ASR Study

1.[ASR Study] # 1 Intro

post-thumbnail

2.[ASR Study] # 2-1 Phonetics

post-thumbnail

3.[ASR Study] # 2-2 Korean Phonology

post-thumbnail

4.[ASR Study] # 2-3 Recognition by Human

post-thumbnail

5.[ASR Study] # 3 Feature Extraction

post-thumbnail

6.[ASR Study] # Paper. WAV2VEC: UNSUPERVISED PRE-TRAINING FOR SPEECH RECOGNITION

post-thumbnail

7.[ASR Study] # Paper. SPEAKER RECOGNITION FROM RAW WAVEFORM WITH SINCNET

post-thumbnail

8.[ASR Study] # Basic Content. 음향 모델(Acoustic Model)

post-thumbnail

9.[ASR Study] # Paper. PASE: Learning Problem-agnostic Speech Representations from Multiple Self-supervised Tasks

post-thumbnail

10.[ASR Study] # Paper. Listen, Attend and Spell

post-thumbnail

11.[ASR Study] # Basic Content. 음향 모델(Acoustic Model) part2

post-thumbnail

12.[ASR Study] # Paper. Deep Speech 2 : End-to-End Speech Recognition in English and Mandarin

post-thumbnail

13.[ASR Study] # Paper: Speech Model Pre-training for End-to-End Spoken Language Understanding

post-thumbnail

14.[ASR Study] # Paper: Conformer: Convolution-augmented transformer for speech recognition

post-thumbnail