In spoken language processing, concept-to-speech (CTS) is the process of translating a conceptual meaning or idea into spoken words or sentences. It involves several stages, including conceptualization, lexical retrieval, syntactic encoding, phonological encoding, and articulation. The input of a concept-to-speech system can be, for example, a sequence of images selected by a user in a picture board used for [[augmentative and alternative communication (AAC)]] or a message generated by a natural language generation system. In both cases, the processes of resolving the ambiguities inherent in the message are very different from the processes used in [[text-to-speech synthesis (TTS)]] for written text.