TWM515143U - Speech translating system and translation processing apparatus - Google Patents

Abstract

A speech translating system and a translation processing apparatus are provided. The speech translating system contains speech transceiving apparatuses and the translation processing apparatus. Each speech transceiving apparatus obtains an audio stream. A target language of each speech transceiving apparatuses are configured by the translation processing apparatus. The audio stream would be transmitted wirelessly to the translation processing apparatus by the speech transceiving apparatus. Then, the translation processing apparatus performs translating with the audio stream to obtain speech translating results, and transmits these speech translating results wirelessly to the corresponding speech transceiving apparatus according to all target languages of the speech transceiving apparatuses. Therefore, a function of instant multi-person translation would be achieved.

Description

Speech translation system and translation processing device

The novel creation is related to a speech translation technology, and in particular to a speech translation system and a translation processing device.

With the development of globalization and the convenience of transportation, the distance between geographical regions is narrowing, and people have more opportunities to work or travel in other countries or cities. In recent years, the number of foreign tourists visiting China has also increased. It can be seen that in addition to international business contacts, tourism and tourism are gradually becoming international.

In general, people from different countries communicate with each other and inevitably encounter language problems. Although many instant translation devices or translation software exist on the market, the cumbersome steps are quite inconvenient for practical use. For example, the user has to press the "Translate" button on the user interface to perform a one-word translation.

The novel creation provides a speech translation system and a translation processing device, which can provide a multi-person speech translation function, and combines a hands free mode to avoid cumbersome operation steps.

The novel creation provides a speech translation system. The speech translation system includes a voice transceiving device and a translation processing device. Each voice transmitting and receiving device acquires a voice stream. The translation processing device sets a target language of each of the voice transmitting and receiving devices, and each of the voice transmitting and receiving devices wirelessly transmits the audio stream to the translation processing device, and the translation processing device translates the voice stream according to the target language of all the voice transmitting and receiving devices to obtain a voice translation result. And the voice translation results are wirelessly transmitted to the corresponding voice transceiver device according to the target language of each voice transceiver device.

The novel creation provides a translation processing device, and the translation processing device includes a communication unit, a storage unit, and a processing unit. The communication unit is used to transmit and receive wireless signals. Storage unit record module. The processing unit is coupled to the communication unit and the storage unit, and accesses and executes the module recorded by the storage unit. These modules include a voice transceiver module and a translation module. The voice transceiver module wirelessly receives a voice stream from one of the voice transceiver devices through the communication unit. The translation module sets the target language of each voice transceiver device, translates the voice stream according to the target language of all voice transceiver devices to obtain a voice translation result, and according to the target language of each voice transceiver device, the voice transceiver module transmits the voice transmission module through the communication unit respectively. The speech translation result is wirelessly transmitted to the corresponding voice transceiving device.

Based on the above, the present invention provides a voice translation system and a translation processing device, which listens to a user's speech through a voice transceiver device to obtain a voice stream, and the translation processing device can wirelessly receive the voice stream and distribute the voice translation result. To the corresponding voice transceiver. Thereby, the novel creation embodiment can provide an instant multi-person dialogue translation function, and can be applied to various situations that need to communicate with foreigners.

The above described features and advantages of the present invention will become more apparent and understood from the following description.

Wireless communication technologies such as Bluetooth, WiFi, etc., can be combined with existing electronic devices (eg, smart phones, tablets, notebooks, etc.) to provide several hands-free features (eg, hands-free calling, music) Streaming, video streaming, etc.). The electronic device can also be connected to several hands-free devices through the aforementioned wireless communication technology. Accordingly, the novel creation embodiment is to use the hands-free device as a voice transceiver device to receive the conversation content of the user, and translate the conversation content into the set target language through the translation processing device, and respectively transmit the content to the plurality of voice transceiver devices. So that all users can listen to the corresponding speech translation results. In this way, the instant multi-person dialogue translation function can be realized. In the following, various embodiments in accordance with the spirit of the present invention are proposed, and those applying the present embodiment can appropriately adjust these embodiments according to their needs, and are not limited to the contents in the following description.

1 is a schematic diagram illustrating a speech translation system in accordance with an embodiment of the present invention. Referring to FIG. 1, the speech translation system 10 includes one or more voice transceiving devices 110 and a translation processing device 150. It should be noted that only two voice transceivers 110 are presented in FIG. 1 , but the actual application is not limited thereto.

The voice transceiver 110 is, for example, a Bluetooth headset or other hands-free device that transmits and receives voice signals through communication technologies such as Bluetooth or WiFi. The voice transceiver device 110 includes a mono or stereo speaker module, a microphone module and a communication module, and can receive the sound emitted by the user through the microphone module through the communication module ( For example, Bluetooth modules, WiFi modules, etc. transmit and receive audio streams and play sound through the speaker module.

The translation processing device 150 is, for example, an electronic device having an arithmetic processing function such as a smart phone, a tablet computer, or a notebook computer. In a hardware perspective, FIG. 2 is a block diagram illustrating a translation processing apparatus 150 in accordance with an embodiment of the present invention. Referring to FIG. 2, the translation processing device 150 includes a communication unit 151, a second communication unit 153, a storage unit 155, and a processing unit 157.

The communication unit 151 can support, for example, a wireless communication technology such as a Bluetooth standard or a WiFi standard. In this embodiment, the communication unit 710 is configured to wirelessly receive the voice stream from the voice transceiver device 110 and wirelessly transmit the voice translation result to each of the voice transceiver devices 110. The generation and processing of the sound stream and the speech translation result are described in detail later.

The second communication unit 153 may be a WiFi standard, third generation wireless communication (3G), fourth generation wireless communication (4G) or other wireless network interface module with wireless transmission function. In this embodiment, the translation processing device 150 can connect to the translation server via the Internet through the second communication unit 153, and transmit the text data to the translation server, and obtain the translation server. Translate text materials. The generation and processing of textual materials and translated textual materials are described in detail later.

The storage unit 155 can be any type of fixed or removable random access memory (RAM), read-only memory (ROM), flash memory or the like. Or a combination of the above elements. In this embodiment, the storage unit 155 is used to record software programs such as the voice transceiver module 155_1, the voice processing module 155_3, and the translation module 155_5. The storage unit 155 described in this embodiment is not limited to a single memory component, and each of the above software modules may be separately stored in two or more memory components of the same or different types.

The voice transceiver module 155_1 is, for example, a management program based on a communication technology supported by the communication unit 151, for example, a Bluetooth low energy (BLE) multi-Dev, a Bluetooth management program, etc., which can be obtained from The communication unit 151 acquires the audio stream from the voice transmitting and receiving device 110, and transmits the voice translation result to the voice transmitting and receiving device 110 via the communication unit 151. The voice processing module 155_3 has an automatic speech recognition (ASR) function and a text to speech (TTS) function, for example, a Google Voice application interface (API), which is identifiable. The sound stream is converted into text data, and the text data can be converted back to the sound stream. The translation module 155_5 is used to translate the converted text data to obtain the speech translation result, and the detailed operation is described in the following embodiments. The implementation example of the translation module 155_5 may be a translation software program, an engine or an application interface (for example, Google translation, Bing translation, etc.) that supports at least two target languages (for example, Chinese, English, Japanese, etc.), and is not limited. The operating system platform of the translation processing device 150 (for example, Android, iOS, etc.).

The processing unit 157 is respectively connected to the communication unit 151, the second communication unit 153, and the storage unit 155, and may be a central processing unit (CPU), or other programmable general purpose or special purpose microprocessor. (Microprocessor), Digital Signal Processor (DSP), Programmable Controller, Application Specific Integrated Circuit (ASIC) or other similar components or a combination of the above. In this embodiment, the processing unit 157 is configured to access and execute the modules recorded in the storage unit 155, thereby implementing the embodiment of the novel creation.

In order to enable those skilled in the art to clarify the embodiments of the novel creation, in the following, two implementation scenarios will be described in conjunction with the voice transceiver 110 and the translation processing device 150, which are one-to-many translation and many-to-many translation. Situation. The various processes can be adjusted accordingly according to the implementation situation, and are not limited thereto.

One-to-many translation scenario

3 is a flow chart showing the speech translation of the speech translation system 10 in accordance with an embodiment of the present invention. Assuming that the context is that the speech translation system 10 includes the speech transmitting and receiving devices 110_1 to 110_4 and the translation processing device 150, the target languages of the users operating the speech transmitting and receiving devices 110_1 to 110_4 are Chinese, English, Japanese, and French, respectively. The translation processing device 150 may have a user interface (User Interface: UI) or a physical button setting interface or the like for the user to set its target language. In some other embodiments, the voice transceivers 110_1 110 110_4 may also have a target language setting interface to receive a user's language setting operation (eg, select English, Japanese, etc.), and transmit the setting information of the target language to the translation processing. Device 150. The translation module 155_5 records the target languages of all of the voice transceiving devices 110_1 to 110_4.

After the target language setting is completed, the voice transceiver 110_1 receives the user's voice input through its microphone module (step S310) (for example, hello), and transmits the voice stream generated by the voice input to the translation processing device 150 ( Step S315). It should be noted that the translation processing device 150 or the voice transceiving devices 110_1~110_4 may have a startup (physical or virtual) button to receive the user's startup operation, thereby starting the speech translation process (ie, proceeding to step S310). The voice transceiver module 155_1 (ie, the Bluetooth management program) receives the voice stream through the communication module 151, and transmits the voice stream to the voice processing module 155_3 (ie, the voice application interface) (step S320). The voice application interface identifies the target language corresponding to the voice stream (in this embodiment, Chinese), and converts the voice stream (ie, voice data) into text data according to the recognized target language (step S330). It should be noted that the format of the text data is in accordance with the input format required by the translation module 155_5.

Next, the translation module 155_5 (ie, the translation program) determines whether or not the authorization key exists, and determines whether the number of used characters exceeds the upper threshold (step S341). This authorization key is used by the translator. If the translation module 155_5 determines that there is an authorization key (for example, stored in the storage unit 155), further counts the number of characters used, and checks whether the number of used characters exceeds the upper threshold (for example, one million, two million a day). Wait for the number of characters used). If the number of characters used exceeds the upper threshold, the processing unit 157 disables the translation module 155_5 (eg, disables some or all of the functions), or provides a payment operation floor (the translation module 155_5 can continue after confirming the payment) Perform subsequent translations).

On the other hand, if the number of used characters does not exceed the upper threshold, the translation module 155_5 can input the text data, and transmit the text data to the translation server through the second communication unit 153 (step S343). It should be noted that the translation module 155_5 first converts the text data into an input format required by the translation server (for example, JSON (JavaScript Object Notation)), and the format of the translation server backhaul is also the JSON format. The translation module 155_5 can obtain the translation result in the JSON format from the translation server through the second communication unit 153, and convert the translation result in the JSON format into the translated text data (step S345) to conform to the input format required by the voice application interface. . It should be noted that the translated text materials may correspond to the target languages (ie, Chinese, English, Japanese, and French) set by the voice transmitting and receiving devices 110_1 to 110_4, respectively.

Next, the voice application interface converts the translated text data into a voice translation result (a voice data format, such as a sound raw material) (step S350). The multimedia playback service program performs voice output processing on the voice translation result (step S360). The Bluetooth management program separately transmits the voice translation result of each target language to the corresponding voice transmitting and receiving device 110_1~110_4 through the communication unit 151 (that is, the voice transmitting device 110_1 obtains the Chinese voice translation result (for example, hello), the voice transceiver device. 110_2 obtains a speech translation result of English (for example, hello), and the like, and so on (step S370). Thereby, the novel creation embodiment can realize the function of one-to-many instant voice translation.

In addition, the voice processing module 155_3 also recognizes whether a sentence is present in the voice stream as an end condition for translating the sentence. For example, "Where is the weather today" and "Where are you going in the afternoon?" can be judged as a broken sentence, "Today's good weather" and "Where are you going in the afternoon?" will be entered into the translation module as two sets of text data respectively. 155_5. After the voice translation result is output to the voice transceiver 110, the Bluetooth program will be automatically turned on to receive the voice stream corresponding to the next sentence. In other words, in actual operation, the user does not need to manually perform the manual start operation, and the translation processing device 150 can continue the translation operation.

Many-to-many translation scenarios

4 is a flow chart showing the speech translation of the speech translation system 10 in accordance with another embodiment of the present invention. Assuming that the context is that the speech translation system 10 includes the speech transmitting and receiving devices 110_1 to 110_3 and the translation processing device 150, the target languages of the users operating the speech transmitting and receiving devices 110_1 to 110_4 are Chinese, English, and Japanese, respectively. For details of the steps S430 to S470, refer to steps S330 to S370 in FIG. 3, and details are not described herein again.

4 is different from FIG. 3 in that the voice transceiving devices 110_1 110 110_3 can respectively receive the voice inputs of three users (for example, good morning, hello, arigatou) at the same time or at different times (step S410), and will respectively be three groups. The three sets of sound streams generated by the sound input are respectively transmitted to the translation processing device 150 (step S415). The Bluetooth management program can receive three sets of sound streams sequentially or simultaneously, and respectively stream the three sets of sounds to the voice application interface (step S430). Since the voice processing module 155_3 can automatically recognize the target language corresponding to the three sets of voice streams, the translation module 155_5 can also obtain three sets of translated text data corresponding to the three sets of voice streams respectively in step S445 (ie, Chinese ( Good morning, hello, thank you), English (good morning, hello, thanks) and Japanese (ohayo gozaimasu, konnichiwa, arigatou)). Thereby, the novel authoring embodiment can realize the function of many-to-many instant voice translation.

It should be noted that, in the foregoing embodiments, the software modules (ie, the voice transceiver module 155_1, the voice processing module 155_3, and the translation module 155_3) can respectively control their respective operations through a single software program, and the software is separately controlled. The program is stored in the storage unit 155 and can be accessed and executed by the processing unit 157.

In summary, the present invention provides a voice translation system and a translation processing device that can process the conversation content received by two or more voice transceivers by a single translation processing device, and transmit the voice translation results separately. To the corresponding voice transceiver. Since the Bluetooth-free headset and the like are portable and widely used by the public, the user only needs to load the software program implemented by the novel creation embodiment on the electronic device (for example, a smart phone, a tablet, etc.) ), one-to-many or many-to-many instant voice translation can be easily implemented.

Although the present invention has been disclosed in the above embodiments, it is not intended to limit the novel creation, and any person skilled in the art can make some changes without departing from the spirit and scope of the novel creation. Retouching, the scope of protection of this new creation is subject to the definition of the scope of the patent application attached.

10‧‧‧Voice translation system
110, 110_1~110_4‧‧‧ voice transceiver
150‧‧‧Translation processing device
151‧‧‧Communication unit
153‧‧‧Second communication unit
155‧‧‧ storage unit
155_1‧‧‧Voice transceiver module
155_3‧‧‧Voice Processing Module
155_5‧‧‧Translation module
157‧‧‧Processing unit
S310～S370, S410～S470‧‧‧ steps

1 is a schematic diagram illustrating a speech translation system in accordance with an embodiment of the present invention. 2 is a block diagram showing a translation processing apparatus in accordance with an embodiment of the present invention. FIG. 3 is a flow chart showing the speech translation of the speech translation system according to an embodiment of the present invention. 4 is a flow chart showing the speech translation of the speech translation system in accordance with another embodiment of the present invention.

150‧‧‧Translation processing device

151‧‧‧Communication unit

153‧‧‧Second communication unit

155‧‧‧ storage unit

155_1‧‧‧Voice transceiver module

155_3‧‧‧Voice Processing Module

155_5‧‧‧Translation module

157‧‧‧Processing unit

Claims (10)

A voice translation system, comprising: a plurality of voice transceivers, wherein each of the voice transceivers obtains a voice stream; and a translation processing device, wherein the translation processing device sets a target language of each of the voice transceivers, each The voice transceivers wirelessly transmit the voice stream to the translation processing device, and the translation processing device translates the voice stream according to the target language of all of the voice transceiver devices to obtain a plurality of voice translation results, and The target language of each of the voice transceivers wirelessly transmits the voice translation results to the corresponding voice transceivers. The speech translation system of claim 1, wherein the translation processing device recognizes the target language corresponding to the audio stream, and converts the audio stream into a text material according to the target language. The speech translation system of claim 2, wherein the translation processing device translates the text data according to the target language of all of the voice transceiving devices to obtain a plurality of translated text materials, and the translated texts are The data is converted into the speech translation results. The speech translation system of claim 2, wherein the translation processing device determines whether an authorization key exists and determines whether the number of used characters exceeds an upper threshold. The speech translation system of claim 3, wherein the translation processing device transmits the text data to a translation server and retrieves the translated text data from the translation server. A translation processing device includes: a communication unit that transmits and receives wireless signals; a storage unit that records a plurality of modules; and a processing unit that couples the communication unit and the storage unit and accesses and executes the storage unit Recording the modules, the modules include: a voice transceiver module, wirelessly receiving a voice stream from one of the plurality of voice transceivers through the communication unit; and a translation module, setting each a target language of the voice transceivers, the voice stream is translated according to the target language of all of the voice transceivers to obtain a plurality of voice translation results, and according to the target language of each of the voice transceivers, The voice transceiver module wirelessly transmits the voice translation results to the corresponding voice transceiver devices through the communication unit. The translation processing device of claim 6, wherein the modules further comprise: a voice processing module, identifying the target language corresponding to the voice stream, and converting the voice stream according to the target language Into a text message. The translation processing device of claim 7, wherein the translation module translates the text data according to the target language of all of the voice transceivers to obtain a plurality of translated text materials, and the voice processing module Converting the translated text data into the speech translation results. The translation processing device of claim 7, wherein the translation module determines whether an authorization key exists and determines whether the number of used characters exceeds an upper threshold. The translation processing device of claim 8, further comprising: a second communication unit, wherein the translation module transmits the text data to a translation server through the second communication unit, and the translation server Obtain the translated text data.