Real-time captioning device with speaker data encapsulation

Abstract

A real-time caption processing device with speaker data encapsulation includes a processing host, an audio input interface, a speech recognition module, a storage unit, a comparison processing module, a caption display control module, a caption output interface, and a caption display device. The storage unit includes a content encapsulation storage area and a speaker data encapsulation storage area. The content encapsulation storage area stores content units and pre-confirmed caption data, while the speaker data encapsulation storage area stores speaker data encapsulation and speaker contextual deviation characteristics. After on-site audio data is input through the audio input interface, the speech recognition module generates speech-recognized text. The comparison processing module retrieves the data from the storage unit and then passes it to the caption display control module to control the caption output interface, causing the caption display device to output the caption content or display status. This reduces the risk of unconfirmed speech-recognized text being output directly and improves caption misalignment, display delay, and the burden of manual switching.

Claims

1. A real-time caption processing device with speaker data encapsulation, comprising: a processing host having a processor, a memory, and an internal data bus; an audio input interface signal-connected to the processing host and used to receive live audio data; a voice recognition module disposed within the processing host and signal-connected to the internal data bus; a storage unit data-connected to the processing host, the storage unit including a content encapsulation storage area and a speaker data encapsulation storage area, the content encapsulation storage area storing at least one content unit and pre-confirmed caption data corresponding to one of the content units, the speaker data encapsulation storage area storing a speaker data encapsulation; a comparison processing module disposed within the processing host and signal-connected to the internal data bus, and the comparison processing module data-connected to the storage unit; a caption display control module disposed within the processing host and signal-connected to the internal data bus; a caption output interface signal-connected to the processing host; and a caption display device signal-connected to the caption output interface; in, The speech recognition module, the comparison processing module, and the subtitle display control module are sequentially arranged between the audio input interface and the subtitle output interface. The speech recognition module generates speech-recognized text, which is then stored in the content encapsulation storage area and the speaker data encapsulation storage area by the comparison processing module. Finally, the subtitle display control module controls the subtitle output interface to output subtitle display content to the subtitle display device.

2. The real-time captioning device with speaker data encapsulation as described in claim 1, wherein, The processor, the memory, the voice recognition module, the comparison processing module, and the subtitle display control module are each connected to the internal data bus signal.

3. The real-time captioning device with speaker data encapsulation as described in claim 1, wherein, The content encapsulation storage area includes a content unit storage section and a pre-confirmation subtitle data storage section. The content unit storage section stores the content unit, and the pre-confirmation subtitle data storage section stores the pre-confirmation subtitle data corresponding to the content unit.

4. The real-time captioning device with speaker data encapsulation as described in claim 1, wherein, The speaker data encapsulation storage area includes a speaker data encapsulation storage unit and a speaker situational deviation feature storage unit. The speaker data encapsulation storage unit stores the speaker data encapsulation, and the speaker situational deviation feature storage unit stores the speaker situational deviation features corresponding to the speaker and the situation.

5. The real-time captioning device with speaker data encapsulation as described in claim 1, wherein, The comparison processing module is configured between the speech recognition module and the subtitle display control module, and is connected to the content encapsulation storage area and the speaker data encapsulation storage area respectively.

6. The real-time captioning device with speaker data encapsulation as described in claim 1, wherein, The subtitle display control module includes a subtitle output control unit and a prompt display control unit. The subtitle output control unit is used to control the subtitle output interface to output the subtitle display content, and the prompt display control unit is used to control the subtitle display device to output a prompt display status.

7. The real-time captioning device with speaker data encapsulation as described in claim 6, wherein, The prompt can be displayed as a waiting symbol, a pulsating indicator, or a blank display.

8. The real-time captioning device with speaker data encapsulation as described in claim 1, wherein, The subtitle output interface can be a wired display output interface, a wireless display output interface, or a projection output interface.

9. The real-time captioning device with speaker data encapsulation as described in claim 1, wherein, The audio input interface can be a microphone, an audio receiver, or an audio port.

10. The real-time captioning device with speaker data encapsulation as described in claim 1, wherein, The storage unit can be a built-in storage device, a removable storage device, or an external storage device.

Images