Preprint
Speech Synthesis and Pronunciation Teaching
Waris Quamer et al., The Encyclopedia of Applied Linguistics, 2nd edition (in press), author preprint, 2024
Read the originalRead on October 17, 2026
- What it is
- A review chapter from Texas A&M University on computer-assisted pronunciation training. It explains why mispronunciation detection differs from speech recognition, and describes explicit corrective feedback for learners.
- How much weight it carries
- An author preprint of an encyclopedia chapter that was in press when we read it. It is a review and a design explanation, not a controlled study of learners, so use it to understand how the systems are built, not to measure how well a given app works.
Facts taken from this source
- A review chapter on pronunciation training says that speech recognition systems, such as those on Siri or Alexa, treat a learner's mispronunciations as noise, because their goal is to transcribe the sounds the speaker intended.
“An ASR system (such as those on Siri or Alexa) treats mispronunciations as noise; that is, the goal of ASR is to transcribe the intended sequence of sounds.” (Section 2, Explicit feedback via speech recognition)