Loading your learn pack…
Read the summary, then start training!
Speech recognition converts spoken language into text or other interpretable forms, supporting applications like transcription and voice interfaces.
Speech recognition (automatic speech recognition, ASR; computer speech recognition; speech-to-text, STT) is a computational linguistics sub-field focused on methods and technologies that convert spoken language into text or other interpretable outputs. Its scope includes translating audio speech signals into symbolic representations (e.g., words or phonemes) and supporting downstream uses such as voice user interfaces, transcription, dictation, and searching within audio recordings. It can also support related tasks like analyzing speaker characteristics (e.g., native language cues) and, in a different but related area, voice recognition (speaker identification) for authentication or simplifying recognition when systems are trained for a particular speaker’s voice. Within its scope, speech recognition systems typically combine acoustic modeling (how speech sounds map to units) and language modeling (how word sequences are likely) to produce the most probable transcription. Historically, the field has evolved from early single-speaker and limited-vocabulary systems toward large-vocabulary, continuous, and speaker-independent recognition, with major progress driven by statistical models (notably hidden Markov models and dynamic time warping) and later by deep learning approaches (e.g., LSTMs, CTC-trained models, and attention-based transformers). Performance evaluation is commonly framed in terms of accuracy (such as word error rate) and speed, and recognition accuracy depends on factors like vocabulary size, speaker dependence, speech type (isolated vs. continuous), task constraints, and adverse conditions such as noise and echoes.
Speech recognition converts spoken language into text or other interpretable forms, supporting applications like transcription and voice interfaces.
The field’s scope spans acoustic and language modeling, and has progressed from statistical methods (HMM/DTW) to deep learning and attention-based approaches.
System performance is commonly measured by accuracy metrics (e.g., WER) and speed, with accuracy affected by vocabulary size, speaker dependence, speech type, and noise/distortion.
A field focused on converting spoken language audio into text or other interpretable outputs using computational methods.
The part of a speech recognition system that maps audio signals to speech units such as phonemes or sub-word units.
The part of a speech recognition system that estimates likely word sequences to improve transcription accuracy.
A statistical model that represents speech as a sequence of states and outputs, commonly used in speech recognition.
A sequence-alignment method that measures similarity between time-varying sequences and was historically used for speech recognition.
An accuracy metric that quantifies transcription errors by counting substitutions, deletions, and insertions relative to reference word count.
A set of tasks focused on identifying or verifying the speaker rather than recognizing the spoken content.
“Can you explain what "Speech recognition converts spoken language into text or other interpretable forms, supporting applications like transcription and voice interfaces." means in simple terms?”