Text-to-speech

Text-to-speech (TTS) is technology that converts written text into spoken audio. It combines language processing with speech synthesis to produce an audible rendition.

Text normalization: The conversion of written forms such as numbers, abbreviations, and symbols into words suitable for speech. TTS systems expand written forms before deciding how to pronounce them.
Phoneme: A contrastive speech sound unit that can distinguish words within a language. TTS systems often represent pronunciation as sequences of phonemes.
Wolfgang von Kempelen: An inventor whose eighteenth-century speaking machine mechanically imitated parts of human speech production. His device is an early landmark in attempts to synthesize speech.
Screen reader: Assistive software that conveys computer interface content through speech or other output. Screen readers commonly rely on TTS to make on-screen text audible.
Text-to-speech versus speech recognition: The computational identification of spoken words from an audio signal. Speech recognition converts speech into text, reversing TTS's usual direction.
Grapheme-to-phoneme conversion: The mapping of written letter sequences to phonemes, the sound units of a language. It supplies pronunciations when spelling alone does not determine how text sounds.
International Phonetic Alphabet: A standardized alphabet for representing speech sounds across languages. Its symbols provide a consistent way to describe pronunciations for TTS.
Bell Labs: An American research laboratory known for influential work in telecommunications, computing, and speech technology. Its researchers developed landmark electronic speech synthesizers, including the VODER.
Augmentative and alternative communication: Methods and tools that support communication when speech or writing is difficult. Speech output lets AAC users express text they compose or select.
Voice conversion: The transformation of one speaker's vocal characteristics into those of another speaker. Voice conversion changes an existing voice signal, while TTS generates speech from text.

Linked from 11 pages