Natural language processing (NLP) is a branch of artificial intelligence focused on enabling computers to understand, interpret, and generate human language in meaningful ways. At VRAIN, our NLP research encompasses multiple dimensions: from speech recognition and synthesis to machine translation, sentiment analysis, and text simplification.

Our work in this area addresses the challenges of multilingual processing and tackles complex linguistic phenomena such as irony detection and automatic summarization. We have developed systems like TransLectures-UPV (TLP) for automatic multilingual transcription and subtitling of training videos, SENTAT for sentiment analysis in Spanish tweets, and EN-IRONIC/ES-IRONIC for irony detection in social media. We also provide TT-Streaming, an RPC API for real-time transcription, translation, and dubbing of live audio broadcasts, along with neural network-based models for speech synthesis and recognition across multiple languages.

Through our research, we aim to break down language barriers and make information more accessible across different languages and contexts.