Learn Before
Feature Vector
The first step in ASR is to transform the input waveform into a sequence of acoustic feature vectors, where each vector represents the information in a small time window of the signal.
0
1
Contributors are:
Who are from:
Tags
Data Science
Related
Dimensions of ASR Variation
LibriSpeech
The Switchboard corpus
The CALLHOME corpus
CORALL
CHiME
The HKUST Mandarin Telephone Speech corpus
The AISHELL-1 corpus
Analog-to-digital Conversion
Automatic Speech Recognition Architecture
Word Error Rate
The Matched-Pair Sentence Segment Word Error (MAPSSWE) test
McNemar's test
Disadvantage of McNemar's test
Intelligent Assistants
Acoustic Waves
Related
Dimensions of ASR Variation
LibriSpeech
The Switchboard corpus
The CALLHOME corpus
CORALL
CHiME
The HKUST Mandarin Telephone Speech corpus
The AISHELL-1 corpus
Analog-to-digital Conversion
Automatic Speech Recognition Architecture
Word Error Rate
The Matched-Pair Sentence Segment Word Error (MAPSSWE) test
McNemar's test
Disadvantage of McNemar's test
Intelligent Assistants
Acoustic Waves