# Speech synthesis

Speech synthesis is the artificial production of human speech by computer systems, converting text or linguistic representations into audible voice. It enables accessibility tools, voice assistants, and communication aids, with quality judged by intelligibility and naturalness.

Speech synthesis is the artificial production of human speech. A computer system used for this purpose is called a speech synthesizer, and can be implemented in software or hardware products. A text-to-speech (TTS) system converts normal language text into speech; other systems render symbolic linguistic representations like phonetic transcriptions into speech. The reverse process is speech recognition.

Synthesized speech can be created by concatenating pieces of recorded speech that are stored in a database. Systems differ in the size of the stored speech units; a system that stores phones or diphones provides the largest output range, but may lack clarity. For specific usage domains, the storage of entire words or sentences allows for high-quality output. Alternatively, a synthesizer can incorporate a model of the vocal tract and other human voice characteristics to create a completely "synthetic" voice output.

The quality of a speech synthesizer is judged by its similarity to the human voice and by its ability to be understood clearly. An intelligible text-to-speech program allows people with visual impairments or reading disabilities to listen to written words on a home computer. The earliest computer operating system to have included a speech synthesizer was Unix in 1974, through the Unix speak utility. In 2000, Microsoft Sam was the default text-to-speech voice synthesizer used by the narrator accessibility feature, which shipped with all Windows 2000 operating systems, and subsequent Windows XP systems.

## Architecture of a Text-to-Speech System

A text-to-speech system (or "engine") is composed of two parts: a front-end and a back-end. The front-end has two major tasks. First, it converts raw text containing symbols like numbers and abbreviations into the equivalent of written-out words. This process is often called text normalization, pre-processing, or tokenization. The front-end then assigns phonetic transcriptions to each word, and divides and marks the text into prosodic units, like phrases, clauses, and sentences. The process of assigning phonetic transcriptions to words is called text-to-phoneme or grapheme-to-phoneme conversion. Phonetic transcriptions and prosody information together make up the symbolic linguistic representation that is output by the front-end.

The back-end, often referred to as the synthesizer, then converts the symbolic linguistic representation into sound. In certain systems, this part includes the computation of the target prosody (pitch contour, phoneme durations), which is then imposed on the output speech. This two-stage design allows for modular development, where linguistic analysis can be improved independently from acoustic generation.

## Historical Development

Long before the invention of electronic signal processing, some people tried to build machines to emulate human speech. There were also legends of the existence of "Brazen Heads", such as those involving Pope Silvester II (d. 1003 AD), Albertus Magnus (1198–1280), and Roger Bacon (1214–1294).

In 1779, the German-Danish scientist Christian Gottlieb Kratzenstein won the first prize in a competition announced by the Russian Imperial Academy of Sciences and Arts for models he built of the human vocal tract that could produce the five long vowel sounds (in International Phonetic Alphabet notation: [aː], [eː], [iː], [oː] and [uː]). There followed the bellows-operated "acoustic-mechanical speech machine" of Wolfgang von Kempelen of Pressburg, Hungary, described in a 1791 paper. This machine added models of the tongue and lips, enabling it to produce consonants as well as vowels. In 1837, Charles Wheatstone produced a "speaking machine" based on von Kempelen's design, and in 1846, Joseph Faber exhibited the "Euphonia". In 1923, Paget resurrected Wheatstone's design.

In the 1930s, [Bell Labs](https://www.wikiprompt.org/wiki/xerox-parc) developed the vocoder, which automatically analyzed speech into its fundamental tones and resonances. From his work on the vocoder, Homer Dudley developed a keyboard-operated voice-synthesizer called The Voder (Voice Demonstrator), which he exhibited at the 1939 New York World's Fair.

Franklin S. Cooper and his colleagues at Haskins Laboratories built the pattern playback in the late 1940s and completed it in 1950. There were several different versions of this hardware device; only one currently survives. The machine converts pictures of the acoustic patterns of speech in the form of a spectrogram back into sound. Using this device, Alvin Liberman and colleagues discovered acoustic cues for the perception of phonetic segments (consonants and vowels).

## Electronic and Computer-Based Systems

The first computer-based speech-synthesis systems originated in the late 1950s. Noriko Umeda et al. developed the first general English text-to-speech system in 1968, at the Electrotechnical Laboratory in Japan. In 1961, physicist John Larry Kelly, Jr and his colleague Louis Gerstman used an IBM 7090 computer to synthesize speech, an event among the most prominent in the history of Bell Labs. Kelly's voice recorder synthesizer (vocoder) recreated the song "Daisy Bell", with musical accompaniment from Max Mathews. Coincidentally, Arthur C. Clarke was visiting his friend and colleague John Pierce at the Bell Labs Murray Hill facility. Clarke was so impressed by the demonstration that he used it in the climactic scene of his screenplay for his novel 2001: A Space Odyssey, where the HAL 9000 computer sings the same song as astronaut Dave Bowman puts it to sleep. Despite the success of purely electronic speech synthesis, research into mechanical speech-synthesizers continues.

Linear predictive coding (LPC), a form of speech coding, began development with the work of Fumitada Itakura of Nagoya University and Shuzo Saito of Nippon Telegraph and Telephone (NTT) in 1966. Further developments in LPC technology were made by Bishnu S. Atal and Manfred R. Schroeder at Bell Labs during the 1970s. LPC was later the basis for early speech synthesizer chips, such as the Texas Instruments LPC Speech Chips used in the Speak & Spell toys from 1978.

In 1975, Fumitada Itakura developed the line spectral pairs (LSP) method for high-compression speech coding, while at NTT. From 1975 to 1981, Itakura studied problems in speech analysis and synthesis based on the LSP method. In 1980, his team developed an LSP-based speech synthesizer chip. LSP is an important technology for speech synthesis and coding, and in the 1990s was adopted by almost all international speech coding standards as an essential component, contributing to the enhancement of digital speech communication over mobile channels and the internet.

In 1975, MUSA was released, and was one of the first Speech Synthesis systems. It consisted of a stand-alone computer hardware and a specialized software that enabled it to read Italian. A second version, released in 1978, was also able to sing Italian in an "a cappella" style.

Dominant systems in the 1980s and 1990s were the DECtalk system, based largely on the work of Dennis Klatt at [MIT](https://www.wikiprompt.org/wiki/mit-csail), and the Bell Labs system; the latter was one of the first multilingual language-independent systems, making extensive use of natural language processing techniques.

## Modern Approaches and Applications

With the rise of [machine learning](https://www.wikiprompt.org/wiki/machine-learning) and [deep learning](https://www.wikiprompt.org/wiki/deep-learning), speech synthesis has shifted toward neural-based methods. [Neural networks](https://www.wikiprompt.org/wiki/neural-network) can model the complex mapping from text to speech directly, often producing more natural-sounding output than earlier concatenative or formant-based systems. These modern systems often leverage [transformer](https://www.wikiprompt.org/wiki/transformer) architectures, which are also foundational to [large language models](https://www.wikiprompt.org/wiki/large-language-model), to capture long-range dependencies in language and prosody.

Contemporary text-to-speech engines are widely deployed in consumer devices, navigation systems, and virtual assistants. Companies such as [Apple](https://www.wikiprompt.org/wiki/apple), [Samsung](https://www.wikiprompt.org/wiki/samsung-electronics), and [Google DeepMind](https://www.wikiprompt.org/wiki/google-deepmind) have integrated advanced synthesis into their products. The technology also supports accessibility features in operating systems, enabling screen readers for visually impaired users. As of the 2020s, research continues to focus on improving emotional expressiveness, voice cloning, and real-time synthesis for interactive applications.

## Evaluation and Challenges

Evaluating speech synthesizers involves both subjective listening tests and objective metrics. Subjective tests measure naturalness and intelligibility, often using mean opinion scores. Objective measures may compare acoustic features or use automatic speech recognition to assess clarity. Challenges remain in handling diverse languages, dialects, and speaking styles, as well as in reducing computational cost for on-device deployment. Ethical considerations also arise with the potential for voice spoofing and misuse of cloned voices, prompting ongoing discussion in the [generative AI](https://www.wikiprompt.org/wiki/generative-ai) community.

## External links

- [Wikipedia: Speech synthesis](https://en.wikipedia.org/wiki/Speech_synthesis)

---
Source: https://www.wikiprompt.org/wiki/speech-synthesis
License: CC BY-SA 4.0 (https://creativecommons.org/licenses/by-sa/4.0/)
Last updated: 2026-09-14T21:02:55.617253+00:00