https://github.com/sooftware/speech-recognition-tutorial
한국어 음성인식 튜토리얼
https://github.com/sooftware/speech-recognition-tutorial
Last synced: 2 months ago
JSON representation
한국어 음성인식 튜토리얼
- Host: GitHub
- URL: https://github.com/sooftware/speech-recognition-tutorial
- Owner: sooftware
- Created: 2020-07-29T16:43:09.000Z (almost 5 years ago)
- Default Branch: master
- Last Pushed: 2020-07-31T05:30:23.000Z (almost 5 years ago)
- Last Synced: 2025-01-24T06:13:25.879Z (4 months ago)
- Size: 16.2 MB
- Stars: 66
- Watchers: 2
- Forks: 11
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Speech Recognition Tutorial
한국어 음성 인식 프로젝트인 [KoSpeech](https://github.com/sooftware/KoSpeech) 프로젝트를 진행하며 팀원들끼리 스터디한 내용들을 공개한 repository입니다.
부족한 점이 많은 학부생들끼리 공부한 내용이니 잘못 이해한 부분이 있을 수 있습니다.
오류사항, 피드백 등 모두 환영합니다.
## Seminar
* [Signal Processing](https://github.com/sooftware/Speech-Recognition-Tutorial/blob/master/seminar/Signal-Processing.pdf)
* [Bayesian](https://github.com/sooftware/Speech-Recognition-Tutorial/blob/master/seminar/Bayesian.pdf)
* [Mel Frequency Cepstral Coefficients (MFCC)](https://github.com/sooftware/Speech-Recognition-Tutorial/blob/master/seminar/MFCC.pdf)
* [Convolutional Neura Network (CNN)](https://github.com/sooftware/Speech-Recognition-Tutorial/blob/master/seminar/CNN.pdf)
* [Gradient Descent Optimization Algorithms](https://github.com/sooftware/Speech-Recognition-Tutorial/blob/master/seminar/GradientDescentOptimizer.pdf)
* [Recurrent Neural Network (RNN)](https://github.com/sooftware/Speech-Recognition-Tutorial/blob/master/seminar/RNN.pdf)
* [LSTM & GRU](https://github.com/sooftware/Speech-Recognition-Tutorial/blob/master/seminar/LSTM_and_GRU.pdf)
* [Bidirectional LSTM](https://github.com/sooftware/Speech-Recognition-Tutorial/blob/master/seminar/BLSTM.pdf)
* [Sequence-to-Sequence](https://github.com/sooftware/Speech-Recognition-Tutorial/blob/master/seminar/Seq2seq.pdf)
* [Teacher Forcing](https://github.com/sooftware/Speech-Recognition-Tutorial/blob/master/seminar/Teacher%20Forcing.pdf)
* [Attention Mechanism](https://github.com/sooftware/Speech-Recognition-Tutorial/blob/master/seminar/Attention-Mechanism.pdf)
* [Listen, Attend and Spell](https://github.com/sooftware/Speech-Recognition-Tutorial/blob/master/seminar/Listen%2C%20Attend%20and%20Spell.pdf)
* [Attention Based Models for Speech Recognition](https://github.com/sooftware/Speech-Recognition-Tutorial/blob/master/seminar/Attention-Based%20Models%20for%20Speech%20Recognition.pdf)
* [Attention Is All You Need](https://github.com/sooftware/Speech-Recognition-Tutorial/blob/master/seminar/Attention%20Is%20All%20You%20Need.pdf)
* [SpecAugment](https://github.com/sooftware/Speech-Recognition-Tutorial/blob/master/seminar/SpecAugmentation.pdf)
* [Learning rate Scheduling & Label Smoothing](https://github.com/sooftware/Speech-Recognition-Tutorial/blob/master/seminar/Learning%20Rate%20Schedule%20%26%20Label%20Smoothing.pdf)
* [Language Model & Fusinging](https://github.com/sooftware/Speech-Recognition-Tutorial/blob/master/seminar/LM-%26-Fusioning.pdf)
* [Perplexity](https://github.com/sooftware/Speech-Recognition-Tutorial/blob/master/seminar/Perplexity.pdf)
* [An Analysis of Incorporating an External Language Model Into Sequence-to-Sequence Model](https://github.com/sooftware/Speech-Recognition-Tutorial/blob/master/seminar/Incorporating%20an%20External%20LM%20into%20A%20seq2seq%20Model.pdf)
* [Ensemble](https://github.com/sooftware/Speech-Recognition-Tutorial/blob/master/seminar/Ensemble.pdf)
* [Word Embedding](https://github.com/sooftware/Speech-Recognition-Tutorial/blob/master/seminar/Word-Embedding.pdf)
## Paper Review
* [Listen, Attend and Spell](https://github.com/sooftware/Speech-Recognition-Tutorial/blob/master/paper-review/Listen%2C%20Attend%20and%20Spell.md)
* [Deep Speech](https://github.com/sooftware/Speech-Recognition-Tutorial/blob/master/paper-review/Deep%20Speech-Scaling%20up%20end-to-end%20speech%20recognition.md)
* [Attention Based Models for Speech Recognition](https://github.com/sooftware/Speech-Recognition-Tutorial/blob/master/paper-review/Attention-Based%20Models%20for%20Speech%20Recognition.md)
* [Attention Is All You Need](https://github.com/sooftware/Speech-Recognition-Tutorial/blob/master/paper-review/Attention%20Is%20All%20You%20Need.md)
* [AN ANALYSIS OF INCORPORATING AN EXTERNAL LANGUAGE MODEL INTO A SEQUENCE-TO-SEQUENCE MODEL](https://github.com/sooftware/Speech-Recognition-Tutorial/blob/master/paper-review/An%20Analysis%20Of%20Incorporating%20An%20External%20Language%20Model%20Into%20A%20Sequence-to-Sequence%20Model.md)
* [STATE-OF-THE-ART SPEECH RECOGNITION WITH SEQUENCE-TO-SEQUENCE MODE](https://github.com/sooftware/Speech-Recognition-Tutorial/blob/master/paper-review/State%20Of%20The%20Art%20Speech%20Recognition%20with%20Sequence%20to%20Sequence%20Models.md)
* [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://github.com/sooftware/Speech-Recognition-Tutorial/blob/master/paper-review/A%20Simple%20Data%20Augmentation%20Method%20for%20Automatic%20Speech%20Recognition.md)
* [ClovaCall: Korean Goal-Oriented Dialog Speech Corpus for Automatic Speech Recognition of Contact Centers](https://github.com/sooftware/Speech-Recognition-Tutorial/blob/master/paper-review/ClovaCall%20-%20Korean%20Goal-Oriented%20Dialog%20Speech%20Corpus%20for%20Automatic%20Speech%20Recognition%20of%20Contact%20Centers.md)
## Author
[Soohwan Kim](https://github.com/sooftware), [Seyoung Bae](https://github.com/triplet02), [Cheolhwang Won](https://github.com/wch18735)