Abstract: A voice conversation reconstruction method performed by a voice conversation reconstruction apparatus is disclosed. The method includes acquiring speaker-specific voice recognition data about voice conversation, dividing the speaker-specific voice recognition data into a plurality of blocks using a boundary between tokens according to a predefined division criterion, arranging the plurality of blocks in chronological order irrespective of a speaker, merging blocks from continuous utterance of the same speaker among the arranged plurality of blocks, and reconstructing the plurality of blocks subjected to the merging in a conversation format in chronological order and based on a speaker.

Abstract: An aspect of the present invention relates to a voice recognition method which may comprise the steps of: receiving a voice signal, and converting the voice signal into voice data; recognizing the voice data by using an initial voice recognition model, and generating an initial voice recognition result; searching for the initial voice recognition result in big data, and collecting data identical and/or similar to the initial voice recognition result; generating or updating a voice recognition model by using the collected identical and/or similar data; and re-recognizing the voice data by using the generated or updated voice recognition model, and generating a final voice recognition result.

Abstract: The present invention relates to a method and device for recognizing a voice. More specifically, the voice recognition device according to the present invention may acquire voice information from a user, convert the obtained voice information into voice data, and generate a first voice recognition result by recognizing the converted voice data as a first voice recognition model. Thereafter, the voice recognition device may generate a second voice recognition result by recognizing the converted voice data as a second voice recognition model, compare the first voice recognition result with the second voice recognition result, and select one of the first voice recognition result and the second voice recognition result on the basis of a result of the comparison.

Abstract: A voice conversation reconstruction method performed by a voice conversation reconstruction apparatus is disclosed. The method includes acquiring speaker-specific voice recognition data about voice conversation, dividing the speaker-specific voice recognition data into a plurality of blocks using a boundary between tokens according to a predefined division criterion, arranging the plurality of blocks in chronological order irrespective of a speaker, merging blocks from continuous utterance of the same speaker among the arranged plurality of blocks, and reconstructing the plurality of blocks subjected to the merging in a conversation format in chronological order and based on a speaker.

Abstract: The voice recognition and translation method by a voice recognition system for multiple parties, according to one embodiment of the present invention, comprises the steps of: receiving a voice input; recognizing a first language which is the language of the voice; recognizing the text of the voice by means of a basic sound model on the basis of the first language; translating the recognized voice into an output language, if the first language is not the output language that has been preset as the output language; and storing and outputting the result in the output language.

Abstract: An automatic speech recognition device, according to the present invention, comprises: a memory for storing a program for converting speech data received via an interface module into transcription data, and outputting same; and a processor for executing the program stored in the memory, wherein, by executing the program, the processor converts the received speech data into pronunciation code data on the basis of a pre-trained first model, and converts the converted pronunciation code data into transcription data on the basis of a pre-trained second model.

Abstract: A translation method and an apparatus therefor are disclosed. Particularly, a method of performing sequence-to-sequence translation may include dividing an entire input into input units for each time point, the input units being units subjected to translation, inserting, into a corresponding one of the input units, a first symbol indicating a position of a symbol to be assigned a highest weight among symbols belonging to the corresponding input unit, and repeatedly deriving an output symbol from the input unit in which the first symbol is inserted each time the time point is increased.