Papers with Code 아카이브
Speech Recognition
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 11
- 평가표
- 236
- 보존된 평가 기록
- 398
Speech Recognition is the task of converting spoken language into text. It involves recognizing the words spoken in an audio recording and transcribing them into a written format. The goal is to accurately transcribe the speech in real-time or from recorded audio, taking into account factors such as accents, speaking speed, and background noise.
<span style="color:grey; opacity: 0.6">( Image credit: SpecAugment )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/ZhengkunTian/OpenTransformer
SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
https://github.com/ZhiqiWang12-hash/text_audio_classification
Learning Alignment for Multimodal Emotion Recognition from Speech
https://github.com/ZhouYuxuanYX/Wavenet-in-Keras-for-Kaggle-Competition-Web-Traffic-Time-Series-Forecasting
https://github.com/a-martyn/unet
https://github.com/aaaceo890/Attention
Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learning
https://github.com/aakashrkaku/seq2seq_hrar
Sequence-to-Sequence Modeling for Action Identification at High Temporal Resolution
https://github.com/aau-es-ml/ssl_noise-robust_kws
Keyword Transformer: A Self-Attention Model for Keyword Spotting
https://github.com/acetylSv/GST-tacotron
Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis
https://github.com/acids-ircam/diffusion_models
https://github.com/adamx97/Data-Science-Advanced-Capstone
A Simple Way to Initialize Recurrent Networks of Rectified Linear Units
https://github.com/adap/flower
Communication-Efficient Learning of Deep Networks from Decentralized Data
https://github.com/adelacvg/ns2vc
NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers
https://github.com/adityaagrawal7/speech-to-text-wavenet
https://github.com/adrienchaton/BERGAN
MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis
https://github.com/ag1988/dss
Efficiently Modeling Long Sequences with Structured State Spaces
https://github.com/agassi4013/Log-DenseNet-Tensorflow
https://github.com/agendd/rwkv-asr
An Embarrassingly Simple Approach for LLM with Strong ASR Capacity
https://github.com/ahmedalbahnasawy/spec_torch_kaldi-compatibility
SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
https://github.com/ahmetumutdurmus/zaremba
https://github.com/ai-agi/hicl
https://github.com/ai-unicamp/tts-objective-metrics
Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron
https://github.com/ai4bharat/indic-tts
Towards Building Text-To-Speech Systems for the Next Billion Users
https://github.com/aigc-audio/audiogpt
https://github.com/aimbsg/EVA4_S15
https://github.com/aizhiqi-work/MM-KWS
WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition
https://github.com/akommini/Spoken-Numeric-Digit-detection
Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition
https://github.com/albarji/neurowriter
https://github.com/albertfgu/diffwave-sashimi
https://github.com/alecokas/lattice_rnn
Bi-Directional Lattice Recurrent Neural Networks for Confidence Estimation
https://github.com/alexa/alexa-with-dstc10-track2-dataset
"How Robust r u?": Evaluating Task-Oriented Dialogue Systems on Spoken Conversations
https://github.com/alexa/wqa-cascade-transformers
Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges
https://github.com/alexandrujeman/dqn
https://github.com/alexjeman/dqn
https://github.com/alibaba-damo-academy/spokennlp
Sequence Model with Self-Adaptive Sliding Window for Efficient Spoken Document Segmentation
https://github.com/alicank/Translation-Augmented-LibriSpeech-Corpus
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.