Blog posts

2021

[Paper-ASR][中文笔记] A Comparative Study on Neural Architectures and Training Methods for Japanese Speech Recognition

4 minute read

Published: July 04, 2021

Last Updated: 2021-07-04

[Paper-ASR][中文笔记] 用于语音识别的无监督字符级分布适配 (CMatch)

less than 1 minute read

Published: June 07, 2021

Last Updated: 2021-07-04

2020

[Collection] Papers, Recipes, Toolkits and Interesting Posts

20 minute read

Published: December 10, 2020

Last Updated: 2020-12-10

PyTorch模型部署踩坑记录

less than 1 minute read

Published: August 14, 2020

Last Updated: 2020-08-14

[Paper-NLP] Meta-Learning for Low-Resource Neural Machine Translation

8 minute read

Published: August 11, 2020

Last Updated: 2020-08-12

[Paper-NLP] Get To The Point: Summarization with Pointer-Generator Networks

9 minute read

Published: July 09, 2020

Last Updated: 2020-08-11

[Paper-Vocoder] WaveNet: A Generative Model for Raw Audio

16 minute read

Published: July 04, 2020

Last Updated: 2020-07-04

[Paper-PreTrain] wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations

18 minute read

Published: June 27, 2020

Last Updated: 2020-06-28

[Paper-NLP] URIEL and lang2vec: Representing languages as typological, geographical, and phylogenetic vectors

7 minute read

Published: June 24, 2020

Last Updated: 2020-06-24

[Paper-ST] Phone Features Improve Speech Translation

8 minute read

Published: June 05, 2020

Last Updated: 2020-06-09

[Paper-PreTrain] Big Transfer (BiT):General Visual Representation Learning

9 minute read

Published: May 23, 2020

Last Updated: 2020-05-26

[Paper-PreTrain] BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

14 minute read

Published: May 03, 2020

Last Updated: 2020-06-13

[Paper-PreTrain] Wav2Vec: Unsupervised Pre-Training For Speech Recognition

12 minute read

Published: April 04, 2020

Last Updated: 2020-04-29

[Paper-PreTrain] Representation Learning with Contrastive Predictive Coding

13 minute read

Published: April 04, 2020

Last Updated: 2020-04-13

[Paper-AST] SkinAugment: Auto-Encoding Speaker Conversions For Automatic Speech Translation

4 minute read

Published: April 02, 2020

Last Updated: 2020-04-03

[Paper-S2ST] Direct speech-to-speech translation with a sequence-to-sequence model

7 minute read

Published: April 02, 2020

Last Updated: 2020-04-02

Understanding and implementing Transformer from scratch

8 minute read

Published: March 31, 2020

Last Updated: 2020-04-01

[Collection] Large-Scale Model Training Related Papers & Repos.

less than 1 minute read

Published: March 05, 2020

Last Updated: 2020-03-05

[ASR] Basic concepts of speech recognition

less than 1 minute read

Published: February 28, 2020

Last Updated: 2020-06-11

[Technique] SegSNR: Properly add noise to synthesized speech

2 minute read

Published: January 17, 2020

Last Updated: 2020-01-17

Hello World 2020

less than 1 minute read

Published: January 02, 2020

Last Updated: 2020-01-02