speech-to-text
Dictation software technology
Speech-to-text refers to technology that converts spoken language into written words, allowing computers and devices to transcribe what people say.
The technology powers voice assistants, dictation software, and accessibility tools for the deaf and hard of hearing.
I use speech-to-text to send messages while driving.
Also called voice recognition or speech recognition, though those terms sometimes emphasize identifying the speaker rather than transcribing their words.
Digital voice helper
- AlexaVirtual home assistant
- Google AssistantVoice-activated digital aide
- closed captionsOn-screen transcription of audio
- subtitlesOn-screen dialogue text
meeting notes · medical transcription · call center · customer service · voice search · smart speaker · hands-free · voice typing
Written version of speech
- voice recognitionTechnology identifying spoken language
- dictationOral text for writing
- NLPMachine language comprehension
- audio processingManipulation of sound signals
neural network · deep learning · language model · algorithm · API · real-time processing · machine learning · decoder
Program converting text to audio
- disabilityImpairment affecting life activities
- deafUnable to hear
- hard of hearingReduced auditory ability
- captioningAdding text to media
CART · assistive technology · accommodation · ADA · inclusion · hearing impairment · live transcription · equal access
Incorrectly identifying something
- homophoneIdentically pronounced, differently spelled word
- accentRegional speech pattern
- dialectRegional language variety
- background noiseIncidental surrounding sounds
clarity · pronunciation · enunciation · vocabulary · correction · editing · punctuation · noise cancellation
Siri
Digital voice helper
- AlexaVirtual home assistant
- Google AssistantVoice-activated digital aide
- closed captionsOn-screen transcription of audio
subtitles · meeting notes · medical transcription · call center · customer service · voice search · smart speaker · hands-free · voice typing · court reporter
transcription
Written version of speech
- voice recognitionTechnology identifying spoken language
- dictationOral text for writing
- NLPMachine language comprehension
audio processing · neural network · deep learning · language model · algorithm · API · real-time processing · machine learning · decoder · waveform
screen reader
Program converting text to audio
- disabilityImpairment affecting life activities
- deafUnable to hear
- hard of hearingReduced auditory ability
captioning · CART · assistive technology · accommodation · ADA · inclusion · hearing impairment · live transcription · equal access · subtitle
misrecognition
Incorrectly identifying something
- homophoneIdentically pronounced, differently spelled word
- accentRegional speech pattern
- dialectRegional language variety
background noise · clarity · pronunciation · enunciation · vocabulary · correction · editing · punctuation · noise cancellation · microphone
- accessibilitywheelchair access, wheelchair sports, wheelchair ramp, adaptive skiing, accessibility features
- language toolsdictionary, translation, translator, thesaurus, grammar books
- Transcriptiontranscript, transcriptionist, live transcription, verbatim, dictation
- accommodationsextra time, double time, time and a half, breaks, rest breaks
- Language Technologynatural language processing, NLP, machine translation, language model, language models
- NLPtokenization, natural language processing, NLP, parsing, stemming
speech-to-texttext-to-speech
Converting writing to audio
TTS · speech synthesis · voice synthesis · screen reader · audio output
speech-to-texttyping
Entering text via keyboard
manual typing · keyboard input · handwriting · touch typing · keyboarding