You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
78 lines
1.1 KiB
78 lines
1.1 KiB
3 years ago
|
# Features
|
||
4 years ago
|
|
||
|
3 years ago
|
### Dataset
|
||
|
|
* Aishell
|
||
|
|
* Librispeech
|
||
|
|
* THCHS30
|
||
|
|
* TIMIT
|
||
|
|
|
||
|
4 years ago
|
### Speech Recognition
|
||
|
|
|
||
|
3 years ago
|
* Non-Streaming
|
||
|
4 years ago
|
* [Baidu's DeepSpeech2](http://proceedings.mlr.press/v48/amodei16.pdf)
|
||
|
|
* [Transformer](https://arxiv.org/abs/1706.03762)
|
||
|
|
* [Conformer](https://arxiv.org/abs/2005.08100)
|
||
|
|
|
||
|
3 years ago
|
* Streaming
|
||
|
|
* [Baidu's DeepSpeech2](http://proceedings.mlr.press/v48/amodei16.pdf)
|
||
|
4 years ago
|
* [U2](https://arxiv.org/pdf/2012.05481.pdf)
|
||
|
|
|
||
|
|
### Language Model
|
||
|
|
|
||
|
|
* Ngram
|
||
|
|
|
||
|
|
### Decoder
|
||
|
|
|
||
|
|
* ctc greedy
|
||
|
|
* ctc prefix beam search
|
||
|
|
* greedy
|
||
|
|
* beam search
|
||
|
|
* attention rescore
|
||
|
|
|
||
|
3 years ago
|
### Deployment
|
||
|
|
|
||
|
|
* Paddle Inference
|
||
|
|
|
||
|
|
### Aligment
|
||
|
|
|
||
|
|
* MFA
|
||
|
|
* CTC Aligment
|
||
|
|
|
||
|
4 years ago
|
### Speech Frontend
|
||
|
|
|
||
|
|
* Audio
|
||
|
|
* Auto Gain
|
||
|
|
* Feature
|
||
|
|
* kaldi fbank
|
||
|
|
* kaldi mfcc
|
||
|
|
* linear
|
||
|
|
* delta detla
|
||
|
|
|
||
|
|
### Speech Augmentation
|
||
|
|
|
||
|
|
* Audio
|
||
|
|
- Volume Perturbation
|
||
|
|
- Speed Perturbation
|
||
|
|
- Shifting Perturbation
|
||
|
|
- Online Bayesian normalization
|
||
|
|
- Noise Perturbation
|
||
|
|
- Impulse Response
|
||
|
|
* Spectrum
|
||
|
|
- SpecAugment
|
||
|
|
- Adaptive SpecAugment
|
||
|
|
|
||
|
|
### Tokenizer
|
||
|
|
|
||
|
|
* Chinese/English Character
|
||
|
|
* English Word
|
||
|
|
* Sentence Piece
|
||
|
|
|
||
|
|
### Word Segmentation
|
||
|
|
|
||
|
|
* [mmseg](http://technology.chtsai.org/mmseg/)
|
||
|
|
|
||
|
|
### Grapheme To Phoneme
|
||
|
|
|
||
|
|
* syallable
|
||
|
4 years ago
|
* phoneme
|