Method and Apparatus for Speech Recognition
Disclosed are a voice recognition method and an apparatus thereof. According to an embodiment of the present invention, the voice recognition method includes the following steps of: extracting a relation between entity names to cluster each of the entity name based on the extracted relation informat...
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Patent |
| Sprache: | eng ; kor |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Zusammenfassung: | Disclosed are a voice recognition method and an apparatus thereof. According to an embodiment of the present invention, the voice recognition method includes the following steps of: extracting a relation between entity names to cluster each of the entity name based on the extracted relation information; and identifying the intention of a speech considering the relation information tagged on the entity names as well as own information of the clustered entity names. Therefore, the voice recognition method is capable of increasing the accuracy of voice recognition in the voice recognition apparatus. A user terminal of the present invention can be connected with an artificial intelligence module, a drone (unmanned aerial vehicle: UAV), a robot, an augmented reality (AR) device, a virtual reality (VR) device and devices related with 5G services.
음성 인식 방법 및 장치가 개시된다. 본 발명의 일 실시예에 따른 음성 인식 처리 방법은 개체명의 관계를 추출하여 추출된 개체명의 관계 정보를 바탕으로 각 개체명을 클러스터링하고, 클러스터링된 각 개체명은 개체명 자체의 정보뿐만 아니라 개체명에 태깅된 개체명의 관계 정보까지 함께 고려하여 발화 의도를 파악함으로써, 음성 인식 장치에서 음성 인식의 정확성을 향상시킬 수 있다. 본 발명의 사용자 단말기는 인공 지능(Artificial Intelligence) 모듈, 드론(Unmanned Aerial Vehicle, UAV), 로봇, 증강 현실(Augmented Reality, AR) 장치, 가상 현실(Virtual Reality, VR) 장치, 5G 서비스와 관련된 장치 등과 연계될 수 있다. |
|---|