https://github.com/seongho608/ringformer
Conformer: Convolution-augmented Transformer for Speech Recognition
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/sh951011/Korean-Speech-Recognition/blob/master/package/feature.py
SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
https://github.com/shehzeen/waveguard_defense
WaveGuard: Understanding and Mitigating Audio Adversarial Examples
https://github.com/shelling203/SpecAugment
SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
https://github.com/shuaijiang/Whisper-Finetune
SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
https://github.com/sinhat98/adapter-wavlm
Efficient Adapter Transfer of Self-Supervised Speech Models for Automatic Speech Recognition
https://github.com/smeetrs/deep_avsr
https://github.com/sonos/nlu-benchmark
https://github.com/sooftware/End-to-end-Speech-Recognition
State-of-the-art Speech Recognition With Sequence-to-Sequence Models
https://github.com/sooftware/OpenSpeech
https://github.com/sooftware/conformer
Conformer: Convolution-augmented Transformer for Speech Recognition
https://github.com/sooftware/sooftware
KoSpeech: Open-Source Toolkit for End-to-End Korean Speech Recognition
https://github.com/sooonwoo/RotNet-OOD
A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
https://github.com/spiritdjy/MixPaper
Natural Language Processing Advancements By Deep Learning: A Survey
https://github.com/srvk/eesen
EESEN: End-to-End Speech Recognition using Deep RNN Models and WFST-based Decoding
https://github.com/switchsyj/adae2ml-xsf
https://github.com/tae-jun/sampleaudio
Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition
https://github.com/thuiar/textoir
A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
https://github.com/thuiar/textoir-demo
A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
https://github.com/thuspmi/cat
https://github.com/tom-doerr/audio_adversarial_examples
Audio Adversarial Examples: Targeted Attacks on Speech-to-Text
https://github.com/toopster/dsc-capstone-project
Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition
https://github.com/trusthlt/dp-rewrite
https://github.com/tuanio/conformer-rnnt
Conformer: Convolution-augmented Transformer for Speech Recognition
https://github.com/tuanio/nextformer
Conformer: Convolution-augmented Transformer for Speech Recognition
https://github.com/tuanio/noisy-student-training-asr
Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition
https://github.com/tudarmstadt-lt/kaldi-tuda-de
https://github.com/ubc-nlp/udistilwhisper
To Distill or Not to Distill? On the Robustness of Robust Knowledge Distillation
https://github.com/unibe-cns/gle-code
Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition
https://github.com/unilight/seq2seq-vc
Pretraining Techniques for Sequence-to-Sequence Voice Conversion
https://github.com/upskyy/ContextNet
https://github.com/upskyy/Squeezeformer
Squeezeformer: An Efficient Transformer for Automatic Speech Recognition
https://github.com/upskyy/Transformer-Transducer
https://github.com/v-iashin/video_features
https://github.com/valerielimyh/Intent_Recognition_using_BERT
https://github.com/victor45664/espnet
FastEmit: Low-latency Streaming ASR with Sequence-level Emission Regularization
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.