Acoustic Model
An acoustic model is created by taking audio recordings of speech, and their text transcriptions, and using software to create statistical representations of the sounds that make up each word. It is used by a speech recognition engine to recognize speech.
Read more about Acoustic Model: Background, Speech Audio Characteristics, Telephony-based Speech Recognition, Desktop-based Speech Recognition
Famous quotes containing the word model:
“She represents the unavowed aspiration of the male human being, his potential infidelity—and infidelity of a very special kind, which would lead him to the opposite of his wife, to the “woman of wax” whom he could model at will, make and unmake in any way he wished, even unto death.”
—Marguerite Duras (b. 1914)