个相匹配，则认为两者相匹配：播放起始时间点、频率、承载内容、旋律、节奏、音色。
在一些实施例中，所述预设的校验音频信号中的至少一个特征信息是随机产生的信息。
在一些实施例中，所述预设的校验音频信号为：所述采集音频信号的过程中，自身播放或授权外部设备播放的校验音频信号。
一种音频解锁装置，包括：采集模块，设置为采集音频信号；分离模块，设置为从所述采集模块采集的音频信号中分离第一音频信号和第二音频信号；解锁处理模块，设置为当所述分离模块分离出的第一音频信号与预设的校验音频信号相匹配，且第二音频信号与预设的解锁音频信号相匹配，则解锁。
在一些实施例中，所述分离模块包括：滤波模块，设置为根据预设的频段范围对所述音频信号进行滤波处理，提取所述音频信号中的所述第一音频信号或第二音频信号，所述音频信号中的其他部分作为所述第二音频信号或第一音频信号；所述第一音频信号、第二音频信号为不同频段。
在一些实施例中，所述解锁处理模块包括第一匹配模块，设置为如果分离出的第一音频信号与预设的校验音频信号的以下特征信息中的至少一个相匹配，则认为两者相匹配：播放起始时间点、频率、承载内容、旋律、节奏、音色。
在一些实施例中，上述音频解锁装置还包括：
放音模块，设置为所述采集模块采集音频信号的过程中，播放校验音频信号，作为所述预设的校验音频信号；
和/或控制模块，设置为所述采集模块采集音频信号的过程中，授权外部设备播放校验音频信号，作为所述预设的校验音频信号。
在一些实施例中，上述音频解锁装置还包括：生成模块，设置为生成一随机信息；编码模块，设置为根据预设编码规则对所述随机信息进行编码；转换模块，设置为对编码后的内容按照预设频率转换成所述校验音频信号，将所述校验音频信号传输至所述放音模块。
本发明实施例中，从采集到的音频信号中分离第一音频信号和第二音频信号，将第一音频信号与预设的校验音频信号进行匹配，将第二音频信号与预设的解锁音频信号进行匹配，两个匹配结果均通过时，才进行解锁，本发明在进行音频解锁时通过匹配特定音频信号的方式来提升音频解锁的安全性。该预设的校验音频信号可以是在采集音频信号的过程中，设备本身或授权的外部设备播放的校验音频信号，使得采集到的音频信号中含有该校验音频信号，当别有用心之人采用录制声音回放的方式进行解锁时，会因为从采集的音频信号中分离出的第一音频信号与采集该音频信号过程中
播放的校验音频信号不匹配，而解锁失败，使得安全性大大提升。
此处所说明的附图用来提供对本发明的进一步理解，构成本申请的一部分，本发明的示意性实施例及其说明用于解释本发明，并不构成对本发明的不当限定。在附图中：
图1为本发明一实施例提供的音频解锁方法的流程图；
图2为本发明一实施例提供的音频解锁装置的示意图。
本发明提供一种思路，在进行音频解锁时通过匹配特定音频信号的方式来提升音频解锁的安全性。
下面通过具体实施例对本发明的构思进一步详细说明。
如图1所示，为本发明一实施例提供的音频解锁方法的流程图，主要包括以下步骤：
S101、采集音频信号。
优选的，采集音频信号的过程中，设备本身或授权外部设备播放校验音频信号，播放的校验音频信号作为预设的校验音频信号。不论是设备本身播放校验音频信号，还是授权外部设备播放校验音频信号，在播放该校验音频信号之前，都需要先生成校验音频信号。
优选的，每一次采集过程中，所播放的校验音频信号不同，使得每一次采集过程中所播放的校验音频信号具有唯一性。
该校验音频信号具有以下特征信息：播放起始时间点、频率、承载内容、旋律、节奏、音色等。任一个特征信息的不同，都表示对应的校验音频信号不同。优选的，每一次采集过程中，所播放的校验音频信号的以上特征信息中的至少一个是随机产生的，来保证每一次采集过程中所播放的校验音频信号具有唯一性。
在一些实施例中，若采用人声来解锁，为了区分人声和校验音频信号，校验音频信号的频率采用推送能力较强，且人声不易达到的频段为佳。人声的频率通常在1000hz至2000hz，校验音频信号的频率可以在1000hz以下，或2000hz以上，例如采用10khz、15khz，可以获得较为清楚地信号，同时又与人声区分开来。当然，若
采用动物声、水流声等来代替人声来解锁，那么，优选的，校验音频信号的频率采用这些声音达不到的频段。
作为一种实施例，假设每一次播放的校验音频信号的承载内容是随机产生的，而播放起始时间点和频率是固定的，则可通过以下步骤生成具有唯一性的校验音频信号：生成一随机信息，根据预设编码规则对所述随机信息进行编码，对编码后的内容按照固定频率转换成校验音频信号，之后再在固定的时起始时间点(比如与音频信号的采集起始时间点相同，或延后固定时间段)播放该校验音频信号。其中，编码规则包括但不局限于摩斯密码规则，例如，生成一随机信息：GG，根据摩斯密码规则，将GG转换成“--.--.”，再采用10khz调频生成校验音频信号。
作为另一种实施例，假设每一次播放的校验音频信号的承载内容和频率是随机产生的，而播放起始时间点是固定的，则可通过以下步骤生成具有唯一性的校验音频信号：生成一随机信息；根据预设编码规则对所述随机信息进行编码；在预设的频率范围中随机确定一频率，对编码后的内容按照该频率转换成校验音频信号，之后再在固定的时起始时间点播放该校验音频信号。
作为另一种实施例，假设每一次播放的校验音频信号的承载内容、频率和播放起始时间点都是随机产生的，则可通过以下步骤生成具有唯一性的校验音频信号：生成一随机信息；根据预设编码规则对所述随机信息进行编码；在预设的频率范围中随机确定一频率，对编码后的内容按照该频率转换成校验音频信号，之后在音频信号的采集过程中随机的一个时间点开始播放该校验音频信号。
S102、从采集到的所述音频信号中分离第一音频信号和第二音频信号。
第一音频信号是用于与预设的校验音频信号进行匹配的，预设的校验音频信号包括但不局限于：采集所述音频信号过程中自身或授权外部设备播放的校验音频信号、仅存储不播放的校验音频信号；第二音频信号是用于与预设的解锁音频信号进行匹配的。第二音频信号包括但不局限于人声、动物声、水流声等。优选的，第一音频信号的频率与第二音频信号的频率不同。
具体分离方式包括但不局限于以下所列举的：
根据预设的频段范围对所述音频信号进行滤波处理，提取所述音频信号中的所述第一音频信号或第二音频信号，所述音频信号中的其他部分作为所述第二音频信号或第一音频信号。
在一些实施例中，假设预设的校验音频信号的频率范围为10khz至15khz，那么在步骤S102中，可以按照这个频率范围提取音频信号中属于这个频段的信号作为第一音频信号，其他频段的作为第二音频信号。
S103、当分离出的第一音频信号与预设的校验音频信号相匹配，且第二音频信号与预设的解锁音频信号相匹配，则解锁。
其中，第一音频信号与预设的校验音频信号相匹配是指，上述特征信息中的至少一个相匹配。为了提升安全性，优选的，播放起始时间点、频率和承载内容三个均匹配时，才认为第一音频信号与校验音频信号相匹配。若别有用心之人采用录制声音回放的方式进行解锁，由于录制时也存在校验音频信号的播放，因此录制的声音中含有在录制时间点播放的一校验音频信号，当采用该录制的声音进行解锁时，采集到的音频信号中含有在录制时间点播放的该校验音频信号，该校验音频信号与采集该音频信号过程中播放的校验音频信号不匹配，因此解锁失败，使得安全性大大提升。
第二音频信号与预设的解锁音频信号相匹配是指，频率、承载内容、旋律、节奏、音色中的至少一个相匹配。以人声为例，承载内容可以是人说的话中的关键字或关键词。
第一音频信号与校验音频信号不匹配，或者第二音频信号与预设的解锁音频信号不匹配时，则禁止解锁，可以提示用户解锁失败。
校验音频信号可包括一个或一个以上的音频信号，当包括一个以上的音频信号时，这些音频信号的特征信息可以不同，比如多频率、多音源的方式，进一步提升安全性。
图2为本发明一实施例提供的音频解锁装置的示意图，音频解锁装置包括：
采集模块21，设置为采集音频信号；采集模块例如可以是麦克风。
分离模块22，设置为从采集模块21采集的音频信号中分离第一音频信号和第二音频信号；
解锁处理模块23，设置为当分离模块22分离出的第一音频信号与预设的校验音频信号相匹配，且第二音频信号与预设的解锁音频信号相匹配，则解锁。
在一些实施例中，分离模块22包括：
滤波模块221，设置为根据预设的频段范围对所述音频信号进行滤波处理，提取所述音频信号中的所述第一音频信号或第二音频信号，所述音频信号中的其他部分作为所述第二音频信号或第一音频信号；所述第一音频信号、第二音频信号为不同频段。
在一些实施例中，解锁处理模块23包括：
第一匹配模块231，设置为如果分离出的第一音频信号与预设的校验音频信号的
以下特征信息中的至少一个相匹配，则认为两者相匹配：
播放起始时间点、频率、承载内容、旋律、节奏、音色。
第二匹配模块232，设置为如果第二音频信号与预设的解锁音频信号的以下特征信息中的至少一个相匹配，则认为两者相匹配：
频率、承载内容、旋律、节奏、音色。
解锁模块233，设置为第一匹配模块231和第二匹配模块232的匹配结果均为相匹配，则解锁。
在一些实施例中，上述音频解锁装置还包括放音模块24，设置为采集模块21采集音频信号的过程中，播放校验音频信号，作为上述预设的校验音频信号。放音模块例如可以是扬声器；和/或控制模块(图中未示出)，设置为采集模块21采集音频信号的过程中，授权外部设备播放校验音频信号，作为所述预设的校验音频信号。控制模块可以通过发送无线信号指令的方式通知外部设备启动播放校验音频信号。
在一些实施例中，上述音频解锁装置还包括校验音频信号生成模块，包括：
生成模块25，设置为生成一随机信息；
编码模块26，设置为根据预设编码规则对所述随机信息进行编码；
转换模块27，设置为对编码后的内容按照预设频率转换成所述校验音频信号，将所述校验音频信号传输至放音模块24。
上述实施例提供音频解锁装置，利用手机本身硬件即可实现相应功能。下面以手机为例，对本发明实施例进一步解释说明：
手机上的语音解锁模块启动，主控模块启动整个语音解锁流程；主控模块调用校验音频信号生成模块，校验音频信号生成模块生成随机信息，例如“GG”，再根据预设编码规则对随机信息进行编码，例如参照摩斯密码规则，将“GG”转换成“--.--.”；再选用特殊频段，例如10khz，生成校验音频信号，并进行保存；
主控模块调用麦克风开始收录用户的解锁声音，同时提取上述存放的校验音频信号，并交由扬声器进行播放；扬声器播放校验音频信号，麦克风拾取含有用户声音和校验音频信号的音频信号；
主控模块将麦克风拾取到的音频信号进行滤波，提取出第一音频信号和第二音频信号，分别交由第一匹配模块和第二匹配模块；第一匹配模块将第一音频信号与扬声器播放的校验音频信号进行匹配，返回结果给解锁模块，第二匹配模块将第二音频信
号与预设的解锁音频信号进行匹配，返回结果给解锁模块，解锁模块在第一匹配模块和第二匹配模块的匹配结果均为相匹配时，进行解锁，若两者有一个不匹配，则通过主控模块终止语音识别流程。
本发明在进行音频解锁时通过匹配特定音频信号的方式来提升音频解锁的安全性。特定音频信号可以是采集音频信号的过程中，自身播放或授权外部设备播放的校验音频信号，当别有用心之人采用录制声音回放的方式进行解锁时，会因为从采集的音频信号中分离出的第一音频信号与采集该音频信号过程中播放的校验音频信号不匹配，而解锁失败，使得安全性大大提升。以手机为例，利用手机本身硬件即可实现上述功能，无需在硬件上进行改进。
以上内容是结合具体的实施方式对本发明所作的进一步详细说明，不能认定本发明的具体实施只局限于这些说明。对于本发明所属技术领域的普通技术人员来说，在不脱离本发明构思的前提下，还可以做出若干简单推演或替换，都应当视为属于本发明的保护范围。
本发明实施例提供的技术方案，应用于音频解锁的过程，在该过程中从采集到的音频信号中分离第一音频信号和第二音频信号，将第一音频信号与预设的校验音频信号进行匹配，将第二音频信号与预设的解锁音频信号进行匹配，两个匹配结果均通过时，才进行解锁，本发明在进行音频解锁时通过匹配特定音频信号的方式来提升音频解锁的安全性。该预设的校验音频信号可以是在采集音频信号的过程中，设备本身或授权的外部设备播放的校验音频信号，使得采集到的音频信号中含有该校验音频信号，当别有用心之人采用录制声音回放的方式进行解锁时，会因为从采集的音频信号中分离出的第一音频信号与采集该音频信号过程中播放的校验音频信号不匹配，而解锁失败，使得安全性大大提升。
Claims (11)
- 一种音频解锁方法，包括：采集环境音频信号；从所述环境音频信号中分离第一音频信号和第二音频信号；如果分离出的第一音频信号与采集所述环境音频信号过程中自身播放或授权外部设备播放的校验音频信号相匹配，且第二音频信号与预设的解锁音频信号相匹配，则解锁。
- 如权利要求1所述的音频解锁方法，其中，所述第一音频信号、第二音频信号为不同频段，从所述环境音频信号中分离第一音频信号和第二音频信号包括：根据预设的频段范围对所述环境音频信号进行滤波处理，提取所述环境音频信号中的所述第一音频信号或第二音频信号，所述环境音频信号中的其他部分作为所述第二音频信号或第一音频信号。
- 如权利要求1所述的音频解锁方法，其中，如果分离出的第一音频信号与采集所述环境音频信号过程中自身播放或授权外部设备播放的校验音频信号的以下特征信息中的至少一个相匹配，则认为两者相匹配：播放起始时间点、频率、承载内容、旋律、节奏、音色。
- 如权利要求3所述的音频解锁方法，其中，所述校验音频信号中的至少一个特征信息是随机产生的信息。
- 如权利要求1至4任一项所述的音频解锁方法，其中，所述采集环境音频信号的过程中，播放所述校验音频信号。
- 如权利要求5所述的音频解锁方法，其中，播放所述校验音频信号之前，还包括按照如下方式生成所述校验音频信号：生成一随机信息；根据预设编码规则对所述随机信息进行编码；对编码后的内容按照预设频率转换成所述校验音频信号。
- 一种音频解锁装置，包括：采集模块，设置为采集环境音频信号；分离模块，设置为从所述采集模块采集的环境音频信号中分离第一音频信号和第二音频信号；解锁处理模块，设置为如果所述分离模块分离出的第一音频信号与采集所述环境音频信号过程中自身播放或授权外部设备播放的校验音频信号相匹配，且第二音频信号与预设的解锁音频信号相匹配，则解锁。
- 如权利要求7所述的音频解锁装置，其中，所述分离模块包括：滤波模块，设置为根据预设的频段范围对所述环境音频信号进行滤波处理，提取所述环境音频信号中的所述第一音频信号或第二音频信号，所述环境音频信号中的其他部分作为所述第二音频信号或第一音频信号；所述第一音频信号、第二音频信号为不同频段。
- 如权利要求7所述的音频解锁装置，其中，所述解锁处理模块包括第一匹配模块，设置为如果分离出的第一音频信号与采集所述环境音频信号过程中自身播放或授权外部设备播放的校验音频信号的以下特征信息中的至少一个相匹配，则认为两者相匹配：播放起始时间点、频率、承载内容、旋律、节奏、音色。
- 如权利要求7至9任一项所述的音频解锁装置，其中，还包括放音模块，设置为所述采集模块采集环境音频信号的过程中，播放所述校验音频信号。
- 如权利要求10所述的音频解锁装置，其中，还包括：生成模块，设置为生成一随机信息；编码模块，设置为根据预设编码规则对所述随机信息进行编码；转换模块，设置为对编码后的内容按照预设频率转换成所述校验音频信号，将所述校验音频信号传输至所述放音模块。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510718103.6A CN106657554A (zh) | 2015-10-29 | 2015-10-29 | 一种音频解锁方法及装置 |
| CN201510718103.6 | 2015-10-29 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2016184096A1 true WO2016184096A1 (zh) | 2016-11-24 |
Family
ID=57319271
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2015/098023 WO2016184096A1 (zh) | 2015-10-29 | 2015-12-21 | 一种音频解锁方法及装置 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN106657554A (zh) |
| WO (1) | WO2016184096A1 (zh) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102019209621B3 (de) * | 2019-07-01 | 2020-08-06 | Sonobeacon Gmbh | Audiosignal-basiertes Paketzustellsystem |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107147791B (zh) * | 2017-05-15 | 2019-11-15 | 上海与德科技有限公司 | 一种语音解锁的方法、装置及移动终端 |
| CN107331395A (zh) * | 2017-06-28 | 2017-11-07 | 上海传英信息技术有限公司 | 一种基于智能终端的语音控制方法及语音控制系统 |
| CN109448138B (zh) * | 2018-09-30 | 2021-03-16 | 山东知味行网络科技有限公司 | 一种电子票券系统及方法 |
| CN109583171A (zh) * | 2018-12-05 | 2019-04-05 | 北京蓦然认知科技有限公司 | 一种用户登录解锁方法、装置 |
| CN109949822A (zh) * | 2019-03-31 | 2019-06-28 | 联想(北京)有限公司 | 信号处理方法和电子设备 |
| CN111275858B (zh) * | 2020-01-22 | 2022-07-01 | 广东快车科技股份有限公司 | 一种声纹识别的授信方法及系统 |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4949379A (en) * | 1989-05-05 | 1990-08-14 | Steve Cordell | Process for encrypted information transmission |
| CN103297590A (zh) * | 2012-02-24 | 2013-09-11 | 中兴通讯股份有限公司 | 一种基于音频实现设备解锁的方法和系统 |
| CN204720160U (zh) * | 2015-04-21 | 2015-10-21 | 吴桂广 | 生物识别音频安全系统 |
-
2015
- 2015-10-29 CN CN201510718103.6A patent/CN106657554A/zh not_active Withdrawn
- 2015-12-21 WO PCT/CN2015/098023 patent/WO2016184096A1/zh active Application Filing
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4949379A (en) * | 1989-05-05 | 1990-08-14 | Steve Cordell | Process for encrypted information transmission |
| CN103297590A (zh) * | 2012-02-24 | 2013-09-11 | 中兴通讯股份有限公司 | 一种基于音频实现设备解锁的方法和系统 |
| CN204720160U (zh) * | 2015-04-21 | 2015-10-21 | 吴桂广 | 生物识别音频安全系统 |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102019209621B3 (de) * | 2019-07-01 | 2020-08-06 | Sonobeacon Gmbh | Audiosignal-basiertes Paketzustellsystem |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106657554A (zh) | 2017-05-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2016184096A1 (zh) | 一种音频解锁方法及装置 | |
| US10720166B2 (en) | Voice biometrics systems and methods | |
| JP5015939B2 (ja) | 音響的外耳特徴付けのための方法及び装置 | |
| JP4573792B2 (ja) | ユーザ認証システム、不正ユーザ判別方法、およびコンピュータプログラム | |
| Shirvanian et al. | Wiretapping via mimicry: Short voice imitation man-in-the-middle attacks on crypto phones | |
| TWI481774B (zh) | 房門解鎖方法、資產使用權租賃方法及使用其之系統 | |
| US20120290297A1 (en) | Speaker Liveness Detection | |
| CN105913850B (zh) | 文本相关声纹密码验证方法 | |
| JP2017534905A (ja) | 声紋情報管理方法および声紋情報管理装置、ならびに本人認証方法および本人認証システム | |
| US20100076770A1 (en) | System and Method for Improving the Performance of Voice Biometrics | |
| CN106463120B (zh) | 一种通过动态声音性的安全信息以辨识或认证人和/或物的方法及装置 | |
| JP2006010809A (ja) | 個人認証システム | |
| TW200820218A (en) | Portable personal authentication method and electronic business transaction method | |
| JP2015191076A (ja) | 音声識別装置 | |
| Shirvanian et al. | Quantifying the breakability of voice assistants | |
| JP2008309959A (ja) | オーディオ信号記録装置、電子ファイル | |
| CN113012715A (zh) | 用于支持语音的计算机系统的声学特征 | |
| US11397799B2 (en) | User authentication by subvocalization of melody singing | |
| JP2002297199A (ja) | 合成音声判別方法と装置及び音声合成装置 | |
| CN101882438A (zh) | 音乐数据处理方法与应用其的电子装置 | |
| JP4263439B2 (ja) | 本人認証装置および本人認証方法、コンピュータプログラム | |
| CN110322890A (zh) | 一种身份识别装置 | |
| WO2023119629A1 (ja) | 情報処理システム、情報処理方法、記録媒体、及びデータ構造 | |
| WO2019006587A1 (zh) | 说话者识别系统及说话者识别方法及入耳式装置 | |
| FI127920B (en) | Online multimodal information transfer method, associated system and device |
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: 15892470 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: 15892470 Country of ref document: EP Kind code of ref document: A1 |