Project: trace a speech and audio system
Sam is deaf, and his tablet should flash when the doorbell rings and caption the intercom. Build the chime detector from a spectrogram, then find out where the captions fail.
Lesson overview
Sam is deaf, and his tablet should flash when the doorbell rings and caption the intercom. Build the chime detector from a spectrogram, then find out where the captions fail.
What you’ll explore
- Build a spectrogram of a synthesized signal, detect a sound event from its pitch track, and compute word error rate by condition from reference and recognized transcripts.
Original explanations, connected to the research.
Robust Speech Recognition via Large-Scale Weak Supervision (Radford et al., 2022), the Whisper paperJurafsky and Martin: Speech and Language ProcessingPrepare a project review
Give someone the context to challenge your thinking.
Download the authored brief, deliverables, and review criteria with your notes. Use the worksheet for self or peer review. Project artifacts are ungraded here, and this review does not award mastery credit.
Suggest a correction
A precise note can make an explanation better.
Choose the scene and describe what needs attention. Download a feedback file to share through a channel you already use. This page does not send feedback or connect you with a reviewer.