Papers with Code 아카이브
Automatic Speech Recognition (ASR)
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 9
- 보존된 평가 기록
- 20
Automatic Speech Recognition (ASR) involves converting spoken language into written text. It is designed to transcribe spoken words into text in real-time, allowing people to communicate with computers, mobile devices, and other technology using their voice. The goal of Automatic Speech Recognition is to accurately transcribe speech, taking into account variations in accent, pronunciation, and speaking style, as well as background noise and other factors that can affect speech quality.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/joseluis1061/neuralnilm
Neural NILM: Deep Neural Networks Applied to Energy Disaggregation
https://github.com/kabongosalomon/listra
Synchronous Speech Recognition and Speech-to-Text Translation with Interactive Decoding
https://github.com/kehanlu/Nemo
https://github.com/keonlee9420/Comprehensive-Transformer-TTS
Conformer: Convolution-augmented Transformer for Speech Recognition
https://github.com/kimjeongsun/specaugment
SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
https://github.com/kingjamessong/rankfeat
A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
https://github.com/kobybibas/pnml_ood_detection
A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
https://github.com/kssteven418/Q-ASR
Integer-only Zero-shot Quantization for Efficient Speech Recognition
https://github.com/kunato/mt3-pytorch
https://github.com/lRomul/argus-freesound
SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
https://github.com/lancopku/avg-avg
A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
https://github.com/levis0045/snips-nlu
https://github.com/lilianemomeni/KWS-Net
Zero-shot keyword spotting for visual speech recognition in-the-wild
https://github.com/lordmartian/deep_avsr
https://github.com/lucidrains/conformer
Conformer: Convolution-augmented Transformer for Speech Recognition
https://github.com/lucidrains/soundstorm-pytorch
Conformer: Convolution-augmented Transformer for Speech Recognition
https://github.com/lukesin/nas-for-kws-2
Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition
https://github.com/lumaku/ctc-segmentation
https://github.com/maxtimer97/ssm-inspired-lif
Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition
https://github.com/mbzuai-nlp/sttatts
SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing
https://github.com/mdangschat/speech-corpus-dl
TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptation
https://github.com/mimbres/yourmt3
https://github.com/mnm-rnd/elsa-voice-asr
https://github.com/mozilla/DeepSpeech
SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
https://github.com/mpc001/Visual_Speech_Recognition_for_Multiple_Languages
https://github.com/msalhab96/Conformer
Conformer: Convolution-augmented Transformer for Speech Recognition
https://github.com/msalhab96/SpeeQ
https://github.com/mu-y/diarist
Streaming Multi-Talker ASR with Token-Level Serialized Output Training
https://github.com/nanzhaogang/contrib/tree/master/application/similarity-of-neural-network-representations-revisited
https://github.com/nateanl/wpd-plus-plus
WPD++: An Improved Neural Beamformer for Simultaneous Speech Separation and Dereverberation
https://github.com/ncsoft/phonmatchnet
Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition
https://github.com/neil-zeng/asr
https://github.com/nhadidi/splashnet
emg2qwerty: A Large Dataset with Baselines for Touch Typing using Surface Electromyography
https://github.com/ogunlao/glowtts_stdp
Can we use Common Voice to train a Multi-Speaker TTS system?
https://github.com/oliverrose1998/Attention-Confidence
Bi-Directional Lattice Recurrent Neural Networks for Confidence Estimation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.