https://github.com/JusperLee/Deep-Clustering-for-Speech-Separation
Single-Channel Multi-Speaker Separation using Deep Clustering
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/KaiyangZhou/mixstyle-release
https://github.com/KathyReid/opensource-voice-tools
Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech Synthesis
https://github.com/KevinMIN95/StyleSpeech
FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
https://github.com/KimJeongSun/SpecAugment_numpy_scipy
SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
https://github.com/KinglittleQ/GST-Tacotron
Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis
https://github.com/Kodiologist/Citematic
https://github.com/Koukyosyumei/NAIST-FedML-Experiments
Communication-Efficient Learning of Deep Networks from Decentralized Data
https://github.com/KrishnaDN/E2E_ASR_Confidence_Estimation
Confidence Estimation for Attention-based Sequence-to-sequence Models for Speech Recognition
https://github.com/KrishnaDN/Keyword-Transformer
Keyword Transformer: A Self-Attention Model for Keyword Spotting
https://github.com/KumudaBG/Short-Story-Deep-Active-Learning
https://github.com/Kylin824/AndroidFLServer
Communication-Efficient Learning of Deep Networks from Decentralized Data
https://github.com/Kylin824/AndroidFederatedLearningServer
Communication-Efficient Learning of Deep Networks from Decentralized Data
https://github.com/Kyubyong/expressive_tacotron
Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis
https://github.com/Kyubyong/tacotron
https://github.com/L0SG/WaveFlow
https://github.com/LIAAD/KeywordExtractor-Datasets
https://github.com/LJKS/noplants
https://github.com/LeBenchmark/Interspeech2021
https://github.com/LeoSerena/MSThesis
Communication-Efficient Learning of Deep Networks from Decentralized Data
https://github.com/Loghijiaha/DeepSpeech-Indo
https://github.com/LucaHermes/lightweight-motion-forecasting
https://github.com/Lyhao0212/FedAvg
Communication-Efficient Learning of Deep Networks from Decentralized Data
https://github.com/MDSKUL/MasterProject
VideoBERT: A Joint Model for Video and Language Representation Learning
https://github.com/MJ-Jang/RNN_SVAE
Recurrent Neural Network-Based Semantic Variational Autoencoder for Sequence-to-Sequence Learning
https://github.com/MKegler/SpeechVGG
Word-level Embeddings for Cross-Task Transfer Learning in Speech Processing
https://github.com/MS-Mind/MS-Code-01/tree/main/speech_transformer
A Simplified Fully Quantized Transformer for End-to-end Speech Recognition
https://github.com/MS-Mind/MS-Code-02/tree/main/configs/convnext
https://github.com/MS-P3/code7/tree/main/unispeech_sat
UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data
https://github.com/MS-P3/code7/tree/main/univnet
https://github.com/MS-P3/code7/tree/main/wav2vec2_with_lm
https://github.com/MS-P3/code7/tree/main/wavlm
WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing
https://github.com/MS-P3/code7/tree/main/whisper
Reproducing Whisper-Style Training Using an Open-Source Toolkit and Publicly Available Data
https://github.com/MSRDL/Deep4Cast
https://github.com/MagicHub-io/Magic-Data-ASR-SD-Challenge
Conformer: Convolution-augmented Transformer for Speech Recognition
https://github.com/MangoMoe/VerbalVim
Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.