Artificial intelligence

Speech & language AI

Terms

7 terms

  • Named entity recognition NER

    Named entity recognition (NER) is the language AI task of finding names of people, organizations, places and similar items in text and labeling their types.

  • NLP

    NLP, or natural language processing, is the field of AI that enables computers to analyze, interpret and generate human language in text and speech.

  • Sentiment analysis

    Sentiment analysis is a language AI task that classifies the opinion or emotional tone in text as positive, negative or neutral, often per aspect.

  • Speech-to-text

    Speech-to-text is the AI task of converting spoken audio into written text, using acoustic and language modeling to produce timed transcripts.

  • Text-to-speech

    Text-to-speech is the speech AI technology that converts written text into natural-sounding spoken audio using neural acoustic models and vocoders.

  • Translation

    Translation in language AI is the automatic conversion of text or speech from one language to another by neural models that preserve meaning, tone and format.

  • Voice cloning

    Voice cloning uses speech synthesis models to reproduce a specific person's voice from recorded samples, generating new speech that sounds like them.