Glossary

Search results

Avoidance Behaviour(also: Avoidance Behaviors, Covert Stuttering)

Strategies used by people who stutter to conceal or prevent stuttering events, including substituting feared words with easier alternatives, talking around a word (circumlocution), using filler words to delay, avoiding certain speaking situations entirely, or pretending to have…

Disfluency(also: Dysfluency, Speech Disfluency)

Any interruption or break in the normal flow of speech, including repetitions, prolongations, blocks, interjections (such as "um" or "uh"), and revisions. While all speakers experience occasional disfluencies, their frequency and severity distinguish typical speech from…

Dysfluency(also: Disfluency, Speech Dysfluency)

An interruption in the normal flow of speech, including repetitions of sounds, syllables, or words ("b-b-because"), prolongations of sounds ("ssssnake"), blocks (silent pauses where speech is temporarily stopped), and interjections ("um", "uh"). While occasional dysfluencies are…

Electrolarynx(also: Artificial Larynx, Electronic Larynx)

A handheld, battery-powered device that produces voice for people who have lost their larynx. The device is held against the neck or cheek and generates vibrations that travel through the throat tissues into the oral cavity, where the user shapes the vibration into speech using…

Endpoint Detection(also: Voice Activity Detection, VAD)

The process by which a speech-recognition system decides when a user has finished speaking, so the system can stop listening and send the captured audio for recognition. Off-the-shelf voice assistants typically use a silence threshold of 500ms-1s, which cuts off users who pause,…

Laryngectomy(also: Total Laryngectomy)

The surgical removal of the larynx (voice box), typically performed as treatment for advanced laryngeal or throat cancer. A total laryngectomy results in the permanent loss of the natural voice, as the vocal folds that produce speech are removed. The airway is also permanently…

Listening Window

The interval during which a voice assistant or speech-recognition system actively captures user audio after being activated (by wake word or button press). A short or fixed listening window causes premature cut-offs for users who pause while formulating speech — common for…

Silent Speech(also: Silent Speech Interface, SSI)

Communication technologies that generate intelligible speech from non-acoustic signals produced during the intent or attempt to speak, without requiring audible voicing. Input modalities include surface electromyography of articulatory muscles, ultrasound tongue imaging,…

Speech Diversity(also: Diverse Speech, Non-Typical Speech)

The full range of ways human speech varies from the narrow 'typical' speech on which most speech-AI systems are trained and benchmarked. Speech diversity includes people who stutter, d/Deaf and Hard-of-Hearing speakers, people with dysarthria, aphasia, or other neurological…

Speech-to-Speech(also: S2S, Speech-to-Speech Conversion)

A class of systems that transform one speech signal directly into another — for example, converting atypical input (whispered, dysarthric, accented, or cross-lingual speech) into clear, intelligible output in a target voice or language. Speech-to-speech systems differ from…

Stuttering(also: Stammering, Speech Disfluency Disorder)

A speech disorder characterized by involuntary disruptions in the flow of speech, including repetitions of sounds, syllables, or words (e.g., "w-w-water"), prolongations of sounds (e.g., "sssssnake"), and blocks where airflow is stopped and no sound is produced. Stuttering…

Voice Customization(also: Voice Personalization, Custom Voice)

The process of creating or modifying synthetic voices to match a user's preferences or identity, including attributes such as gender, age, pitch, breathiness, hoarseness, and speech variation. Voice customization is particularly important in accessibility for people with speech…

Whispered Speech(also: Whisper, Whispering)

A mode of speech production in which the vocal folds do not vibrate periodically; sound is generated by turbulent airflow through a narrow glottal opening. Whispered speech lacks a fundamental frequency and carries lower acoustic energy, which makes it harder for humans and for…

13 results.