WO2017161741A1 - 聋哑人进行信息交流的方法、装置及智能终端 - Google Patents

聋哑人进行信息交流的方法、装置及智能终端 Download PDF

Info

Publication number
WO2017161741A1
WO2017161741A1 PCT/CN2016/088485 CN2016088485W WO2017161741A1 WO 2017161741 A1 WO2017161741 A1 WO 2017161741A1 CN 2016088485 W CN2016088485 W CN 2016088485W WO 2017161741 A1 WO2017161741 A1 WO 2017161741A1
Authority
WO
WIPO (PCT)
Prior art keywords
sign language
gesture
voice signal
library
matching
Prior art date
Legal status (The legal status 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 status listed.)
Ceased
Application number
PCT/CN2016/088485
Other languages
English (en)
French (fr)
Inventor
赵永贵
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Le Holdings Beijing Co Ltd
Leshi Zhixin Electronic Technology Tianjin Co Ltd
Original Assignee
Le Holdings Beijing Co Ltd
Leshi Zhixin Electronic Technology Tianjin Co Ltd
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 Le Holdings Beijing Co Ltd, Leshi Zhixin Electronic Technology Tianjin Co Ltd filed Critical Le Holdings Beijing Co Ltd
Publication of WO2017161741A1 publication Critical patent/WO2017161741A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

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
    • G10L15/08—Speech classification or search
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/5866—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures

Definitions

  • the embodiments of the present invention relate to the technical field of intelligent terminals, and in particular, to a method, device, and intelligent terminal for information exchange between deaf and dumb people.
  • Mobile phones as an important and popular communication tool in modern times, especially the arrival of mobile Internet technology, have made the traditional mobile phone function machine has been replaced by a smart machine with powerful data processing functions.
  • the intelligent machine can also rely on the mobile Internet for information acquisition and information exchange.
  • the smartphone For most users who have no language and hearing impairments, the smartphone is very convenient for information acquisition and communication, and can be used without barriers.
  • the inventors have found that at least the following problems exist in the prior art: for a deaf-mute person with language and hearing impairment, when the information is exchanged, the standard language cannot be listened to because of the inability to pronounce normally. It can be carried out by sending and receiving text messages. Therefore, the performance of the mobile phone is not fully utilized, and the convenience provided by the deaf-mute people in information exchange is poor.
  • the purpose of the embodiments of the present application is to provide a method, a device, and an intelligent terminal for communicating information with a deaf person, which are used to solve the defect that the performance of the smart terminal is not fully exerted when the deaf-mute person performs information exchange in the prior art, and is enhanced.
  • Deaf-mute people use smart terminals for information exchange convenience.
  • the embodiment of the present application provides a method for information exchange with a deaf person, which includes:
  • the presentation selects standard sign language information corresponding to the voice signal from the sign language library.
  • the receiving a voice signal, and matching the voice signal in a pre-established sign language library includes:
  • selecting, according to a matching result of the voice signal in a pre-established sign language library, selecting standard sign language information corresponding to the voice signal from the sign language library includes:
  • the presenting that selecting the standard sign language information corresponding to the voice signal from the sign language library includes:
  • the displaying, by using the sign language library, the standard sign language information that matches the digital signal corresponding to the voice signal comprises: graphically displaying the selection from the sign language library The standard sign language information matched by the digital signal corresponding to the voice signal.
  • the method further includes: determining whether to start the hoarse interaction, and if yes, performing the receiving of the standard voice signal; otherwise, ending.
  • the embodiment of the present application provides a computer readable recording medium on which a program for executing the above method is recorded.
  • the embodiment of the present application provides a method for information exchange with a deaf person, which includes:
  • Each of the sign language gesture images in the opponent gesture image sequence performs gesture feature recognition and positioning
  • the capturing a sign language gesture and collecting the captured sign language gesture to form a sign language gesture image sequence includes:
  • the sign language gesture is captured and the captured sign language gesture is captured, a sequence of sign language gesture images is formed, and the sequence of sign language gesture images is converted into a digital signal.
  • the matching and the located gesture feature are matched in the sign language library to generate a digital signal:
  • a matching and generating a speech signal is performed in the sign language library according to the recognized and positioned gesture feature on the digital signal corresponding to the sign language gesture image.
  • performing gesture feature recognition and positioning for each of the sign language gesture images in the sequence of hand gesture gesture images includes:
  • Each sign language gesture image gesture decomposition in the opponent gesture image sequence is performed, and gesture feature recognition and positioning are performed on the gesture-decomposed sign language gesture image.
  • the method further includes: determining whether to start the hoarse interaction, and if yes, performing the capturing of the start sign language gesture; otherwise, ending.
  • the embodiment of the present application provides a computer readable recording medium on which a program for executing the above method is recorded.
  • An embodiment of the present application provides an apparatus for performing information exchange with a deaf person, including:
  • a receiving module configured to receive a voice signal, and match the voice signal in a pre-established sign language library
  • a matching module configured to select a standard sign language information corresponding to the voice signal from the sign language library according to a matching result of the voice signal in a pre-established sign language library;
  • a presentation module configured to present, from the sign language library, select standard sign language information corresponding to the voice signal.
  • the embodiment of the present application provides a method for information exchange with a deaf person, which includes:
  • An acquisition module configured to capture a sign language gesture and collect the captured sign language gesture to form a sequence of sign language gesture images
  • a positioning module configured to perform gesture feature recognition and positioning for each of the sign language gesture images in the sequence of hand gesture gesture images
  • a matching module configured to perform in the sign language library based on the recognized and positioned gesture features Equipped with a digital signal
  • a sending module configured to send a digital signal generated based on a matching result in the sign language library.
  • An embodiment of the present application provides an intelligent terminal, including a presentation module and a hardware processor, where the hardware processor is configured to receive a voice signal, and match the voice signal in a pre-established sign language library; a matching result of the speech signal in the sign language library, and selecting standard sign language information corresponding to the speech signal from the sign language library; the rendering module is configured to present a selection from the sign language library to correspond to the speech signal Standard sign language information.
  • the embodiment of the present application provides a smart terminal, including a camera, a hardware processor, and a radio frequency module, where the camera captures a sign language gesture and collects the captured sign language gesture to form a sign language gesture image sequence; the hardware processor is configured as a hand gesture Each of the sign language gesture images in the image sequence performs gesture feature recognition and positioning; and generates a digital signal according to the identified and positioned gesture features in the sign language library; the radio frequency module is configured to send the generated according to the matching result in the sign language library. Digital signal.
  • FIG. 1 is a schematic flow chart of a method for information exchange with a deaf person according to Embodiment 1 of the present application;
  • FIG. 2 is a schematic flowchart of a method for performing information exchange with a deaf person according to Embodiment 2 of the present application;
  • FIG. 3 is a schematic structural diagram of an apparatus for performing information exchange with a deaf person according to Embodiment 3 of the present application;
  • FIG. 4 is a schematic structural diagram of an apparatus for performing information exchange with a deaf person according to Embodiment 4 of the present application;
  • FIG. 5 is a schematic structural diagram of a fifth intelligent terminal according to Embodiment 5 of the present application.
  • FIG. 6 is a schematic structural diagram of a smart terminal according to Embodiment 6 of the present application.
  • the voice signal is matched in a pre-established sign language library, and standard sign language information corresponding to the voice signal is selected from the sign language library, so that the voice signal can be corresponding to the voice signal.
  • the standard sign language information is presented to the deaf person as the receiver; or, the sign language gesture is captured and the captured sign language gesture is captured to form a sequence of sign language gesture images, and the gesture feature recognition and positioning is performed for each sign language gesture image and matched in the sign language library.
  • the voice signal is generated to generate a voice signal, and the sign language of the deaf person is presented to the receiver's non-listening and language-disabled users, thereby realizing the information interaction between the two parties, and overcoming the performance of the smart terminal when the deaf-mute person performs information exchange.
  • the defects have enhanced the convenience of deaf-mute people using intelligent terminals for information exchange.
  • the smart terminal may include a smart phone, and may also include a smart tablet, a smart TV, a smart bracelet, and the like.
  • FIG. 1 is a schematic flow chart of a method for information exchange with a deaf person according to Embodiment 1 of the present application; in this embodiment, a user without language and hearing impairment calls a deaf-mute person with language and hearing impairment as an example, and the calling party is For users without language and hearing impairment, the listener is a deaf person with language and hearing impairment.
  • This embodiment describes the technical solution from the listener side. As shown in Figure 1, it includes:
  • S101 Receive a voice signal, and match the voice signal in a pre-established sign language library.
  • the speech signal is from a user without language and hearing impairment
  • the sign language library includes standard sign language information.
  • the sign language library is established by standardizing all the sign language used by the deaf person in daily use. Specifically, it is possible to collect sign language systems used by different countries or regions, such as the "vocabulary sign language” in the United States and the "scrabble sign language” in China, and an independent sign language library can be established for different sign language systems.
  • the sign language library is built specifically, the sign language model of different sign language in different sign language systems can be determined first, based on the comparison of the speech signal and the different sign language models, so as to achieve the matching process.
  • the receiving the voice signal in step S101, and matching the voice signal in the pre-established sign language library may specifically include: receiving the voice signal, converting the voice signal into The digital signal matches the digital signal corresponding to the voice signal in a pre-established sign language library.
  • the matching process implements a process of determining the correspondence between the speech signal and the standardized sign language in the sign language library.
  • the sign language system and the sign language system may be first determined.
  • the corresponding sign language library searches for a standardized sign language corresponding to the voice signal in the determined sign language library. Specifically, since in the sign language library, each sign language pattern can be matched to a corresponding binary code, a corresponding speech signal is generated according to the binary code.
  • the selecting the standard sign language information corresponding to the voice signal from the sign language library according to the matching result of the voice signal in the pre-established sign language library comprises: And matching the digital signal corresponding to the voice signal, and selecting standard sign language information matching the digital signal corresponding to the voice signal from the sign language library.
  • the presentation selects standard sign language information corresponding to the voice signal from the sign language library.
  • the presenting that selecting the standard sign language information corresponding to the voice signal from the sign language library comprises: displaying standard sign language information that matches a digital signal corresponding to the voice signal from the sign language library.
  • the displaying, by using the sign language library, the standard sign language information that matches the digital signal corresponding to the voice signal comprises: graphically displaying, selecting, from the sign language library, a digital signal matching corresponding to the voice signal Standard sign language information.
  • sign language can be graphically displayed on the display of the smart terminal.
  • the method further includes: determining whether to start the hoarse interaction, and if yes, performing the receiving of the standard voice signal; otherwise, ending.
  • a quick start button can be set on the smart terminal, and the trigger of the quick start button is used to determine whether the deaf mode is activated.
  • an APP may be created according to the method described in FIG. 1 above, and the APP is installed and started on the smart terminal.
  • the above voice signals may include signals transmitted through a carrier network such as GSM/CDMA, and may also include signals transmitted through the mobile Internet, such as by WeChat.
  • the embodiment of the present application provides a computer readable recording medium on which a program for executing the above method is recorded.
  • the computer readable recording medium includes any mechanism for storing or transmitting information in a form readable by a computer (eg, a computer).
  • a machine-readable medium includes read only memory (ROM), random access memory (RAM), magnetic disk storage media, optical storage media, flash storage media, electrical, optical, acoustic, or other forms of propagation signals (eg, carrier waves) , infrared signals, digital signals, etc.).
  • FIG. 2 is a schematic flowchart of a method for exchanging information with a deaf person according to a second embodiment of the present application; in this embodiment, a user with language and hearing impairment dials a telephone to a deaf-mute person without language and hearing impairment as an example, and the calling party is For users with language and hearing impairments, the listener is a deaf person with no language and hearing impairment.
  • This embodiment describes the technical solution from the listener side. As shown in Figure 2, it includes:
  • the smart terminal is configured with a front or rear camera.
  • the camera captures and collects the sign language gesture to form the gesture image. Sequence, including gesture images at successive points in time.
  • the capturing the sign language gesture and collecting the captured sign language gesture to form the sign language gesture image sequence in step S201 includes:
  • the sign language gesture is captured and the captured sign language gesture is captured, a sequence of sign language gesture images is formed, and the sequence of sign language gesture images is converted into a digital signal.
  • performing gesture feature recognition and positioning on each of the sign language gesture images in the sequence of the opponent gesture image in step S202 includes:
  • Each sign language gesture image gesture decomposition in the opponent gesture image sequence is performed, and gesture feature recognition and positioning are performed on the gesture-decomposed sign language gesture image.
  • the invariant features on the finger include at least: a shape , skin color, texture, edge information.
  • an annotated speech signal is established in the gesture library.
  • the sign language system and the sign language library corresponding to the sign language system can be determined first. , find in the identified sign language library A standard speech signal corresponding to a sign language signal.
  • the matching and the located gesture feature are matched in the sign language library to generate a digital signal:
  • a matching and generating a speech signal is performed in the sign language library according to the recognized and positioned gesture feature on the digital signal corresponding to the sign language gesture image.
  • the matched voice signal is sent to the receiver, and played on the receiving terminal.
  • the method may further include: determining whether to start the hoarse interaction, and if yes, performing the capturing of the startup sign language gesture; otherwise, ending.
  • a quick start button can be set on the smart terminal, and the trigger of the quick start button is used to determine whether the deaf mode is activated.
  • an APP may be created according to the method described in FIG. 1 above, and the APP is installed and started on the smart terminal.
  • the above voice signals may include signals transmitted through a carrier network such as GSM/CDMA, and may also include signals transmitted through the mobile Internet, such as by WeChat.
  • step S201 may be performed on the sender side, and steps S202-204 may be performed on the receiver side.
  • the embodiment of the present application provides a computer readable recording medium on which a program for executing the above method is recorded.
  • the computer readable recording medium includes any mechanism for storing or transmitting information in a form readable by a computer (eg, a computer).
  • a machine-readable medium includes read only memory (ROM), random access memory (RAM), magnetic disk storage media, optical storage media, flash storage media, electrical, optical, acoustic, or other forms of propagation signals (eg, carrier waves) , infrared signals, digital signals, etc.).
  • FIG. 3 is a schematic structural diagram of an apparatus for performing information exchange with a deaf person according to Embodiment 3 of the present application; as shown in FIG. 3, the method includes:
  • the receiving module 301 is configured to receive a voice signal, and match the voice signal in a pre-established sign language library;
  • the matching module 302 is configured to select a standard sign language information corresponding to the voice signal from the sign language library according to a matching result of the voice signal in a pre-established sign language library;
  • the presentation module 303 is configured to present, from the sign language library, select standard sign language information corresponding to the voice signal.
  • the receiving module is further configured to receive a voice signal, convert the voice signal into a digital signal, and match the digital signal corresponding to the voice signal in a pre-established sign language library.
  • the matching module is further configured to select, according to a matching result of the digital signal corresponding to the voice signal, a digital signal corresponding to the voice signal from the sign language library. Standard sign language information.
  • the presentation module is further configured to display standard sign language information that matches a digital signal corresponding to the voice signal from the sign language library.
  • the presentation module is further configured to graphically display, from the sign language library, standard sign language information that matches a digital signal corresponding to the voice signal.
  • the method further includes: a determining module configured to determine whether to initiate the deaf-mute interaction, and if yes, executing the initiating receiving module to receive the standard voice signal; otherwise, ending.
  • FIG. 4 is a schematic structural diagram of an apparatus for performing information exchange with a deaf person according to Embodiment 4 of the present application; as shown in FIG. 4, the method includes:
  • the acquiring module 401 is configured to capture a sign language gesture and collect the captured sign language gesture to form a sequence of sign language gesture images;
  • the positioning module 402 is configured to perform gesture feature recognition and positioning for each of the sign language gesture images in the sequence of hand gesture gesture images;
  • the matching module 403 is configured to generate a digital signal by matching in the sign language library according to the recognized and located gesture features;
  • Sending module 404 configured to send a digital letter generated according to a matching result in the sign language library number.
  • the collection module 401 is further configured to capture a sign language gesture and collect the captured sign language gesture to form a sign language gesture image sequence, and convert the sign language gesture image sequence into a digital signal.
  • the matching module 403 is further configured to perform matching to generate a voice signal in the sign language library according to the digital signal on the corresponding sign language gesture image according to the recognized and located gesture feature.
  • the positioning module 402 is further configured to decompose each of the sign language gesture image gestures in the sequence of hand gesture gesture images, and perform gesture feature recognition and positioning on the gesture-decomposed sign language gesture image.
  • the method further includes a judging module (not shown) configured to determine whether to start the deaf-mute interaction, and if so, initiating the acquisition module to capture the sign language gesture; otherwise, ending.
  • a judging module (not shown) configured to determine whether to start the deaf-mute interaction, and if so, initiating the acquisition module to capture the sign language gesture; otherwise, ending.
  • the smart terminal 500 includes a presentation module 501 and a hardware processor 502, and the hardware processor 502 is configured to receive a voice signal in a pre-established sign language library. Matching the voice signal; and selecting standard sign language information corresponding to the voice signal from the sign language library according to a matching result of the voice signal in a pre-established sign language library; the presentation module 501 is configured The standard sign language information corresponding to the voice signal is selected from the sign language library for presentation.
  • the camera 601 may include a camera 601, a hardware processor 602, and a radio frequency module 603.
  • the camera 601 captures a sign language gesture and collects the captured sign language gesture to form a sign language. a sequence of gesture images;
  • the hardware processor 602 is configured to perform gesture feature recognition and positioning for each of the sign language gesture images in the sequence of hand gesture gesture images, and generate a digital signal by matching in the sign language library according to the recognized and positioned gesture features.
  • the gesture library includes a standard voice signal;
  • the radio frequency module 603 is configured to transmit a digital signal generated according to a matching result in the sign language library.
  • the camera can be replaced by a handwriting screen of the smart terminal for capturing a sign language gesture and collecting the captured sign language gesture to form a sequence of sign language gesture images, which are not illustrated in detail.
  • the device embodiments described above are merely illustrative, wherein the modules described as separate components may or may not be physically separate, and the components displayed as modules may or may not be physical modules, ie may be located A place, or it can be distributed to multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the embodiment. Those of ordinary skill in the art can understand and implement without deliberate labor.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • Multimedia (AREA)
  • Acoustics & Sound (AREA)
  • Human Computer Interaction (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Databases & Information Systems (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Library & Information Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Computation (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Telephonic Communication Services (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

一种聋哑人进行信息交流的方法、装置及智能终端，其中一方法包括：接收语音信号，在预先建立的手语库中对所述语音信号进行匹配（S101）；根据在预先建立的手语库中对所述语音信号的匹配结果，从所述手语库中选择与所述语音信号对应标准手语信息（S102）；以及呈现从所述手语库中选择与所述语音信号对应标准手语信息（S103）。通过在预先建立的手语库中对所述语音信号进行匹配，从所述手语库中选择与所述语音信号对应标准手语信息，从而可以将与所述语音信号对应标准手语信息展现给作为接收方的聋哑人，从而克服了聋哑人在进行信息交流时智能终端性能没有充分发挥的缺陷，增强了聋哑人利用智能终端进行信息交流的便捷性。

Description

聋哑人进行信息交流的方法、装置及智能终端
本申请要求于2016年3月23日提交中国专利局、申请号为201610168501.X，发明名称为“一种聋哑人进行信息交流的方法、装置及智能终端”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请实施例涉及智能终端技术领域，尤其涉及一种聋哑人进行信息交流的方法、装置及智能终端。
背景技术
手机作为现代重要而普及的交流工具，尤其是移动互联网技术的到来，使得传统意义上的手机即功能机已经被逐渐的具有强大数据处理功能的智能机代替。智能机除了可以实现传统手机的基本通信功能比如发短信、打电话等，还可以依托于移动互联网进行信息获取以及信息交流。
对于大多数无语言和听觉障碍的用户来说，智能手机极大的方便了信息的获取和交流，可以无障碍的进行使用。在实现本申请过程中，发明人发现现有技术中至少存在如下问题：对于有语言和听觉障碍的聋哑人来说，在进行信息交流时，由于无法正常发音，无法收听标准的语言，只能通过收发短信来进行，因此，使得手机的性能没有充分的发挥，对聋哑人在信息交流时提供的便捷性较差。
发明内容
本申请实施例的目的在于提供一种与聋哑人进行信息交流的方法、装置及智能终端，用以解决现有技术中聋哑人在进行信息交流时智能终端性能没有充分发挥的缺陷，增强聋哑人利用智能终端进行信息交流的便捷性。
本申请实施例采用的技术方案如下：
本申请实施例提供一种与聋哑人进行信息交流的方法，其包括：
接收语音信号，在预先建立的手语库中对所述语音信号进行匹配；
根据在预先建立的手语库中对所述语音信号的匹配结果，从所述手 语库中选择与所述语音信号对应标准手语信息；
呈现从所述手语库中选择与所述语音信号对应标准手语信息。
具体地，在本申请的一实施例中，所述接收语音信号，在预先建立的手语库中对所述语音信号进行匹配包括：
接收语音信号，将所述语音信号转换成数字信号，在预先建立的手语库中对所述语音信号对应的数字信号进行匹配。
具体地，在本申请的一实施例中，所述根据在预先建立的手语库中对所述语音信号的匹配结果，从所述手语库中选择与所述语音信号对应标准手语信息包括：
根据对所述语音信号对应的数字信号的匹配结果，从所述手语库中选择与所述语音信号对应的数字信号匹配的标准手语信息。
具体地，在本申请的一实施例中，所述呈现从所述手语库中选择与所述语音信号对应标准手语信息包括：
显示从所述手语库中选择与所述语音信号对应的数字信号匹配的标准手语信息。
具体地，在本申请的一实施例中，所述显示从所述手语库中选择与所述语音信号对应的数字信号匹配的标准手语信息包括：以图形方式显示从所述手语库中选择与所述语音信号对应的数字信号匹配的标准手语信息。
具体地，在本申请的一实施例中，还包括：判断是否启动聋哑交互，如果是，则执行启动标准语音信号的接收；否则，结束。
本申请实施例提供一种在其上记录有用于执行上述方法的程序的计算机可读记录介质。
本申请实施例提供一种与聋哑人进行信息交流的方法，其包括：
捕获手语手势并采集捕获到的手语手势形成手语手势图像序列；
对手语手势图像序列中每个手语手势图像进行手势特征识别和定位；
根据识别和定位到的手势特征在手语库中进行匹配生成数字信号；
发送根据在手语库中匹配结果生成的数字信号。
具体地，在本申请的一实施例中，所述捕获手语手势并采集捕获到的手语手势形成手语手势图像序列包括：
捕获手语手势并采集捕获到的手语手势，形成手语手势图像序列，将所述手语手势图像序列转换成数字信号。
具体地，在本申请的一实施例中，所述根据识别和定位到的手势特征在手语库中进行匹配生成数字信号：
根据识别和定位到的手势特征在对应手语手势图像上的数字信号，在手语库中进行匹配生成语音信号。
具体地，在本申请的一实施例中，所述对手语手势图像序列中每个手语手势图像进行手势特征识别和定位包括：
对手语手势图像序列中每个手语手势图像手势分解，在手势分解了的手语手势图像上进行手势特征识别和定位。
具体地，在本申请的一实施例中，还包括：判断是否启动聋哑交互，如果是，则执行启动手语手势的捕获；否则，结束。
本申请实施例提供一种在其上记录有用于执行上述方法的程序的计算机可读记录介质。
本申请实施例提供一种与聋哑人进行信息交流的装置，其包括：
接收模块，配置为接收语音信号，在预先建立的手语库中对所述语音信号进行匹配；
匹配模块，配置为根据在预先建立的手语库中对所述语音信号的匹配结果，从所述手语库中选择与所述语音信号对应标准手语信息；
呈现模块，配置为呈现从所述手语库中选择与所述语音信号对应标准手语信息。
本申请实施例提供一种与聋哑人进行信息交流的方法，其包括：
采集模块，配置为捕获手语手势并采集捕获到的手语手势形成手语手势图像序列；
定位模块，配置为对手语手势图像序列中每个手语手势图像进行手势特征识别和定位；
匹配模块，配置为根据识别和定位到的手势特征在手语库中进行匹 配生成数字信号；
发送模块，配置为发送根据在手语库中匹配结果生成的数字信号。
本申请实施例提供一种智能终端，其包括呈现模块以及硬件处理器，所述硬件处理器配置为接收语音信号，在预先建立的手语库中对所述语音信号进行匹配；以及根据在预先建立的手语库中对所述语音信号的匹配结果，从所述手语库中选择与所述语音信号对应标准手语信息；所述呈现模块配置为呈现从所述手语库中选择与所述语音信号对应标准手语信息。
本申请实施例提供一种智能终端，其包括摄像头、硬件处理器以及射频模块，所述摄像头捕获手语手势并采集捕获到的手语手势形成手语手势图像序列；所述硬件处理器配置为对手语手势图像序列中每个手语手势图像进行手势特征识别和定位；以及根据识别和定位到的手势特征在手语库中进行匹配生成数字信号；所述射频模块配置为发送根据在手语库中匹配结果生成的数字信号。
本申请实施例的技术方案具有以下优点：
通过在预先建立的手语库中对所述语音信号进行匹配，从所述手语库中选择与所述语音信号对应标准手语信息，从而可以将与所述语音信号对应标准手语信息展现给作为接收方的聋哑人；或者，捕获手语手势并采集捕获到的手语手势形成手语手势图像序列，对每个手语手势图像进行手势特征识别和定位并在手语库中进行匹配生成语音信号从而生成语音信号，将聋哑人的手语展现给接收方的无听力和语言障碍用户，从而实现了双方的信息交互，克服了聋哑人在进行信息交流时智能终端性能没有充分发挥的缺陷，增强了聋哑人利用智能终端进行信息交流的便捷性。
附图说明
为了更清楚地说明本申请实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作一简单地介绍，显而易见地，下面描述中的附图是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其 他的附图。
图1为本申请实施例一与聋哑人进行信息交流的方法流程示意图；
图2为本申请实施例二与聋哑人进行信息交流的方法流程示意图；
图3为本申请实施例三与聋哑人进行信息交流的装置结构示意图；
图4为本申请实施例四与聋哑人进行信息交流的装置结构示意图；
图5为本申请实施例五智能终端结构示意图；
图6为本申请实施例六智能终端结构示意图。
具体实施方式
为使本申请实施例的目的、技术方案和优点更加清楚，下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
本申请下述实施例中，通过在预先建立的手语库中对所述语音信号进行匹配，从所述手语库中选择与所述语音信号对应标准手语信息，从而可以将与所述语音信号对应标准手语信息展现给作为接收方的聋哑人；或者，捕获手语手势并采集捕获到的手语手势形成手语手势图像序列，对每个手语手势图像进行手势特征识别和定位并在手语库中进行匹配生成语音信号从而生成语音信号，将聋哑人的手语展现给接收方的无听力和语言障碍用户，从而实现了双方的信息交互，克服了聋哑人在进行信息交流时智能终端性能没有充分发挥的缺陷，增强了聋哑人利用智能终端进行信息交流的便捷性。
下述实施例中，智能终端除了可以包括智能手机，还可以包括智能平板、智能电视、智能手环等等智能硬件设备。
图1为本申请实施例一与聋哑人进行信息交流的方法流程示意图；本实施例中，无语言和听觉障碍的用户向有语言和听觉障碍的聋哑人拨打电话为例，拨打方为无语言和听觉障碍的用户，收听方为有语言和听觉障碍的聋哑人，本实施例从收听方一侧进行技术方案的说明。如图1所示，其包括：
S101、接收语音信号，在预先建立的手语库中对所述语音信号进行匹配；
本实施例中，语音信号来自无语言和听觉障碍的用户，手语库中包括标准的手语信息，手语库的建立通过把聋哑人在日常使用过程中所有使用到的手语，并进行标准化得到。具体地，可以收集不同国家或地区的使用的手语体系，比如有美国的“词汇性手语”、中国的“拼字性手语”，可以为不同手语体系建立独立的手语库。在具体建立手语库时，可以首先确定一个不同手语体系不同手语的手语模型，基于语音信号与不同手语模型的比对，从而实现匹配的过程。
具体地，本实施例中或其他任意实施例中，步骤S101中接收语音信号，在预先建立的手语库中对所述语音信号进行匹配可以具体包括：接收语音信号，将所述语音信号转换成数字信号，在预先建立的手语库中对所述语音信号对应的数字信号进行匹配。
具体地，接收的语音信号可以是射频信号，通过对该射频信号进行解调、信道分离、解密、信道解码、语音解码等方式得到数字信号。
S102、根据在预先建立的手语库中对所述语音信号的匹配结果，从所述手语库中选择与所述语音信号对应标准手语信息；
本实施例中或其他任意实施例中，匹配的过程实现了语音信号与手语库中标准化手语的对应关系确定过程，当进行语音信号与标准化手语的对应时，可以首先确定手语体系以及该手语体系对应的手语库，在确定的手语库中查找与语音信号对应的标准化手语。具体地中，由于在手语库中，每一个手语图形可以匹配到对应一个二进制码，根据该二进制码生成对应的语音信号。
本实施例中或其他任意实施例中，所述根据在预先建立的手语库中对所述语音信号的匹配结果，从所述手语库中选择与所述语音信号对应标准手语信息包括：根据对所述语音信号对应的数字信号的匹配结果，从所述手语库中选择与所述语音信号对应的数字信号匹配的标准手语信息。
S103、呈现从所述手语库中选择与所述语音信号对应标准手语信息。
本实施例中，所述呈现从所述手语库中选择与所述语音信号对应标准手语信息包括：显示从所述手语库中选择与所述语音信号对应的数字信号匹配的标准手语信息。具体地，所述显示从所述手语库中选择与所述语音信号对应的数字信号匹配的标准手语信息包括：以图形方式显示从所述手语库中选择与所述语音信号对应的数字信号匹配的标准手语信息。
对于视力良好的聋哑人，可以将手语以图形方式显示在智能终端的显示屏上。
具体地，在本申请的一实施例中，还包括：判断是否启动聋哑交互，如果是，则执行启动标准语音信号的接收；否则，结束。
具体地，可以在智能终端上设定一快捷启动按键，通过该快捷启动按键的触发来判断是否启动了聋哑交互模式。
但是，需要说明的是，也可以根据上述图1所述的方法制作一APP，在智能终端上安装并启动该APP。
上述语音信号可以包括通过运营商网络如GSM/CDMA进行发送的信号，也可以包括通过移动互联网进行传输的信号，比如通过微信等。
本申请实施例提供一种在其上记录有用于执行上述方法的程序的计算机可读记录介质。
所述计算机可读记录介质包括用于以计算机(例如计算机)可读的形式存储或传送信息的任何机制。例如，机器可读介质包括只读存储器(ROM)、随机存取存储器(RAM)、磁盘存储介质、光存储介质、闪速存储介质、电、光、声或其他形式的传播信号(例如，载波、红外信号、数字信号等)等。
图2为本申请实施例二与聋哑人进行信息交流的方法流程示意图；本实施例中，有语言和听觉障碍的用户向无语言和听觉障碍的聋哑人拨打电话为例，拨打方为有语言和听觉障碍的用户，收听方为无语言和听觉障碍的聋哑人，本实施例从收听方一侧进行技术方案的说明。如图2所示，其包括：
S201、捕获手语手势并采集捕获到的手语手势形成手语手势图像序 列；
本实施例中或者其他任意实施例中，在智能终端上均配置有前置或者后置摄像头，当聋哑人在使用手语进行信息表达的过程中，通过摄像头捕获并采集手语手势从而形成手势图像序列，包括在连续时间点上的手势图像。
本实施例中或者其他任意实施例中，步骤S201中所述捕获手语手势并采集捕获到的手语手势形成手语手势图像序列包括：
捕获手语手势并采集捕获到的手语手势，形成手语手势图像序列，将所述手语手势图像序列转换成数字信号。
另外，对于支持手写的智能手机来说，可以捕获聋哑人在手机触控屏幕上手写输入的手语手势，比如在微信上手写出手语。
S202、对手语手势图像序列中每个手语手势图像进行手势特征识别和定位；
本实施例中或者其他任意实施例中，步骤S202中所述对手语手势图像序列中每个手语手势图像进行手势特征识别和定位包括：
对手语手势图像序列中每个手语手势图像手势分解，在手势分解了的手语手势图像上进行手势特征识别和定位。
本实施例中，通过在一系列的图像上寻找不变特征，并利用这些特征来定位入脸，具体包括模板匹配法和基于外观形状的方法，所述手指上的不变特征至少包括：形状、肤色、纹理、边缘信息。
或者，制作标准模板(固定模板)或将模板先行参数化(可变模板)，计算输入图像与模板之间的相关值，这个相关值通常都是独立计算手指的轮廓、指尖各自的匹配程度后得出的综合描述，最后再根据相关值和预先设定的阈值来确定图像中是否存在手指。
S203、根据识别和定位到的手势特征在手语库中进行匹配生成数字信号；
与上述图1类似，根据不同手语手势与语音信号的对应关系，在手势库中建立了标注语音信号，当进行手语与语音信号的对应时，可以首先确定手语体系以及该手语体系对应的手语库，在确定的手语库中查找 与手语信号对应的标准语音信号。
具体地，在本申请的一实施例中，所述根据识别和定位到的手势特征在手语库中进行匹配生成数字信号：
根据识别和定位到的手势特征在对应手语手势图像上的数字信号，在手语库中进行匹配生成语音信号。
S204、发送根据在手语库中匹配结果生成的数字信号。
本实施例或者其他任意实施例中，将匹配到的语音信号发送到接收方，并在接收方得智能终端上进行播放。
本实施例或其他任意实施例中，还可以包括：判断是否启动聋哑交互，如果是，则执行启动手语手势的捕获；否则，结束。
具体地，可以在智能终端上设定一快捷启动按键，通过该快捷启动按键的触发来判断是否启动了聋哑交互模式。
但是，需要说明的是，也可以根据上述图1所述的方法制作一APP，在智能终端上安装并启动该APP。
上述语音信号可以包括通过运营商网络如GSM/CDMA进行发送的信号，也可以包括通过移动互联网进行传输的信号，比如通过微信等。
需要说明的是，在另外一实施例中，上述步骤S201可以在发送方侧执行，而步骤S202-204可以在接收方侧执行。
本申请实施例提供一种在其上记录有用于执行上述方法的程序的计算机可读记录介质。
所述计算机可读记录介质包括用于以计算机(例如计算机)可读的形式存储或传送信息的任何机制。例如，机器可读介质包括只读存储器(ROM)、随机存取存储器(RAM)、磁盘存储介质、光存储介质、闪速存储介质、电、光、声或其他形式的传播信号(例如，载波、红外信号、数字信号等)等。
图3为本申请实施例三与聋哑人进行信息交流的装置结构示意图；如图3所示，其包括：
接收模块301，配置为接收语音信号，在预先建立的手语库中对所述语音信号进行匹配；
匹配模块302，配置为根据在预先建立的手语库中对所述语音信号的匹配结果，从所述手语库中选择与所述语音信号对应标准手语信息；
呈现模块303，配置为呈现从所述手语库中选择与所述语音信号对应标准手语信息。
本实施例中或其他任意实施例中，所述接收模块进一步配置为接收语音信号，将所述语音信号转换成数字信号，在预先建立的手语库中对所述语音信号对应的数字信号进行匹配。
本实施例中或其他任意实施例中，所述匹配模块进一步配置为根据对所述语音信号对应的数字信号的匹配结果，从所述手语库中选择与所述语音信号对应的数字信号匹配的标准手语信息。
本实施例中或其他任意实施例中，所述呈现模块进一步配置为显示从所述手语库中选择与所述语音信号对应的数字信号匹配的标准手语信息。
本实施例中或其他任意实施例中，所述呈现模块进一步配置为以图形方式显示从所述手语库中选择与所述语音信号对应的数字信号匹配的标准手语信息。
本实施例中或其他任意实施例中，还包括判断模块，配置为判断是否启动聋哑交互，如果是，则执行启动接收模块，接收标准语音信号；否则，结束。
图4为本申请实施例四与聋哑人进行信息交流的装置结构示意图；如图4所示，其包括：
采集模块401：配置为捕获手语手势并采集捕获到的手语手势形成手语手势图像序列；
定位模块402：配置为对手语手势图像序列中每个手语手势图像进行手势特征识别和定位；
匹配模块403：配置为根据识别和定位到的手势特征在手语库中进行匹配生成数字信号；
发送模块404：配置为发送根据在手语库中匹配结果生成的数字信 号。
本实施例或其他任意实施例中，所述采集模块401进一步配置为捕获手语手势并采集捕获到的手语手势，形成手语手势图像序列，将所述手语手势图像序列转换成数字信号。
本实施例或其他任意实施例中，所述匹配模块403进一步配置为根据识别和定位到的手势特征在对应手语手势图像上的数字信号，在手语库中进行匹配生成语音信号。
本实施例或其他任意实施例中，所述定位模块402进一步配置为对手语手势图像序列中每个手语手势图像手势分解，在手势分解了的手语手势图像上进行手势特征识别和定位。
本实施例或其他任意实施例中，还包括判断模块(图中未示出)，配置为判断是否启动聋哑交互，如果是，则启动采集模块捕获手语手势；否则，结束。
图5为本申请实施例五智能终端结构示意图；如图5所示，智能终端500包括呈现模块501以及硬件处理器502，所述硬件处理器502配置为接收语音信号，在预先建立的手语库中对所述语音信号进行匹配；以及根据在预先建立的手语库中对所述语音信号的匹配结果，从所述手语库中选择与所述语音信号对应标准手语信息；所述呈现模块501配置为呈现从所述手语库中选择与所述语音信号对应标准手语信息。
图6为本申请实施例六智能终端结构示意图；如图6所示，其可以包括摄像头601、硬件处理器602以及射频模块603，所述摄像头601捕获手语手势并采集捕获到的手语手势形成手语手势图像序列；所述硬件处理器602配置为对手语手势图像序列中每个手语手势图像进行手势特征识别和定位，以及根据识别和定位到的手势特征在手语库中进行匹配生成数字信号，所述手势库包括标准的语音信号；所述射频模块603配置为发送根据在手语库中匹配结果生成的数字信号。
另外一实施例中，摄像头可被智能终端的手写屏幕代替，用于捕获手语手势并采集捕获到的手语手势形成手语手势图像序列，详细不再附图说明。
以上所描述的装置实施例仅仅是示意性的，其中所述作为分离部件说明的模块可以是或者也可以不是物理上分开的，作为模块显示的部件可以是或者也可以不是物理模块，即可以位于一个地方，或者也可以分布到多个网络模块上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。本领域普通技术人员在不付出创造性的劳动的情况下，即可以理解并实施。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到各实施方式可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件。基于这样的理解，上述技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品可以存储在计算机可读存储介质中，如ROM/RAM、磁碟、光盘等，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)执行各个实施例或者实施例的某些部分所述的方法。
最后应说明的是：以上实施例仅用以说明本申请的技术方案，而非对其限制；尽管参照前述实施例对本申请进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围。

Claims (17)

  1. 一种与聋哑人进行信息交流的方法，其特征在于，包括：
    接收语音信号，在预先建立的手语库中对所述语音信号进行匹配；
    根据在预先建立的手语库中对所述语音信号的匹配结果，从所述手语库中选择与所述语音信号对应标准手语信息；
    呈现从所述手语库中选择与所述语音信号对应标准手语信息。
  2. 根据就权利要求1所述的方法，其特征在于，所述接收语音信号，在预先建立的手语库中对所述语音信号进行匹配包括：
    接收语音信号，将所述语音信号转换成数字信号，在预先建立的手语库中对所述语音信号对应的数字信号进行匹配。
  3. 根据权利要求2所述的方法，其特征在于，所述根据在预先建立的手语库中对所述语音信号的匹配结果，从所述手语库中选择与所述语音信号对应标准手语信息包括：
    根据对所述语音信号对应的数字信号的匹配结果，从所述手语库中选择与所述语音信号对应的数字信号匹配的标准手语信息。
  4. 根据权利要求1所述的方法，其特征在于，所述呈现从所述手语库中选择与所述语音信号对应标准手语信息包括：
    显示从所述手语库中选择与所述语音信号对应的数字信号匹配的标准手语信息。
  5. 根据权利要求4所述的方法，其特征在于，所述显示从所述手语库中选择与所述语音信号对应的数字信号匹配的标准手语信息包括：以图形方式显示从所述手语库中选择与所述语音信号对应的数字信号匹配的标准手语信息。
  6. 根据权利要求1-5任一项所述的方法，其特征在于，还包括：判断是否启动聋哑交互，如果是，则执行启动标准语音信号的接收；否则，结束。
  7. 一种与聋哑人进行信息交流的方法，其特征在于，包括：
    捕获手语手势并采集捕获到的手语手势形成手语手势图像序列；
    对手语手势图像序列中每个手语手势图像进行手势特征识别和定 位；
    根据识别和定位到的手势特征在手语库中进行匹配生成数字信号；
    发送根据在手语库中匹配结果生成的数字信号。
  8. 根据权利要求7所述的方法，其特征在于，所述捕获手语手势并采集捕获到的手语手势形成手语手势图像序列包括：
    捕获手语手势并采集捕获到的手语手势，形成手语手势图像序列，将所述手语手势图像序列转换成数字信号。
  9. 根据权利要求8所述的方法，其特征在于，所述根据识别和定位到的手势特征在手语库中进行匹配生成数字信号：
    根据识别和定位到的手势特征在对应手语手势图像上的数字信号，在手语库中进行匹配生成语音信号。
  10. 根据权利要求7所述的方法，其特征在于，所述对手语手势图像序列中每个手语手势图像进行手势特征识别和定位包括：
    对手语手势图像序列中每个手语手势图像手势分解，在手势分解了的手语手势图像上进行手势特征识别和定位。
  11. 根据权利要求7所述的方法，其特征在于，还包括：判断是否启动聋哑交互，如果是，则执行启动手语手势的捕获；否则，结束。
  12. 一种与聋哑人进行信息交流的装置，其特征在于，包括：
    接收模块，配置为接收语音信号，在预先建立的手语库中对所述语音信号进行匹配；
    匹配模块，配置为根据在预先建立的手语库中对所述语音信号的匹配结果，从所述手语库中选择与所述语音信号对应标准手语信息；
    呈现模块，配置为呈现从所述手语库中选择与所述语音信号对应标准手语信息。
  13. 一种与聋哑人进行信息交流的装置，其特征在于，包括：
    采集模块，配置为捕获手语手势并采集捕获到的手语手势形成手语手势图像序列；
    定位模块，配置为对手语手势图像序列中每个手语手势图像进行手势特征识别和定位；
    匹配模块，配置为根据识别和定位到的手势特征在手语库中进行匹配生成数字信号；
    发送模块，配置为发送根据在手语库中匹配结果生成的数字信号。
  14. 一种智能终端，其特征在于，包括呈现模块以及硬件处理器，所述硬件处理器配置为接收语音信号，在预先建立的手语库中对所述语音信号进行匹配；以及根据在预先建立的手语库中对所述语音信号的匹配结果，从所述手语库中选择与所述语音信号对应标准手语信息；所述呈现模块配置为呈现从所述手语库中选择与所述语音信号对应标准手语信息。
  15. 一种智能终端，其特征在于，包括摄像头、硬件处理器以及射频模块，所述摄像头捕获手语手势并采集捕获到的手语手势形成手语手势图像序列；所述硬件处理器配置为对手语手势图像序列中每个手语手势图像进行手势特征识别和定位；以及根据识别和定位到的手势特征在手语库中进行匹配生成数字信号；所述射频模块配置为发送根据在手语库中匹配结果生成的数字信号。
  16. 一种在其上记录有用于执行权利要求1所述方法的程序的计算机可读记录介质。
  17. 一种在其上记录有用于执行权利要求7所述方法的程序的计算机可读记录介质。
PCT/CN2016/088485 2016-03-23 2016-07-04 聋哑人进行信息交流的方法、装置及智能终端 Ceased WO2017161741A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610168501.X 2016-03-23
CN201610168501.XA CN105868282A (zh) 2016-03-23 2016-03-23 聋哑人进行信息交流的方法、装置及智能终端

Publications (1)

Publication Number Publication Date
WO2017161741A1 true WO2017161741A1 (zh) 2017-09-28

Family

ID=56625530

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/088485 Ceased WO2017161741A1 (zh) 2016-03-23 2016-07-04 聋哑人进行信息交流的方法、装置及智能终端

Country Status (2)

Country Link
CN (1) CN105868282A (zh)
WO (1) WO2017161741A1 (zh)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109858043A (zh) * 2018-12-19 2019-06-07 上海立势达机电科技有限公司 一种手势语言与语音语言双向智能翻译装置
CN110008839A (zh) * 2019-03-08 2019-07-12 西安研硕信息技术有限公司 一种自适应手势识别的智能手语交互系统及方法
CN110111651A (zh) * 2018-02-01 2019-08-09 周玮 基于体态感知的智能语言交互系统
CN112256827A (zh) * 2020-10-20 2021-01-22 平安科技（深圳）有限公司 一种手语翻译方法、装置、计算机设备及存储介质
CN116805272A (zh) * 2022-10-29 2023-09-26 武汉行已学教育咨询有限公司 一种可视化教育教学分析方法、系统及存储介质

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106653051A (zh) * 2016-12-09 2017-05-10 天脉聚源(北京)传媒科技有限公司 一种视频聋哑模式的方法及装置
CN106789593B (zh) * 2017-01-13 2019-01-11 山东师范大学 一种融合手语的即时消息处理方法、服务器及系统
US10854110B2 (en) 2017-03-03 2020-12-01 Microsoft Technology Licensing, Llc Automated real time interpreter service
CN108629241B (zh) * 2017-03-23 2022-01-14 华为技术有限公司 一种数据处理方法和数据处理设备
CN107798964A (zh) * 2017-11-24 2018-03-13 郑军 一种实时识别手势的手语智能交互设备及其交互方法
CN110555329A (zh) * 2018-05-31 2019-12-10 苏州欧力机器人有限公司 一种手语翻译的方法、终端以及存储介质
CN108960158A (zh) * 2018-07-09 2018-12-07 珠海格力电器股份有限公司 一种智能手语翻译的系统和方法
CN111461005B (zh) * 2020-03-31 2023-11-28 腾讯科技（深圳）有限公司 一种手势识别方法、装置、计算机设备以及存储介质
CN113851029B (zh) * 2021-07-30 2023-09-05 阿里巴巴达摩院(杭州)科技有限公司 一种无障碍通信方法和装置

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101594434A (zh) * 2009-06-16 2009-12-02 中兴通讯股份有限公司 移动终端的手语处理方法和手语处理移动终端
CN101661330A (zh) * 2009-09-22 2010-03-03 深圳华为通信技术有限公司 一种转换手语的方法及终端
CN101794528A (zh) * 2010-04-02 2010-08-04 北京大学软件与微电子学院无锡产学研合作教育基地 一种手语语音双向翻译系统
US20140171036A1 (en) * 2009-11-18 2014-06-19 Gwendolyn Simmons Method of communication
CN103956167A (zh) * 2014-05-06 2014-07-30 北京邮电大学 一种基于Web的可视化手语翻译方法及设备

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101605158A (zh) * 2008-06-13 2009-12-16 鸿富锦精密工业（深圳）有限公司 聋哑人专用手机
CN101539994B (zh) * 2009-04-16 2012-07-04 西安交通大学 一种手语语音互译系统及手语语音互译方法
US8640021B2 (en) * 2010-11-12 2014-01-28 Microsoft Corporation Audience-based presentation and customization of content
CN102497513A (zh) * 2011-11-25 2012-06-13 中山大学 一种面向数字电视的视频虚拟人手语系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101594434A (zh) * 2009-06-16 2009-12-02 中兴通讯股份有限公司 移动终端的手语处理方法和手语处理移动终端
CN101661330A (zh) * 2009-09-22 2010-03-03 深圳华为通信技术有限公司 一种转换手语的方法及终端
US20140171036A1 (en) * 2009-11-18 2014-06-19 Gwendolyn Simmons Method of communication
CN101794528A (zh) * 2010-04-02 2010-08-04 北京大学软件与微电子学院无锡产学研合作教育基地 一种手语语音双向翻译系统
CN103956167A (zh) * 2014-05-06 2014-07-30 北京邮电大学 一种基于Web的可视化手语翻译方法及设备

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110111651A (zh) * 2018-02-01 2019-08-09 周玮 基于体态感知的智能语言交互系统
CN109858043A (zh) * 2018-12-19 2019-06-07 上海立势达机电科技有限公司 一种手势语言与语音语言双向智能翻译装置
CN109858043B (zh) * 2018-12-19 2023-10-27 上海立势达机电科技有限公司 一种手势语言与语音语言双向智能翻译装置
CN110008839A (zh) * 2019-03-08 2019-07-12 西安研硕信息技术有限公司 一种自适应手势识别的智能手语交互系统及方法
CN110008839B (zh) * 2019-03-08 2023-01-03 陕西联森电子科技有限公司 一种自适应手势识别的智能手语交互系统及方法
CN112256827A (zh) * 2020-10-20 2021-01-22 平安科技（深圳）有限公司 一种手语翻译方法、装置、计算机设备及存储介质
CN116805272A (zh) * 2022-10-29 2023-09-26 武汉行已学教育咨询有限公司 一种可视化教育教学分析方法、系统及存储介质

Also Published As

Publication number Publication date
CN105868282A (zh) 2016-08-17

Similar Documents

Publication Publication Date Title
WO2017161741A1 (zh) 聋哑人进行信息交流的方法、装置及智能终端
US11580983B2 (en) Sign language information processing method and apparatus, electronic device and readable storage medium
KR101786944B1 (ko) 화자 표시 방법 및 이를 구현하는 영상 통화 단말기
CN108885614B (zh) 一种文本和语音信息的处理方法以及终端
US20190251972A1 (en) Speech processing method and device
CN107123418B (zh) 一种语音消息的处理方法及移动终端
WO2016169095A1 (zh) 终端的报警方法及装置
WO2017072534A2 (en) Communication system and method
CN106128478B (zh) 语音播报方法及装置
CN103841272B (zh) 一种发送语音消息的方法及装置
CN108960158A (zh) 一种智能手语翻译的系统和方法
US11321280B2 (en) Multimedia file sharing method and terminal device
CN108074574A (zh) 音频处理方法、装置及移动终端
CN106331293A (zh) 来电信息处理方法及装置
CN109257498B (zh) 一种声音处理方法及移动终端
WO2016187910A1 (zh) 一种语音文字的转换方法及设备、存储介质
CN107483736A (zh) 一种即时通信应用程序的消息处理方法及装置
CN106601251A (zh) 通话文本的生成方法及系统
CN120151651A (zh) 对焦控制系统和方法、可穿戴设备、介质和程序产品
WO2016202277A1 (zh) 一种消息的发送方法及移动终端
CN111524518B (zh) 增强现实处理方法及装置、存储介质和电子设备
CN109887492A (zh) 一种数据处理方法、装置和电子设备
CN108920471A (zh) 一种语音翻译方法和电子设备
CN113127613B (zh) 聊天信息处理方法及装置
US20200184973A1 (en) Transcription of communications

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16895092

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 16895092

Country of ref document: EP

Kind code of ref document: A1