WO2015149359A1 - 一种自动调节音量的方法、音量调节装置及电子设备 - Google Patents

一种自动调节音量的方法、音量调节装置及电子设备 Download PDF

Info

Publication number
WO2015149359A1
WO2015149359A1 PCT/CN2014/074821 CN2014074821W WO2015149359A1 WO 2015149359 A1 WO2015149359 A1 WO 2015149359A1 CN 2014074821 W CN2014074821 W CN 2014074821W WO 2015149359 A1 WO2015149359 A1 WO 2015149359A1
Authority
WO
WIPO (PCT)
Prior art keywords
electronic device
voice signal
volume adjustment
volume
evaluation
Prior art date
Application number
PCT/CN2014/074821
Other languages
English (en)
French (fr)
Inventor
陈永
孙增才
Original Assignee
华为终端有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为终端有限公司 filed Critical 华为终端有限公司
Priority to CN201480001379.6A priority Critical patent/CN104335559B/zh
Priority to PCT/CN2014/074821 priority patent/WO2015149359A1/zh
Priority to EP14888498.4A priority patent/EP3110116B1/en
Publication of WO2015149359A1 publication Critical patent/WO2015149359A1/zh

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04MTELEPHONIC COMMUNICATION
    • H04M1/00Substation equipment, e.g. for use by subscribers
    • H04M1/60Substation equipment, e.g. for use by subscribers including speech amplifiers
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04MTELEPHONIC COMMUNICATION
    • H04M2250/00Details of telephonic subscriber devices
    • H04M2250/74Details of telephonic subscriber devices with voice recognition means

Definitions

  • the present invention relates to the field of electronic devices, and in particular, to a method for automatically adjusting a volume, a volume adjusting device, and an electronic device. Background technique
  • the volume of the call may be unsatisfactory to the caller due to environmental or human factors.
  • the output volume of the electronic device is manually adjusted, so that the call volume meets his own needs.
  • the technical problem mainly solved by the present invention is how to automatically adjust the volume according to the actual situation conveniently and quickly, and improve the user's calling experience.
  • the present invention provides a method for automatically adjusting the volume, a volume adjusting device, and an electronic device, which can automatically adjust the volume according to the semantics of the caller, thereby improving the user's calling experience.
  • an embodiment of the present invention provides a method for automatically adjusting a volume, where the method includes: after establishing a call connection, the first electronic device receives a voice signal; identifying the voice signal and performing semantic analysis to obtain semantic recognition Result: matching the semantic recognition result with the pre-stored evaluation semantics to obtain a volume adjustment rule; and automatically adjusting a volume output mode of the electronic device according to the volume adjustment rule.
  • the voice signal includes a voice signal received by the first electronic device by using a microphone, or a second received by the first electronic device The voice signal sent by the electronic device.
  • the voice signal is a voice signal received by the first electronic device through a microphone
  • the pre-stored evaluation semantics are that the evaluation sound is too small, and the corresponding volume adjustment rule is Increasing the volume of the earpiece of the first electronic device; or the pre-stored evaluation semantics is that the evaluation sound is too large, and the corresponding volume adjustment rule is to reduce the volume of the earpiece of the first electronic device; or the pre-stored evaluation semantics is When the evaluation environment is noisy, the corresponding volume adjustment rule is to switch the first electronic device from the earpiece output to the rabi output.
  • the pre-storing The evaluation semantics is that the evaluation sound is too small, and the corresponding volume adjustment rule is to increase the microphone gain of the first electronic device to increase the microphone volume; or the pre-stored evaluation semantics is that the evaluation sound is too large, and the corresponding volume adjustment rule is The microphone gain of the first electronic device is lowered to reduce the microphone volume.
  • an embodiment of the present invention provides a volume adjustment apparatus, where the volume adjustment apparatus includes a receiving module, an identification module, a matching module, and a volume adjustment module, where the volume adjustment apparatus is applied to a first electronic device, where:
  • the receiving module is configured to receive a voice signal after the electronic device establishes a call connection;
  • the identifying module is configured to identify the voice signal received by the receiving module and perform semantic analysis to obtain a semantic recognition result;
  • the sound adjustment module is configured to automatically adjust the volume adjustment rule according to the volume adjustment rule acquired by the matching module, by using the voice recognition result obtained by the identification module to match the pre-stored evaluation semantics.
  • the volume output mode of the electronic device where:
  • the volume adjustment device is applied to a first electronic device, where the voice signal includes a voice signal received by the first electronic device through a microphone; Or the first electronic device performs a received voice signal sent by the second electronic device.
  • the voice signal is a voice signal received by the first electronic device by using a microphone
  • the pre-stored evaluation semantics is that the evaluation sound is too small, and the corresponding volume adjustment rule is to increase the earpiece volume of the first electronic device; or the pre-stored evaluation semantics is that the evaluation sound is too large, and the corresponding volume adjustment rule is to reduce the The earphone volume of the first electronic device; or the pre-stored evaluation semantics is when the environment in which the evaluation is performed is noisy, and the corresponding volume adjustment rule is to switch the first electronic device from the earpiece output to the rabi output.
  • the third possible aspect of the second aspect In an implementation manner, when the voice signal is a voice signal from a second electronic device that is in a conversation with the first electronic device, the pre-stored evaluation semantics is that the evaluation sound is too small, and the corresponding volume adjustment rule is increased.
  • the microphone gain of the first electronic device is used to increase the microphone volume; or the pre-stored evaluation semantics is that the evaluation sound is too large, and the corresponding volume adjustment rule is to reduce the microphone gain of the first electronic device to reduce the microphone volume.
  • an embodiment of the present invention provides an electronic device, where the electronic device includes a processor, a memory, and a receiver, where the processor is coupled to the memory and the receiver, where the electronic device is a first electronic device.
  • the receiver is configured to receive a voice signal after the electronic device establishes a call connection;
  • the processor identifies the voice signal received by the receiver and performs semantic analysis to obtain a semantic recognition result,
  • the semantic recognition result is matched with the pre-stored evaluation semantics to obtain a volume adjustment rule, and the volume output mode of the electronic device is automatically adjusted according to the volume adjustment rule;
  • the memory is configured to store the evaluation semantics.
  • the receiver includes a microphone or a wireless transceiver, and when the receiver is a microphone, the voice signal is the first electronic device a voice signal received by the microphone; or a voice signal transmitted by the second electronic device received by the first electronic device when the receiver is the wireless transceiver.
  • the voice signal is a voice signal that is received by the first electronic device by using the microphone
  • the pre-stored evaluation semantics is that the evaluation sound is too small, and the corresponding volume adjustment rule is to increase the earpiece volume of the first electronic device; or the pre-stored evaluation semantics is that the evaluation sound is too large, and the corresponding volume adjustment rule is lowered.
  • the earphone volume of the first electronic device; or the pre-stored evaluation semantics is when the environment in which the environment is evaluated is noisy, and the corresponding volume adjustment rule is to switch the first electronic device from the earpiece output to the speaker output.
  • a third possible implementation manner of the third aspect when the voice signal is a voice from a second electronic device that is in a conversation with the first electronic device, the pre-stored evaluation semantics is that the evaluation sound is too small, and the corresponding volume adjustment rule is to increase the microphone gain of the first electronic device to increase the microphone volume; or the pre-stored evaluation semantics is evaluation The sound is too loud, and the corresponding volume adjustment rule is to reduce the microphone gain of the first electronic device to reduce the microphone volume.
  • Embodiments of the present invention provide a method and an electronic device for automatically adjusting a volume, by receiving a language
  • the sound signal identify and perform semantic analysis to obtain the semantic recognition result, obtain the volume adjustment rule by matching the semantic recognition result with the pre-stored evaluation semantics, and automatically adjust the volume output mode of the electronic device according to the volume adjustment rule.
  • the volume adjustment can be automatically performed based on the semantic recognition result of the voice signal without manual intervention, thereby avoiding the impact of the call process and improving the call experience of the caller.
  • FIG. 1 is a flow chart of a method for automatically adjusting a volume according to an embodiment of the present invention
  • FIG. 2 is a schematic structural diagram of a first volume adjustment device according to an embodiment of the present invention
  • FIG. 3 is a first embodiment of the present invention. Schematic diagram of the structure of an electronic device. detailed description
  • FIG. 1 is a flowchart of a method for automatically adjusting a volume according to an embodiment of the present invention. This embodiment is described by using an electronic device.
  • the method for automatically adjusting a volume in this embodiment includes the following steps:
  • the electronic device After the electronic device establishes a call with another electronic device, the electronic device receives the voice signal.
  • the electronic device is defined as a first electronic device, and another electronic device that establishes a call with the electronic device is a second electronic device.
  • the voice signal may be a voice signal received by the electronic device through the microphone, or may be a voice signal sent by the second electronic device received by the electronic device.
  • Semantic analysis is to extract keywords from the speech recognition results, analyze and understand the meaning that the user wants to express, and then give the semantic recognition results. For example, receiving the voice signal from the first electronic device is "Oh, how is the sound so small”, the result of the speech recognition is "Oh, how is the sound so small”. Semantic analysis is to extract keywords such as "sound” and “small” from “Oh, how sound is so small”, and to analyze and understand that the semantic recognition result may be "sound too small.” When performing semantic analysis, it can be performed according to a predetermined rule. For example, if the extracted keyword has “sound” and “small”, the semantic recognition result is considered to be “sound too small”. Or as long as there is a "big””sound” in the extracted relationship words, The result of the semantic recognition is "sound too loud”.
  • the correspondence between the pre-stored evaluation semantics and the volume adjustment rule is as follows:
  • the correspondence between the above evaluation semantics and the volume adjustment rule may be pre-stored in the database.
  • the correspondence between the above evaluation semantics and the volume adjustment rule may be pre-stored in the database 1. That is, as long as the received speech signal is a speech signal from the first electronic device end, the semantic recognition result is matched with the evaluation semantics in the database 1 when the speech signal is identified and semantically analyzed to obtain a semantic recognition result.
  • the voice signal is a voice signal sent by the second electronic device received by the first electronic device
  • the correspondence between the pre-stored evaluation semantics and the volume adjustment rule is as follows:
  • the correspondence between the above evaluation semantics and the volume adjustment rule may be pre-stored in the database.
  • the correspondence between the above evaluation semantics and the volume adjustment rule may be pre-stored in the database 2. That is, as long as the received speech signal is a speech signal from the second electronic device end, the semantic recognition result is matched with the evaluation semantics in the database 2 when the speech signal is identified and semantically analyzed to obtain a semantic recognition result.
  • the corresponding relationship between the pre-existing evaluation semantics and the volume adjustment rules of the above two application scenarios is The distinction is made separately for description and preservation.
  • the correspondence between the pre-stored evaluation semantics and the volume adjustment rules for the above two different application scenarios can also be stored in the same database.
  • S104 automatically adjust the volume output mode of the electronic device according to the volume adjustment rule; adjust the volume output mode of the electronic device according to the volume adjustment rule.
  • the amplitude of the volume adjustment can be adjusted according to the preset adjustment threshold. For example, when the semantic expression is that the sound is too small, the volume of the earpiece of the electronic device is automatically increased by a threshold. When the semantic expression is too loud, the volume of the earpiece of the electronic device is automatically lowered by a threshold.
  • This threshold is a value preset according to experience, such as one, two or three. That is to say, when the threshold is set to one grid, each time the volume is adjusted or lowered according to the volume adjustment rule, the current handset volume is turned up or down by one grid.
  • the user can also set an adjustment threshold according to his own needs. The invention is not limited thereto.
  • the method for automatically adjusting the volume obtained by the embodiment of the present invention obtains a semantic recognition result by receiving a voice signal, identifying and performing semantic analysis, and obtaining a volume by matching the semantic recognition result with the pre-stored evaluation semantics.
  • the adjustment rule automatically adjusts the volume output mode of the electronic device according to the volume adjustment rule.
  • a and B use a mobile phone to make a call, and the A-end mobile phone is the first electronic device. After the call is connected, it is assumed that A says "your side.”"How is the sound so small?" The A-side phone is voiced and semantically analyzed to obtain the semantic recognition result "sound is too small”.
  • the correspondence between the semantics and the volume adjustment rule is evaluated in the context of the above-mentioned voice signal from the first electronic device.
  • the corresponding volume adjustment rule is to increase the volume of the earpiece of the first electronic device, that is, to increase the volume of the handset of the A-end handset.
  • the A-end mobile phone automatically raises the volume of the handset so that A can hear the voice transmitted from the B-side mobile phone. And if A said "I am so noisy here", the A-side mobile phone is voiced and semantically analyzed to obtain the semantic recognition result "environmental noisy”, and the semantic and volume adjustment is evaluated by the above-mentioned voice signal from the first electronic device. Corresponding relationship of the rules, matching the corresponding volume adjustment rule is to switch the output of the first electronic device from the handset output to the rabi output, that is, the A-end mobile phone is switched from the handset output mode to the rabi output mode.
  • FIG. 2 is a schematic structural diagram of a first volume adjustment apparatus according to an embodiment of the present invention.
  • the volume adjustment apparatus 100 of the embodiment includes a receiving module 11, an identification module 12, a matching module 13, and a volume adjustment module 14,
  • the volume adjusting device of this embodiment is a first volume adjusting device, wherein:
  • the receiving module 11 is configured to receive a voice signal after the electronic device establishes a call connection; after the electronic device establishes a call connection with another electronic device, the receiving module 11 receives the voice signal.
  • the electronic device is defined as a first electronic device, and another electronic device that defines a call with the first electronic device is a second electronic device.
  • the volume adjustment device 100 of this embodiment is applied to the first electronic device, where the voice signal may be a voice signal received by the first electronic device through the microphone, or may be a voice signal sent by the second electronic device received by the first electronic device. .
  • the identification module 12 is configured to identify and perform semantic analysis on the voice signal received by the receiving module 11 to obtain a semantic recognition result
  • the recognition module 12 performs speech recognition on the received speech signal to obtain a speech recognition result, and further performs semantic analysis on the speech recognition result to obtain a semantic recognition result.
  • Semantic analysis is to extract the keywords from the speech recognition results, analyze and understand the meaning that the user wants to express, and then give the semantic recognition results. For example, the caller on the first electronic device said, "I am so noisy here.” After the speech recognition, the speech recognition result is "I am so noisy here.” Further semantic analysis shows that the semantic recognition result may be "environmentally noisy”.
  • the matching module 13 is configured to match the speech recognition result recognized by the identification module 12 with the pre-stored evaluation semantics to obtain a volume adjustment rule.
  • Semantic recognition results are obtained in semantic recognition.
  • the evaluation semantics are pre-stored for evaluating the volume.
  • Each pre-existing evaluation The semantics correspond to a volume adjustment rule.
  • the volume adjustment rule corresponding to the matched pre-stored evaluation semantics is obtained.
  • the corresponding relationship between the evaluation semantics and the volume adjustment rule can be referred to the detailed description of the above embodiments, and details are not described herein.
  • the volume adjustment module 14 is configured to automatically adjust the volume output module of the electronic device according to the volume adjustment rule acquired by the matching module 13.
  • the amplitude of the volume adjustment can be adjusted according to the preset adjustment threshold.
  • the volume of the earpiece of the electronic device is automatically increased by a threshold.
  • the semantic expression is too loud, the volume of the earpiece of the electronic device is automatically lowered by a threshold.
  • This threshold is a value preset according to experience, such as one, two or three. That is to say, when the threshold is set to one grid, each time the volume is adjusted or lowered according to the volume adjustment rule, the current handset volume is turned up or down by one grid.
  • the user can also set an adjustment threshold according to his own needs. The invention is not limited thereto.
  • FIG. 3 is a schematic structural diagram of a first electronic device according to an embodiment of the present invention.
  • the electronic device 200 of the embodiment includes a processor 21, a memory 22, a receiver 23, a transmitter 24, and a bus system 25.
  • the electronic device of this embodiment is a first electronic device, wherein:
  • the processor 21 controls the operation of the electronic device 200, which may also be referred to as a CPU (Central Processing Unit).
  • Processor 21 may be an integrated circuit chip with signal processing capabilities.
  • the processor 21 can also be a general-purpose processor, a digital signal processing (DSP), an application specific integrated circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other Programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.
  • the general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
  • the memory 22 can include read only memory and random access memory and provides instructions and data to the processor 21. A portion of the memory 22 may also include non-volatile random access memory (NVRAM).
  • NVRAM non-volatile random access memory
  • the various components of the electronic device 200 are coupled together by a bus system 25, wherein the bus system In addition to the data bus, 25 may include a power bus, a control bus, and a status signal bus.
  • the bus system may be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus.
  • the bus may be one or more physical lines, and when it is a plurality of physical lines, it may be divided into an address bus, a data bus, a control bus, and the like.
  • the processor 21, the memory 22, and the receiver 23 and the transmitter 24 may also be directly connected through a communication line.
  • various buses are labeled as the bus system 25 in the figure.
  • Memory 22 stores the following elements, executable modules or data structures, or a subset of them, or their extended set:
  • Operation instructions Includes various operation instructions for implementing various operations.
  • Operating System Includes a variety of system programs for implementing a variety of basic services and handling hardware-based tasks.
  • the processor 21 calls an operation instruction stored in the memory 22 (the operation instruction can be stored in the operating system).
  • the receiver 23 is configured to receive a voice signal after establishing a call connection.
  • the processor 21 controls the receiver 23 to receive the voice signal.
  • the electronic device is defined as a first electronic device, and another electronic device that defines a call with the first electronic device is a second electronic device.
  • the receiver 23 may be a microphone or a wireless receiver.
  • the voice signal here is a voice signal received by the first electronic device through the microphone.
  • the receiver 23 is a wireless receiver, the voice signal is sent by the second electronic device received by the first electronic device. The voice signal is played through the handset of the first electronic device.
  • the processor 21 performs speech recognition on the speech signal received by the receiver 23 and performs semantic analysis to obtain a semantic recognition result, and matches the semantic recognition result with the pre-stored evaluation semantics to obtain a volume adjustment rule, and automatically adjusts the volume of the electronic device according to the volume adjustment rule. Output mode.
  • the processor 21 performs speech recognition on the speech signal received by the receiver 23 to obtain a speech recognition result, and further performs semantic analysis on the speech recognition result to obtain a semantic recognition result.
  • Semantic analysis is to extract keywords from the speech recognition results, and analyze and understand the user's desired table. The meaning of reaching, thus giving the result of semantic recognition. For example, the voice signal received from the first electronic device is "Oh, how is the sound so small”, and the speech recognition result is "Oh, how is the sound so small”. Semantic analysis is to extract keywords such as "sound” from “Oh, how is the voice so small”,
  • the semantic recognition result is obtained, and the processor 21 matches the semantic recognition result with the pre-stored evaluation semantics, and the evaluation semantics are pre-stored for evaluating the volume.
  • the pre-stored evaluation semantics corresponds to a volume adjustment rule.
  • the volume adjustment rule corresponding to the pre-stored evaluation semantics is obtained, and the processor 21 adjusts the volume output mode of the electronic device according to the volume adjustment rule.
  • the correspondence between the pre-stored evaluation semantics and the volume adjustment rule can be seen in Table 1 above, and when the voice signal is the second received by the first electronic device.
  • the correspondence between the pre-stored evaluation semantics and the volume adjustment rule can be seen in Table 2 above.
  • the corresponding relationship between the evaluation semantics and the volume adjustment rule in the two application scenarios may be correspondingly stored in different databases. Of course, it can also be stored in the same database.
  • matching is performed, if the match is not successful, the volume adjustment action is not performed.
  • the memory 22 is used to store evaluation semantics.
  • Transmitter 24 is used to send data to the outside.
  • each step of the above method may be completed by an integrated logic circuit of hardware in the processor 21 or an instruction in a form of software.
  • the methods, steps, and logical block diagrams disclosed in the embodiments of the present invention may be implemented or executed.
  • the steps of the method disclosed in the embodiments of the present invention may be directly implemented as a hardware decoding processor, or by using a hard processor in the decoding processor.
  • the combination of the piece and the software module is completed.
  • the software modules can be located in a conventional storage medium such as random access memory, flash memory, read only memory, programmable read only memory or electrically erasable programmable memory, registers, and the like.
  • the storage medium is located in the memory 22, and the processor 21 reads the information in the memory 22 and combines the hardware to perform the steps of the above method.
  • the method and the electronic device for automatically adjusting the volume obtained by the embodiment of the present invention obtain the semantic recognition result by receiving the voice signal, identifying and performing semantic analysis, and obtaining the volume by matching the semantic recognition result with the pre-stored evaluation semantics.
  • the adjustment rule automatically adjusts the volume output mode of the electronic device according to the volume adjustment rule. In the above manner, the volume adjustment can be automatically performed based on the semantic recognition result of the voice signal without manual intervention, thereby avoiding the influence of the call process and improving the call experience of the caller.
  • the disclosed system, apparatus, and method may be implemented in other manners.
  • the device embodiments described above are merely illustrative.
  • the division of the modules or units is only a logical function division.
  • there may be another division manner for example, multiple units or components may be used. Combined or can be integrated into another system, or some features can be ignored, or not executed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect connection or communication connection through some interface, device or unit, and may be in electrical, mechanical or other form.
  • the components displayed as units may or may not be physical units, i.e., may be located in one place, or may be distributed over multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.
  • the integrated unit if implemented in the form of a software functional unit and sold or used as a standalone product, may be stored in a computer readable storage medium.
  • the technical solution of the present invention may contribute to the prior art or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium.
  • the foregoing storage medium includes: a U disk, a removable hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like, which can store program code. .

Landscapes

  • Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Telephone Function (AREA)

Abstract

一种自动调节音量的方法及电子设备,其中,自动调节音量的方法包括:在电子设备建立通话连接后,电子设备接收语音信号,将语音信号进行识别并进行语义分析得到语义识别结果,将语义识别结果与预存的评价语义进行匹配获取音量调节规则,根据音量调节规则调节电子设备的音量输出模式。通过这样的方式,能够根据语音信号的语义识别结果自动调节音量,提升用户的通话体验。

Description

一种自动调节音量的方法、 音量调节装置及电子设备 技术领域
本发明涉及电子设备领域, 特别涉及一种自动调节音量的方法、 音量 调节装置及电子设备。 背景技术
随着社会的发展, 电子设备比如手机、 平板电脑逐渐普及, 几乎人手 一个电子设备。
在利用电子设备进行通话的过程中, 可能因为环境或人为因素, 有时 候通话音量可能会令通话者不满意。 通常在通话过程中, 如果通话者对当 前的通话音量不是很满意时, 都是通过手动方式调节电子设备的输出音量, 从而使得通话音量符合自己的需求。
但是这种调节方式往往比较复杂, 而且有可能使当前通话受到干扰。 发明内容
本发明主要解决的技术问题是如何方便快捷地根据实际情况自动调节 音量, 提升用户的通话体验。
有鉴于此, 本发明提出一种自动调节音量的方法、 音量调节装置及电 子设备, 能够根据通话者的语义自动调节音量, 提升用户的通话体验。
第一方面, 本发明实施例提供一种自动调节音量的方法, 所述方法包 括: 在建立通话连接后, 第一电子设备接收语音信号; 将所述语音信号进 行识别并进行语义分析得到语义识别结果; 将所述语义识别结果与预存的 评价语义进行匹配获取音量调节规则; 根据所述音量调节规则自动调节所 述电子设备的音量输出模式。
结合第一方面, 在第一方面的第一种可能的实现方式中: 所述语音信 号包括所述第一电子设备通过麦克风接收到的语音信号; 或所述第一电子 设备接收到的第二电子设备发送的语音信号。
结合第一方面的第一种可能的实现方式, 在第一方面的第二种可能的 实现方式中: 当所述语音信号为所述第一电子设备通过麦克风接收到的语 音信号时, 所述预存的评价语义为评价声音太小, 对应的音量调节规则为 调高所述第一电子设备的听筒音量; 或所述预存的评价语义为评价声音太 大, 对应的音量调节规则为降低所述第一电子设备的听筒音量; 或所述预 存的评价语义为评价所处环境嘈杂时, 对应的音量调节规则为将所述第一 电子设备由听筒输出切换为喇八输出。
结合第一方面的第二种可能的实现方式, 在第一方面的第三种可能的 实现方式中: 当所述第一电子设备接收到的第二电子设备发送的语音信号 时, 所述预存的评价语义为评价声音太小, 对应的音量调节规则为调高所 述第一电子设备的麦克风增益以提高麦克风音量; 或所述预存的评价语义 为评价声音太大, 对应的音量调节规则为降低所述第一电子设备的麦克增 益以降低麦克风音量。
第二方面, 本发明实施例提供一种音量调节装置, 所述音量调节装置 包括接收模块、 识别模块、 匹配模块以及音量调节模块, 所述音量调节装 置应用于第一电子设备, 其中: 所述接收模块用于在所述电子设备建立通 话连接后, 接收语音信号; 所述识别模块用于将所述接收模块接收的所述 语音信号进行识别并进行语义分析得到语义识别结果; 所述匹配模块用于 将所述识别模块识别得到的所述语音识别结果与预存的评价语义进行匹配 获取音量调节规则; 所述音量调节模块用于根据所述匹配模块获取的所述 音量调节规则自动调节所述电子设备的音量输出模式。
结合第二方面, 在第二方面的第一种可能的实现方式中: 所述音量调 节装置应用于第一电子设备, 所述语音信号包括所述第一电子设备通过麦 克风接收到的语音信号; 或所述第一电子设备进行接收到的第二电子设备 发送的语音信号。
结合第二方面的第一种可能的实现方式, 在第二方面的第二种可能的 实现方式中: 当所述语音信号为所述第一电子设备通过麦克风接收到的语 音信号时, 所述预存的评价语义为评价声音太小, 对应的音量调节规则为 调高所述第一电子设备的听筒音量; 或所述预存的评价语义为评价声音太 大, 对应的音量调节规则为降低所述第一电子设备的听筒音量; 或所述预 存的评价语义为评价所处环境嘈杂时, 对应的音量调节规则为将所述第一 电子设备由听筒输出切换为喇八输出。
结合第二方面的第一种可能的实现方式, 在第二方面的第三种可能的 实现方式中: 当所述语音信号为来自与所述第一电子设备进行通话的第二 电子设备的语音信号时, 所述预存的评价语义为评价声音太小, 对应的音 量调节规则为调高所述第一电子设备的麦克风增益以提高麦克风音量; 或 所述预存的评价语义为评价声音太大, 对应的音量调节规则为降低所述第 一电子设备的麦克风增益以降低麦克风音量。
第三方面, 本发明实施例提供一种电子设备, 所述电子设备包括处理 器、 存储器以及接收器, 所述处理器分别耦接所述存储器以及接收器, 所 述电子设备为第一电子设备, 其中: 所述接收器用于在所述电子设备建立 通话连接后, 接收语音信号; 所述处理器对所述接收器接收的所述语音信 号进行识别并进行语义分析得到语义识别结果, 将所述语义识别结果与预 存的评价语义进行匹配获取音量调节规则, 根据所述音量调节规则自动调 节所述电子设备的音量输出模式; 所述存储器用于存储所述评价语义。
结合第三方面, 在第三方面的第一种可能的实现方式中: 所述接收器 包括麦克风或无线收发器, 当所述接收器为麦克风时, 所述语音信号为所 述第一电子设备通过麦克风接收到的语音信号; 或当所述接收器为所述无 线收发器时, 所述第一电子设备接收到的第二电子设备发送的语音信号。
结合第三方面的第一种可能的实现方式, 在第三方面的第二种可能的 实现方式中: 当所述语音信号为所述第一电子设备通过所述麦克风接收到 的语音信号时, 所述预存的评价语义为评价声音太小, 对应的音量调节规 则为调高所述第一电子设备的听筒音量; 或所述预存的评价语义为评价声 音太大, 对应的音量调节规则为降低所述第一电子设备的听筒音量; 或所 述预存的评价语义为评价所处环境嘈杂时, 对应的音量调节规则为将所述 第一电子设备由听筒输出切换为喇叭输出。
结合第三方面的第一种可能的实现方式, 在第三方面的第三种可能的 实现方式中: 当所述语音信号为来自与所述第一电子设备进行通话的第二 电子设备的语音信号时, 所述预存的评价语义为评价声音太小, 对应的音 量调节规则为调高所述第一电子设备的所述麦克风增益以提高所述麦克风 音量; 或所述预存的评价语义为评价声音太大, 对应的音量调节规则为降 低所述第一电子设备的所述麦克风增益以降低所述麦克风音量。
本发明实施例提供一种自动调节音量的方法及电子设备, 通过接收语 音信号, 识别并进行语义分析得到语义识别结果, 通过语义识别结果与预 存的评价语义进行匹配获取音量调节规则, 根据音量调节规则自动调节电 子设备端的音量输出模式。 通过上述方式, 能够基于语音信号的语义识别 结果, 自动进行音量调节, 无需人工干预, 从而避免了通话过程受到影响, 提高通话者的通话体验。 附图说明
图 1是本发明实施例提供的一种自动调节音量的方法的流程图; 图 2是本发明实施例提供的第一种音量调节装置的结构示意图; 图 3是本发明实施例提供的第一种电子设备的结构示意图。 具体实施方式
请参阅图 1,图 1是本发明实施例提供的一种自动调节音量的方法的流 程图, 本实施例以电子设备的角度来进行描述, 本实施例的自动调节音量 的方法包括以下步骤:
S101 : 在建立通话连接后, 电子设备接收语音信号;
在电子设备与另一电子设备建立通话后, 电子设备接收语音信号。 为 了便于描述, 本发明实施例中, 为了描述方便, 定义电子设备为第一电子 设备, 定义与所述电子设备建立通话的另一电子设备为第二电子设备。 这 里语音信号可以是电子设备通过麦克风接收到的语音信号, 也可以是电子 设备接收到的第二电子设备发送的语音信号。
S102: 将语音信号进行识别并进行语义分析得到语义识别结果; 对接收到的语音信号进行语音识别得到语音识别结果, 并进一步对语 音识别结果进行语义分析得到语义识别结果。 语义分析即是从语音识别结 果中进行提取出关键字, 进行分析理解得到用户想要表达的意思, 从而给 出语义识别结果。 比如接收来自第一电子设备端的语音信号为"哎呀, 声音 怎么这么小", 语音识别结果即是 "哎呀, 声音怎么这么小"。 语义分析即 是从 "哎呀, 声音怎么这么小" 中提取关键字如 "声音"、 "小", 进行分析 理解得到语义识别结果可能是"声音太小"。在进行语义分析时,可以根据预 定规则来进行, 比如只要提取的关键字中有 "声音" "小", 就认为语义识 别结果为 "声音太小"。 或者是只要提取的关系字中有 "大" "声音", 就认 为语义识别结果为 "声音太大"。
S103: 将语义识别结果与预存的评价语义进行匹配获取音量调节规则; 在语义识别得到语义识别结果时, 通过将语义识别结果与预存的评价 语义进行匹配, 评价语义是预存的用于对音量进行评价的。 每个预存的评 价语义分别对应一个音量调节规则。 当语义识别结果与预存的评价语义匹 配成功时, 获取与匹配的预存的评价语义相对应的音量调节规则。
当语音信号是第一电子设备通过麦克风接收到的语音信号时, 预存的 评价语义与音量调节规则的对应关系如下表 1所示:
表 1: 预存的评价语义与音量调节规则的一种对应关系
Figure imgf000007_0001
上述的评价语义与音量调节规则的对应关系, 可以预存在数据库中, 为了便于区分, 这里可以将上述的评价语义与音量调节规则的对应关系预 存在数据库 1 中。 也就是说, 只要接收的语音信号为来自第一电子设备端 的语音信号时, 在对语音信号进行识别并进行语义分析得到语义识别结果 时, 将语义识别结果与数据库 1中的评价语义进行匹配。
当语音信号为第一电子设备接收到的第二电子设备发送的语音信号 时, 预存的评价语义与音量调节规则的对应关系如下表 2所示:
表 2: 预存的评价语义与音量调节规则的另一种对应关系
Figure imgf000007_0002
上述的评价语义与音量调节规则的对应关系, 可以预存在数据库中, 为了便于区分, 这里可以将上述的评价语义与音量调节规则的对应关系预 存在数据库 2 中。 也就是说, 只要接收的语音信号为来自第二电子设备端 的语音信号时, 在对语音信号进行识别并进行语义分析得到语义识别结果 时, 将语义识别结果与数据库 2中的评价语义进行匹配。
上述两种应用场景的预存评价语义与音量调节规则的对应关系为了便 于区分才分开来进行描述和保存, 事实上, 针对上述两种不同应用场景的 预存的评价语义与音量调节规则的对应关系也可以存储在同一个数据库 中。 在进行匹配的时候, 如果匹配不成功, 不执行音量调节动作。
当然, 以上评价语义与音量调节规则的对应关系, 只是一种举例, 在 能够实现本发明目的的情况下, 也可以釆用其他的对应关系, 这可以根据 使用者的需要自行决定, 本发明对此不作限定。
S104: 根据音量调节规则自动调节电子设备的音量输出模式; 根据音量调节规则调节电子设备的音量输出模式。 需要说明的是, 在 具体音量调节的时候, 音量调节的幅度可以根据预设的调节阔值来进行调 节。 比如说, 当语义表达的是声音太小, 那自动将电子设备的听筒音量调 高一个阔值, 当语义表达的是声音太大, 那自动将电子设备的听筒音量调 低一个阈值等等。 这个阈值是根据经验预设的一个值, 比如可以是一格、 两格或者三格等。 也就是说, 当阔值设定为一格时, 每次根据音量调节规 则调高或调低音量时, 都是将当前听筒音量调高或调低一格。 当然, 用户 也可以根据自己的需要自行设置一个调节阔值。 本发明对此不作限定。
通过上述实施例的阐述, 可以理解, 本发明实施例提供的自动调节音 量的方法, 通过接收语音信号, 识别并进行语义分析得到语义识别结果, 通过语义识别结果与预存的评价语义进行匹配获取音量调节规则, 根据音 量调节规则自动调节电子设备端的音量输出模式。 通过上述方式, 能够基 于语音信号的语义识别结果, 自动进行相应的音量调节, 无需人工干预, 从而避免通话过程受到影响, 提高通话者的通话体验。
以下以一个具体的实施例来详细说明本发明的自动调节音量的方法, 例如 A和 B利用手机进行通话, A端手机为上述第一电子设备, 电话接通 后, 假设 A说 "你那边声音怎么那么小呢", A端手机经语音并语义分析后 得出语义识别结果 "声音太小", 以上述语音信号来自第一电子设备的情景 下评价语义与音量调节规则的对应关系, 匹配为对应的音量调节规则是调 高第一电子设备的听筒音量即调高 A端手机听筒音量。 这时候, A端手机 自动将听筒音量调高, 以便于 A能听清楚 B端手机传过来的语音。 而如果 是 A说"我这里好吵", A端手机经语音并语义分析后得出语义识别结果"环 境嘈杂", 以上述语音信号来自第一电子设备的情景下评价语义与音量调节 规则的对应关系, 匹配为对应的音量调节规则是将第一电子设备由听筒输 出切换为喇八输出即将 A端手机由听筒输出模式切换为喇八输出模式。 假 设是 B说 "哎呀, 这声音怎么那么小呢", A端手机经语音并语义分析后得 出语义识别结果 "声音太小", 以上述语音信号来自第二电子设备的情景下 评价语义与音量调节规则的对应关系, 匹配为对应的音量调节规则是调高 第一电子设备的麦克风增益, 以使得 A说话的声音调大后再传输到 B端手 机。 对于其他情景以此类推, 本发明不——举例说明。
请参阅图 2,图 2是本发明实施例提供的第一种音量调节装置的结构示 意图, 本实施例的音量调节装置 100包括接收模块 11、 识别模块 12、 匹配 模块 13以及音量调节模块 14,本实施例的音量调节装置为第一音量调节装 置, 其中:
接收模块 11用于在电子设备建立通话连接后, 接收语音信号; 在电子设备与另一电子设备建立通话连接后, 接收模块 11接收语音信 号。 为了便于描述, 本发明实施例中, 定义电子设备为第一电子设备, 定 义与第一电子设备建立通话的另一电子设备为第二电子设备。 本实施例的 音量调节装置 100应用于第一电子设备, 这里语音信号可以是第一电子设备 通过麦克风接收到的语音信号, 也可以是第一电子设备接收到的第二电子 设备发送的语音信号。
识别模块 12用于将接收模块 11接收的语音信号进行识别并进行语义分 析得到语义识别结果;
识别模块 12对接收到的语音信号进行语音识别得到语音识别结果, 并 进一步对语音识别结果进行语义分析得到语义识别结果。 语义分析即是从 语音识别结果中提取出关键字, 进行分析理解得到用户想要表达的意思, 从而给出语义识别结果。 比如第一电子设备端的通话者说"我这里好吵",经 过语音识别得到语音识别结果为 "我这里好吵" , 进一步进行语义分析得 到语义识别结果可能是"环境嘈杂 "。
匹配模块 13用于将识别模块 12识别得到的语音识别结果与预存的评价 语义进行匹配获取音量调节规则。
在语义识别得到语义识别结果, 通过将语义识别结果与预存的评价语 义进行匹配, 评价语义是预存的用于对音量进行评价的。 每个预存的评价 语义分别对应一个音量调节规则。 当语义识别结果与预存的评价语义匹配 成功时, 获取与匹配的预存的评价语义相对应的音量调节规则。
对于语音信号来自第一电子设备或者是来自第二电子设备两种不同的 应用场景, 评价语义与音量调节规则的对应关系可以参阅上述实施例的详 细描述, 在此不在赘述。
音量调节模块 14用于根据匹配模块 13获取的音量调节规则自动调节 电子设备的音量输出模块。
根据音量调节规则调节电子设备的音量输出模式。 需要说明的是, 在 具体音量调节的时候, 音量调节的幅度可以根据预设的调节阔值来进行调 节。 比如说, 当语义表达的是声音太小, 那自动将电子设备的听筒音量调 高一个阔值, 当语义表达的是声音太大, 那自动将电子设备的听筒音量调 低一个阈值等等。 这个阈值是根据经验预设的一个值, 比如可以是一格、 两格或者三格等。 也就是说, 当阔值设定为一格时, 每次根据音量调节规 则调高或调低音量时, 都是将当前听筒音量调高或调低一格。 当然, 用户 也可以根据自己的需要自行设置一个调节阔值。 本发明对此不作限定。
请参阅图 3,图 3是本发明实施例提供的第一种电子设备的结构示意图, 本实施例的电子设备 200包括处理器 21、 存储器 22、 接收器 23、 发送器 24以及总线系统 25, 本实施例的电子设备为第一电子设备, 其中:
处理器 21控制电子设备 200的操作,处理器 21还可以称为 CPU( Central Processing Unit, 中央处理单元)。 处理器 21可能是一种集成电路芯片, 具 有信号的处理能力。处理器 21还可以是通用处理器、数字信号处理器(DSP, Digital Signal Processing )、 专用集成电路 ( ASIC, Application Specific Integrated Circuit )、 现场可编程门阵列 ( FPGA, Field - Programmable Gate Array )或者其他可编程逻辑器件、 分立门或者晶体管逻辑器件、 分立硬件 组件。 通用处理器可以是微处理器或者该处理器也可以是任何常规的处理 器等。
存储器 22可以包括只读存储器和随机存取存储器, 并向处理器 21提 供指令和数据。 存储器 22的一部分还可以包括非易失性随机存取存储器 ( NVRAM )。
电子设备 200的各个组件通过总线系统 25耦合在一起, 其中总线系统 25除包括数据总线之外, 还可以包括电源总线、 控制总线和状态信号总线 等。 该总线系统可以是 ISA ( Industry Standard Architecture, 工业标准体系 结构)总线、 PCI ( Peripheral Component Interconnect, 夕卜部设备互连)总线 或 EISA ( Extended Industry Standard Architecture, 扩展工业标准体系结构) 总线等。 所述总线可以是一条或多条物理线路, 当是多条物理线路时可以 分为地址总线、 数据总线、 控制总线等。 在本发明的其它一些实施例中, 处理器 21、 存储器 22以及接收器 23、 发送器 24也可以通过通信线路直接 连接。 但是为了清楚说明起见, 在图中将各种总线都标为总线系统 25。
存储器 22存储了如下的元素, 可执行模块或者数据结构, 或者它们的 子集, 或者它们的扩展集:
操作指令: 包括各种操作指令, 用于实现各种操作。
操作系统: 包括各种系统程序, 用于实现各种基础业务以及处理基于 硬件的任务。
在本发明实施例中, 处理器 21调用存储器 22存储的操作指令(该操 作指令可存储在操作系统中)。
接收器 23用于在建立通话连接后, 接收语音信号。
在第一电子设备与另一电子设备建立通话后, 处理器 21控制接收器 23 接收语音信号。 为了便于描述, 本发明实施例中, 定义电子设备为第一电 子设备, 定义与所述第一电子设备建立通话的另一电子设备为第二电子设 备。
具体实现时, 接收器 23可以是麦克风, 也可以是无线接收器。 当接收 器 23为麦克风时, 这里语音信号是第一电子设备通过麦克风接收到的语音 信号, 当接收器 23是无线接收器时, 语音信号是第一电子设备接收到的第 二电子设备发送的语音信号, 通过第一电子设备的听筒来进行播放。
处理器 21对接收器 23接收的语音信号进行语音识别并进行语义分析得 到语义识别结果, 将语义识别结果与预存的评价语义进行匹配获取音量调 节规则, 根据与音量调节规则自动调节电子设备的音量输出模式。
处理器 21对接收器 23接收到的语音信号进行语音识别得到语音识别结 果, 并进一步对语音识别结果进行语义分析得到语义识别结果。 语义分析 即是从语音识别结果中进行提取出关键字, 进行分析理解得到用户想要表 达的意思, 从而给出语义识别结果。 比如接收来自第一电子设备端的语音 信号为"哎呀, 声音怎么这么小", 语音识别结果即是 "哎呀, 声音怎么这么 小" 。语义分析即是从 "哎呀, 声音怎么这么小" 中提取关键字如 "声音" 、
"小" , 进行分析理解得到语义识别结果可能是"声音太小"。 在进行语义分 析时,可以根据预定规则来进行,比如只要提取的关键字中有"声音" "小", 就认为语义识别结果为 "声音太小" 。 或者是只要提取的关系字中有 "大"
"声音" , 就认为语义识别记过为 "声音太大" 。
在语义识别得到语义识别结果, 处理器 21通过将语义识别结果与预存 的评价语义进行匹配, 评价语义是预存的用于对音量进行评价的。 每个预 存的评价语义分别对应一个音量调节规则。
当语义识别结果与预存的评价语义相匹配, 获取与预存的评价语义对 应的音量调节规则, 处理器 21就按照音量调节规则调节电子设备端的音量 输出模式。
当语音信号是第一电子设备通过麦克风接收到的语音信号时, 预存的 评价语义与音量调节规则的对应关系可参见上表 1 所示, 而当语音信号是 第一电子设备接收到的第二电子设备发送的语音信号时, 预存的评价语义 与音量调节规则的对应关系可参见上表 2所示。
为了便于区分, 可以将两种应用场景下评价语义与音量调节规则的对 应关系分别对应存储在不同的数据库中。 当然, 也可以存储在同一个数据 库中。 在进行匹配的时候, 如果匹配不成功, 不执行音量调节动作。
当然, 以上评价语义与音量调节规则的对应关系, 只是一种举例, 在 能够实现本发明目的的情况下, 也可以釆用其他的对应关系, 这可以根据 使用者的需要自行决定, 本发明对此不作限定。
存储器 22用于存储评价语义。
发送器 24用于对外发送数据。
上述本发明实施例揭示的方法可以应用于处理器 21中, 或者由处理器 21实现。在实现过程中, 上述方法的各步骤可以通过处理器 21中的硬件的 集成逻辑电路或者软件形式的指令完成。 可以实现或者执行本发明实施例 中的公开的各方法、 步骤及逻辑框图。 结合本发明实施例所公开的方法的 步骤可以直接体现为硬件译码处理器执行完成, 或者用译码处理器中的硬 件及软件模块组合执行完成。 软件模块可以位于随机存储器, 闪存、 只读 存储器, 可编程只读存储器或者电可擦写可编程存储器、 寄存器等本领域 成熟的存储介质中。 该存储介质位于存储器 22, 处理器 21读取存储器 22 中的信息, 结合其硬件完成上述方法的步骤。
通过上述实施例的阐述, 本发明实施例提供的自动调节音量的方法及 电子设备, 通过接收语音信号, 识别并进行语义分析得到语义识别结果, 通过语义识别结果与预存的评价语义进行匹配获取音量调节规则, 根据音 量调节规则自动调节电子设备端的音量输出模式。 通过上述方式, 能够基 于语音信号的语义识别结果, 自动进行音量调节, 无需人工干预, 从而避 免通话过程受到影响, 提高通话者的通话体验。
在本发明所提供的几个实施例中, 应该理解到, 所揭露的系统, 装置 和方法, 可以通过其它的方式实现。 例如, 以上所描述的装置实施例仅仅 是示意性的, 例如, 所述模块或单元的划分, 仅仅为一种逻辑功能划分, 实际实现时可以有另外的划分方式, 例如多个单元或组件可以结合或者可 以集成到另一个系统, 或一些特征可以忽略, 或不执行。 另一点, 所显示 或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口, 装 置或单元的间接辆合或通信连接, 可以是电性, 机械或其它的形式。 作为单元显示的部件可以是或者也可以不是物理单元, 即可以位于一个地 方, 或者也可以分布到多个网络单元上。 可以根据实际的需要选择其中的 部分或者全部单元来实现本实施例方案的目的。
另外, 在本发明各个实施例中的各功能单元可以集成在一个处理单元 中, 也可以是各个单元单独物理存在, 也可以两个或两个以上单元集成在 一个单元中。 上述集成的单元既可以釆用硬件的形式实现, 也可以釆用软 件功能单元的形式实现。
所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销 售或使用时, 可以存储在一个计算机可读取存储介质中。 基于这样的理解, 本发明的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方 案的全部或部分可以以软件产品的形式体现出来, 该计算机软件产品存储 在一个存储介质中, 包括若干指令用以使得一台计算机设备(可以是个人 计算机, 服务器, 或者网络设备等)或处理器(processor )执行本发明各个 实施例所述方法的全部或部分步骤。 而前述的存储介质包括: U盘、 移动 硬盘、 只读存储器(ROM, Read-Only Memory )、 随机存取存储器(RAM, Random Access Memory )、 磁碟或者光盘等各种可以存储程序代码的介质。
以上所述仅为本发明的实施例, 并非因此限制本发明的专利范围, 凡 是利用本发明说明书及附图内容所作的等效结构或等效流程变换, 或直接 或间接运用在其他相关的技术领域, 均同理包括在本发明的专利保护范围 内。

Claims

权利要求
1. 一种自动调节音量的方法, 其特征在于, 所述方法包括:
在建立通话连接后, 第一电子设备接收语音信号;
将所述语音信号进行识别并进行语义分析得到语义识别结果; 将所述语义识别结果与预存的评价语义进行匹配获取音量调节规则; 根据所述音量调节规则调节所述电子设备的音量输出模式。
2.根据权利要求 1所述的方法, 其特征在于, 所述语音信号包括所述第 一电子设备通过麦克风接收到的语音信号; 或
所述第一电子设备接收到的第二电子设备发送的语音信号。
3.根据权利要求 2所述的方法, 其特征在于, 当所述语音信号为所述第 一电子设备通过麦克风接收到的语音信号时,
所述预存的评价语义为评价声音太小, 对应的音量调节规则为调高所 述第一电子设备的听筒音量; 或
所述预存的评价语义为评价声音太大, 对应的音量调节规则为降低所 述第一电子设备的听筒音量; 或
所述预存的评价语义为评价所处环境嘈杂时, 对应的音量调节规则为 将所述第一电子设备由听筒输出切换为喇叭输出。
4.根据权利要求 2所述的方法, 其特征在于, 当所述语音信号为所述第 一电子设备接收到的第二电子设备发送的语音信号时,
所述预存的评价语义为评价声音太小, 对应的音量调节规则为调高所 述第一电子设备的麦克风增益以提高麦克风音量; 或
所述预存的评价语义为评价声音太大, 对应的音量调节规则为降低所 述第一电子设备的麦克增益以降低麦克风音量。
5.—种音量调节装置, 其特征在于, 所述音量调节装置包括接收模块、 识别模块、 匹配模块以及音量调节模块, 所述音量调节装置应用于第一电 子设备, 其中:
所述接收模块用于在所述第一电子设备建立通话连接后, 接收语音信 号;
所述识别模块用于将所述接收模块接收的所述语音信号进行识别并进 行语义分析得到语义识别结果;
所述匹配模块用于将所述识别模块识别得到的所述语音识别结果与预 存的评价语义进行匹配获取音量调节规则;
所述音量调节模块用于根据所述匹配模块获取的所述音量调节规则调 节所述电子设备的音量输出模式。
6.根据权利要求 5所述的音量调节装置, 其特征在于, 所述音量调节装 置应用于第一电子设备, 所述语音信号包括所述第一电子设备通过麦克风 接收到的语音信号; 或
所述第一电子设备接收到的第二电子设备发送的语音信号。
7.根据权利要求 6所述的音量调节装置, 其特征在于, 当所述语音信号 为所述第一电子设备通过麦克风接收到的语音信号时,
所述预存的评价语义为评价声音太小, 对应的音量调节规则为调高所 述第一电子设备的听筒音量; 或
所述预存的评价语义为评价声音太大, 对应的音量调节规则为降低所 述第一电子设备的听筒音量; 或
所述预存的评价语义为评价所处环境嘈杂时, 对应的音量调节规则为 将所述第一电子设备由听筒输出切换为喇叭输出。
8.根据权利要求 6所述的电子设备, 其特征在于, 当所述语音信号为所 述第一电子设备接收到的第二电子设备发送的语音信号时,
所述预存的评价语义为评价声音太小, 对应的音量调节规则为调高所 述第一电子设备的麦克风增益以提高麦克风音量; 或
所述预存的评价语义为评价声音太大, 对应的音量调节规则为降低所 述第一电子设备的麦克风增益以降低麦克风音量。
9.一种电子设备, 其特征在于, 所述电子设备包括处理器、 存储器以及 接收器, 所述处理器分别耦接所述存储器以及接收器, 所述电子设备为第 一电子设备, 其中:
所述接收器用于在所述电子设备建立通话连接后, 接收语音信号; 所述处理器对所述接收器接收的所述语音信号进行识别并进行语义分 析得到语义识别结果, 将所述语义识别结果与预存的评价语义进行匹配获 取音量调节规则, 根据所述音量调节规则调节所述电子设备的音量输出模 式;
所述存储器用于存储所述评价语义。
10.根据权利要求 9所述的电子设备, 其特征在于, 所述接收器包括麦克 风或无线接收器,
当所述接收器为所述麦克风时, 所述语音信号为所述第一电子设备通 过所述麦克风接收到的语音信号;
当所述接收器为所述无线接收器时, 所述语音信号为所述第一电子设 备通过所述无线接收器接收到的第二电子设备发送的语音信号。
11.根据权利要求 10所述的电子设备, 其特征在于, 当所述语音信号为 所述第一电子设备通过所述麦克风接收到的语音信号时,
所述预存的评价语义为评价声音太小, 对应的音量调节规则为调高所 述第一电子设备的听筒音量; 或
所述预存的评价语义为评价声音太大, 对应的音量调节规则为降低所 述第一电子设备的听筒音量; 或
所述预存的评价语义为评价所处环境嘈杂时, 对应的音量调节规则为 将所述第一电子设备由听筒输出切换为喇叭输出。
12.根据权利要求 10所述的电子设备, 其特征在于, 当所述语音信号所 述第一电子设备接收到的第二电子设备发送的语音信号时,
所述预存的评价语义为评价声音太小, 对应的音量调节规则为调高所 述第一电子设备的所述麦克风增益以提高所述麦克风音量; 或
所述预存的评价语义为评价声音太大, 对应的音量调节规则为降低所 述第一电子设备的所述麦克风增益以降低所述麦克风音量。
PCT/CN2014/074821 2014-04-04 2014-04-04 一种自动调节音量的方法、音量调节装置及电子设备 WO2015149359A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
CN201480001379.6A CN104335559B (zh) 2014-04-04 2014-04-04 一种自动调节音量的方法、音量调节装置及电子设备
PCT/CN2014/074821 WO2015149359A1 (zh) 2014-04-04 2014-04-04 一种自动调节音量的方法、音量调节装置及电子设备
EP14888498.4A EP3110116B1 (en) 2014-04-04 2014-04-04 Method for automatically adjusting volume, volume adjustment apparatus and electronic device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2014/074821 WO2015149359A1 (zh) 2014-04-04 2014-04-04 一种自动调节音量的方法、音量调节装置及电子设备

Publications (1)

Publication Number Publication Date
WO2015149359A1 true WO2015149359A1 (zh) 2015-10-08

Family

ID=52408647

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2014/074821 WO2015149359A1 (zh) 2014-04-04 2014-04-04 一种自动调节音量的方法、音量调节装置及电子设备

Country Status (3)

Country Link
EP (1) EP3110116B1 (zh)
CN (1) CN104335559B (zh)
WO (1) WO2015149359A1 (zh)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190141428A1 (en) * 2016-06-03 2019-05-09 Nova Products Gmbh EAR JEWELRY WITH INTEGRATED HEADSET (as-amended)
CN111724774A (zh) * 2019-03-22 2020-09-29 阿里巴巴集团控股有限公司 语音交互及车载语音交互方法、装置、设备及存储介质
CN112185369A (zh) * 2019-07-04 2021-01-05 百度在线网络技术(北京)有限公司 一种基于语音控制的音量调节方法、装置、设备和介质
CN113223519A (zh) * 2021-04-23 2021-08-06 深圳创维-Rgb电子有限公司 远场音量控制方法、设备、存储介质及计算机程序产品
CN113488024A (zh) * 2021-05-31 2021-10-08 杭州摸象大数据科技有限公司 一种基于语义识别的电话打断识别方法和系统

Families Citing this family (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105825854B (zh) * 2015-10-19 2019-12-03 维沃移动通信有限公司 一种语音信号处理方法、装置及移动终端
CN105657165A (zh) * 2015-12-30 2016-06-08 广东欧珀移动通信有限公司 一种通话音量的调节方法及装置
CN105609104A (zh) * 2016-01-22 2016-05-25 北京云知声信息技术有限公司 一种信息处理方法、装置及智能语音路由控制器
CN106201426B (zh) * 2016-07-14 2019-04-02 北京元心科技有限公司 音量控制的方法及装置
CN107785013A (zh) * 2016-08-24 2018-03-09 中兴通讯股份有限公司 语音控制方法及装置
CN106506809A (zh) * 2016-10-11 2017-03-15 合网络技术(北京)有限公司 一种基于通话内容自动调节音量的方法、系统及设备
CN108702411B (zh) 2017-03-21 2021-12-14 华为技术有限公司 一种控制通话的方法、终端及计算机可读存储介质
CN106782544A (zh) * 2017-03-29 2017-05-31 联想(北京)有限公司 语音交互设备及其输出方法
CN107395849B (zh) * 2017-08-09 2021-09-07 维沃移动通信有限公司 一种通话方法、移动终端及计算机可读存储介质
CN107968969B (zh) * 2017-09-13 2019-08-20 深圳中泰智丰物联网科技有限公司 一种用户语音的响应方法、装置及终端设备
CN108076226B (zh) * 2017-12-22 2020-08-21 Oppo广东移动通信有限公司 一种通话质量调整的方法、移动终端及存储介质
CN108419109A (zh) * 2018-03-06 2018-08-17 杭州政信金服互联网科技有限公司 一种会议直播声音调节方法和系统
CN110738995B (zh) * 2019-10-11 2022-11-11 北京地平线机器人技术研发有限公司 一种声音信号采集方法及装置

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1952541A (zh) * 2005-10-21 2007-04-25 乐金电子(天津)电器有限公司 可通过用户的语音信号控制电视操作的冰箱
CN202889458U (zh) * 2012-11-02 2013-04-17 姚西 一种根据环境噪声自动调节通话音量的手机
CN103369112A (zh) * 2012-03-30 2013-10-23 富泰华工业(深圳)有限公司 模式管理系统及其管理方法
CN103685757A (zh) * 2013-12-19 2014-03-26 闻泰通讯股份有限公司 手机语音通话控制系统及方法

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100345537B1 (ko) * 1999-07-27 2002-07-26 삼성전자 주식회사 휴대폰의 송수화음 및 키톤 레벨조절방법
JP2004013084A (ja) * 2002-06-11 2004-01-15 Sharp Corp 音量制御装置
JP4654651B2 (ja) * 2004-10-13 2011-03-23 トヨタ自動車株式会社 車載ハンズフリー通話システム
US20110044474A1 (en) * 2009-08-19 2011-02-24 Avaya Inc. System and Method for Adjusting an Audio Signal Volume Level Based on Whom is Speaking
US9380142B2 (en) * 2011-10-07 2016-06-28 Nokia Technologies Oy Framework for user-created device applications
KR101467519B1 (ko) * 2011-11-21 2014-12-02 주식회사 케이티 음성 정보를 이용한 컨텐츠 검색 서버 및 방법
US9099972B2 (en) * 2012-03-13 2015-08-04 Motorola Solutions, Inc. Method and apparatus for multi-stage adaptive volume control
CN102710838B (zh) * 2012-04-25 2015-01-21 华为技术有限公司 一种音量调节方法及装置、电子设备
CN102915753B (zh) * 2012-10-23 2015-09-30 华为终端有限公司 一种电子设备的智能控制音量的方法及实现装置
CN103973870B (zh) * 2013-01-28 2017-02-08 联想(北京)有限公司 信息处理设备和信息处理方法
CN103200329A (zh) * 2013-04-10 2013-07-10 威盛电子股份有限公司 语音操控方法、移动终端装置及语音操控系统

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1952541A (zh) * 2005-10-21 2007-04-25 乐金电子(天津)电器有限公司 可通过用户的语音信号控制电视操作的冰箱
CN103369112A (zh) * 2012-03-30 2013-10-23 富泰华工业(深圳)有限公司 模式管理系统及其管理方法
CN202889458U (zh) * 2012-11-02 2013-04-17 姚西 一种根据环境噪声自动调节通话音量的手机
CN103685757A (zh) * 2013-12-19 2014-03-26 闻泰通讯股份有限公司 手机语音通话控制系统及方法

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190141428A1 (en) * 2016-06-03 2019-05-09 Nova Products Gmbh EAR JEWELRY WITH INTEGRATED HEADSET (as-amended)
US10993015B2 (en) * 2016-06-03 2021-04-27 Nova Products Gmbh Ear jewelry with integrated headset
CN111724774A (zh) * 2019-03-22 2020-09-29 阿里巴巴集团控股有限公司 语音交互及车载语音交互方法、装置、设备及存储介质
CN111724774B (zh) * 2019-03-22 2024-05-17 斑马智行网络(香港)有限公司 语音交互及车载语音交互方法、装置、设备及存储介质
CN112185369A (zh) * 2019-07-04 2021-01-05 百度在线网络技术(北京)有限公司 一种基于语音控制的音量调节方法、装置、设备和介质
CN112185369B (zh) * 2019-07-04 2024-04-26 百度在线网络技术(北京)有限公司 一种基于语音控制的音量调节方法、装置、设备和介质
CN113223519A (zh) * 2021-04-23 2021-08-06 深圳创维-Rgb电子有限公司 远场音量控制方法、设备、存储介质及计算机程序产品
CN113223519B (zh) * 2021-04-23 2024-06-04 深圳创维-Rgb电子有限公司 远场音量控制方法、设备、存储介质及计算机程序产品
CN113488024A (zh) * 2021-05-31 2021-10-08 杭州摸象大数据科技有限公司 一种基于语义识别的电话打断识别方法和系统
CN113488024B (zh) * 2021-05-31 2023-06-23 杭州摸象大数据科技有限公司 一种基于语义识别的电话打断识别方法和系统

Also Published As

Publication number Publication date
CN104335559A (zh) 2015-02-04
EP3110116B1 (en) 2019-09-25
CN104335559B (zh) 2018-06-05
EP3110116A1 (en) 2016-12-28
EP3110116A4 (en) 2017-03-22

Similar Documents

Publication Publication Date Title
WO2015149359A1 (zh) 一种自动调节音量的方法、音量调节装置及电子设备
WO2016184119A1 (zh) 一种音量调节方法、系统、设备和计算机存储介质
US10079014B2 (en) Name recognition system
CN109961780B (zh) 一种人机交互方法、装置、服务器和存储介质
WO2016165590A1 (zh) 语音翻译方法及装置
US10270736B2 (en) Account adding method, terminal, server, and computer storage medium
US10178228B2 (en) Method and apparatus for classifying telephone dialing test audio based on artificial intelligence
WO2017031846A1 (zh) 噪声消除、语音识别方法、装置、设备及非易失性计算机存储介质
WO2021135604A1 (zh) 语音控制方法、装置、服务器、终端设备及存储介质
KR102265931B1 (ko) 음성 인식을 이용하는 통화 수행 방법 및 사용자 단말
US10204639B2 (en) Method and device for processing sound signal for communications device
CN102117614A (zh) 个性化文本语音合成和个性化语音特征提取
US20150229756A1 (en) Device and method for authenticating a user of a voice user interface and selectively managing incoming communications
CN103841272A (zh) 一种发送语音消息的方法及装置
WO2020103447A1 (zh) 视频信息链式存储方法、装置、计算机设备及存储介质
US8868419B2 (en) Generalizing text content summary from speech content
TW201903755A (zh) 可調整輸出聲音之電子裝置及調整輸出聲音之方法
CN111681650A (zh) 一种智能会议控制方法和装置
CN113176870B (zh) 音量调整方法、装置、电子设备及存储介质
WO2017166495A1 (zh) 一种语音信号处理方法及装置
CN107948854B (zh) 一种操作音频生成方法、装置、终端及计算机可读介质
KR101595090B1 (ko) 음성 인식을 이용한 정보 검색 방법 및 장치
CN107977187B (zh) 一种混响调节方法及电子设备
US20200285815A1 (en) Speech translation terminal, mobile terminal, translation system, translation method, and translation device
CN110232919A (zh) 实时语音流提取与语音识别系统及方法

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: 14888498

Country of ref document: EP

Kind code of ref document: A1

REEP Request for entry into the european phase

Ref document number: 2014888498

Country of ref document: EP

WWE Wipo information: entry into national phase

Ref document number: 2014888498

Country of ref document: EP

NENP Non-entry into the national phase

Ref country code: DE