the
∞
.ai
Search
/
Concepts
trail ·
0 nodes
Every concept
Speech
8 concepts, 8 reviewed and merged.
Compression
Neural Audio Codec
A codec turns a waveform into a small number of symbols and back again.
verified
Metrics
Word Error Rate
The standard score for a transcript: line the hypothesis up against the reference, count the words you had to…
verified
Objectives
CTC
Speech recognition has an alignment problem: you have the audio and you have the transcript, but not which frames…
verified
Recognition
Speech Recognition
Turning audio into text used to mean four separate models — acoustics, pronunciation, language, and a decoder to…
verified
Representation
Spectrogram
A waveform is tens of thousands of numbers a second and almost none of them mean anything alone.
verified
Speech Representation Learning
Transcribed speech is expensive and raw audio is nearly free.
verified
Serving
Streaming ASR
A transcript that arrives after you stop talking is a different product from one that appears as you speak.
verified
Synthesis
Text to Speech
Reading a sentence aloud is not one problem but two: deciding how it should sound, and producing a waveform that…
verified