ASR progress report(Wang, Yi-Ling) Server Server IP 1 ssh lenny@140.113.170.49 -p 20203 3 ssh lenny@140.113.170.46 -p 10201 ML-public Click Running SpeechTransformer ICAASP2018 Pending RNN-T Structure Transofrmer RNN-T Reference Code Name Language Developer Speech-Transformer Pytorch - Speech-Transformer Pytorch&Kaldi - Online-Speech-Recognition(RNN-T) Pytorch - PaperWithCode Title Paper Code Source Longformer: The Long-Document Transformer Link Pytorch – - Linformer: Self-Attention with Linear Complexity Link Pytorch1 、 Pytorch2 Facebook Speech-Transformer: A No-Recurrence Sequence-to-Sequence Model for Speech Recognition Link Pytorch1 、 Pytorch2 ICASSP 2018 Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention Link Pytorch1 、 Pytorch2 ICML 2020 Fast Transformers with Clustered Attention Link Pytorch – - Star-Transformer Link Pytorch NAACL 2019 Lite Transformer with Long-Short Range Attention Link Pytorch 、 ICLR 2020 Encoding word order in complex embeddings Link Pytorch ICLR 2020 Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks Link Pytorch ICML 2019 Funnel-Transformer: Filtering out Sequential Redundancy for Efficient Language Processing Link 、 中文版 Pytorch Google、CMU Adaptive Attention Span in Transformers Link Pytorch Facebook、ACL 2019 Transformer-XL Link Pytorch ACL 2019 Techinque Name Publisher SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition Interspeech 2019 ? Semantic Mask for Transformer based End-to-End Speech Recognition Microsoft Research ? Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks Google ? State-of-the-art Speech Recognition With Sequence-to-Sequence Models Google ICASSP2019 SYNTHESIZER: Rethinking Self-Attention in Transformer Models ] Google ICLR2021 CP-GAN: CONTEXT PYRAMID GENERATIVE ADVERSARIAL NETWORK FOR SPEECH ENHANCEMENT ] Group meeting ICASSP 2020 Dataset Corpus Language AI Shell Chinese Librispeech English WSJ English Switchboard English Benchmark Result: Corpus Librispeech ICML Learning to Encode Position for Transformer with Continuous Dynamical Model Improving the Gating Mechanism of Recurrent Neural Network EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks Stabilizing Transformers for Reinforcement Learning Interspeech Improving Transformer-based End-to-End Speech Recognition with Connectionist Temporal Classification and Language Model Integration Automatic Spelling Correction with Transformer for CTC-based End-to-End Speech Recognition Git Transformer-based online speech recognition system with TensorFlow 2 Reference(Net) Attention_reform1 Attention_reform2 ICLR 2020 Trend of Transformer IBM_transformer Mix https://blog.csdn.net/qq_37236745/article/details/107352273?utm_medium=distribute.pc_relevant.none-task-blog-title-6&spm=1001.2101.3001.4242 Old Releated Paper Name Instution Source Listen, attend and spell: A neural network for large vocabulary conversational speech recognition CMU Google ICASSP2016 A Comparison of Sequence-to-Sequence Models for Speech Recognition Google Interspeech 2017 A comparable study of modeling units for end-to-end Mandarin speech recognition Didi ISCSLP2018* Reference Code Name Language Developer LAS_Mandarin_PyTorch Pytorch LAS End-to-end-ASR-Pytorch Pytorch LAS LAS Structure Structure LAS(Listen, Attend and Spell)