{"total":543,"rows":[{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631,"area":"moe"},{"id":"2109.12894","title":"Training Spiking Neural Networks Using Lessons From Deep Learning","created":"2021-09-27","cited_by_count":259,"area":null},{"id":"2303.01037","title":"Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages","created":"2023-03-02","cited_by_count":231,"area":null},{"id":"2110.03370","title":"WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition","created":"2021-10-07","cited_by_count":197,"area":null},{"id":"2106.15561","title":"A Survey on Neural Speech Synthesis","created":"2021-06-29","cited_by_count":184,"area":null},{"id":"2206.08317","title":"Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition","created":"2022-06-16","cited_by_count":144,"area":null},{"id":"2111.01690","title":"Recent Advances in End-to-End Automatic Speech Recognition","created":"2021-11-02","cited_by_count":140,"area":null},{"id":"2301.08727","title":"Neural Architecture Search: Insights from 1000 Papers","created":"2023-01-20","cited_by_count":139,"area":null},{"id":"2303.03329","title":"End-to-End Speech Recognition: A Survey","created":"2023-03-03","cited_by_count":129,"area":null},{"id":"2203.12221","title":"Modality Competition: What Makes Joint Training of Multi-modal Network Fail in Deep Learning? (Provably)","created":"2022-03-23","cited_by_count":122,"area":null},{"id":"2601.21337","title":"Qwen3-ASR Technical Report","created":"2026-01-29","cited_by_count":118,"area":null},{"id":"2204.00895","title":"Class-Incremental Learning by Knowledge Distillation with Adaptive Feature Consolidation","created":"2022-04-02","cited_by_count":113,"area":"distill"},{"id":"2102.03216","title":"Intermediate Loss Regularization for CTC-based Speech Recognition","created":"2021-02-05","cited_by_count":96,"area":null},{"id":"2305.11013","title":"FunASR: A Fundamental End-to-End Speech Recognition Toolkit","created":"2023-05-18","cited_by_count":95,"area":null},{"id":"2207.02971","title":"Branchformer: Parallel MLP-Attention Architectures to Capture Local and Global Context for Speech Recognition and Understanding","created":"2022-07-06","cited_by_count":91,"area":null},{"id":"2311.00430","title":"Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labelling","created":"2023-11-01","cited_by_count":90,"area":"distill"},{"id":"2402.08846","title":"An Embarrassingly Simple Approach for LLM with Strong ASR Capacity","created":"2024-02-13","cited_by_count":88,"area":null},{"id":"2104.02133","title":"SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network","created":"2021-04-05","cited_by_count":83,"area":null},{"id":"2101.07597","title":"UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data","created":"2021-01-19","cited_by_count":77,"area":null},{"id":"2103.14636","title":"A Practical Survey on Faster and Lighter Transformers","created":"2021-03-26","cited_by_count":73,"area":null},{"id":"2109.06870","title":"Performance-Efficiency Trade-offs in Unsupervised Pre-training for Speech Recognition","created":"2021-09-14","cited_by_count":68,"area":null},{"id":"2110.07603","title":"Sub-word Level Lip Reading With Visual Attention","created":"2021-10-14","cited_by_count":63,"area":null},{"id":"2104.07163","title":"Annealing Knowledge Distillation","created":"2021-04-14","cited_by_count":61,"area":"distill"},{"id":"2205.13660","title":"Contextual Adapters for Personalized Speech Recognition in Neural Transducers","created":"2022-05-26","cited_by_count":57,"area":null},{"id":"2307.04172","title":"Can Generative Large Language Models Perform ASR Error Correction?","created":"2023-07-09","cited_by_count":57,"area":null},{"id":"2105.04949","title":"BERT is to NLP what AlexNet is to CV: Can Pre-Trained Language Models Identify Analogies?","created":"2021-05-11","cited_by_count":56,"area":null},{"id":"2111.03250","title":"Context-Aware Transformer Transducer for Speech Recognition","created":"2021-11-05","cited_by_count":56,"area":null},{"id":"2310.06434","title":"Whispering LLaMA: A Cross-Modal Generative Error Correction Framework for Speech Recognition","created":"2023-10-10","cited_by_count":56,"area":null},{"id":"2103.16775","title":"Attention, please! A survey of Neural Attention Models in Deep Learning","created":"2021-03-31","cited_by_count":51,"area":null},{"id":"2104.11462","title":"LeBenchmark: A Reproducible Framework for Assessing Self-Supervised Representation Learning from Speech","created":"2021-04-23","cited_by_count":47,"area":null},{"id":"2203.15455","title":"WeNet 2.0: More Productive End-to-End Speech Recognition Toolkit","created":"2022-03-29","cited_by_count":47,"area":null},{"id":"2103.09935","title":"Advancing RNN Transducer Technology for Speech Recognition","created":"2021-03-17","cited_by_count":44,"area":null},{"id":"2303.00456","title":"N-best T5: Robust ASR Error Correction using Multiple Input Hypotheses and Constrained Decoding Space","created":"2023-03-01","cited_by_count":42,"area":null},{"id":"2309.15701","title":"HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models","created":"2023-09-27","cited_by_count":42,"area":null},{"id":"2105.14779","title":"Towards One Model to Rule All: Multilingual Strategy for Dialectal Code-Switching Arabic ASR","created":"2021-05-31","cited_by_count":41,"area":null},{"id":"2111.01024","title":"With a Little Help from my Temporal Context: Multimodal Egocentric Action Recognition","created":"2021-11-01","cited_by_count":41,"area":null},{"id":"2106.08922","title":"Momentum Pseudo-Labeling for Semi-Supervised Speech Recognition","created":"2021-06-16","cited_by_count":40,"area":null},{"id":"2203.16844","title":"Open Source MagicData-RAMC: A Rich Annotated Mandarin Conversational(RAMC) Speech Dataset","created":"2022-03-31","cited_by_count":40,"area":null},{"id":"2102.12664","title":"MixSpeech: Data Augmentation for Low-resource Automatic Speech Recognition","created":"2021-02-25","cited_by_count":39,"area":null},{"id":"2201.12806","title":"Improving End-to-End Contextual Speech Recognition with Fine-Grained Contextual Knowledge Selection","created":"2022-01-30","cited_by_count":39,"area":null},{"id":"2102.01380","title":"Internal Language Model Training for Domain-Adaptive End-to-End Speech Recognition","created":"2021-02-02","cited_by_count":37,"area":null},{"id":"2406.06619","title":"LoRA-Whisper: Parameter-Efficient and Extensible Multilingual ASR","created":"2024-06-07","cited_by_count":36,"area":null},{"id":"2305.11408","title":"AlignAtt: Using Attention-based Audio-Translation Alignments as a Guide for Simultaneous Speech Translation","created":"2023-05-19","cited_by_count":35,"area":null},{"id":"2106.07803","title":"SynthASR: Unlocking Synthetic Data for Speech Recognition","created":"2021-06-14","cited_by_count":34,"area":null},{"id":"2202.01094","title":"RescoreBERT: Discriminative Speech Recognition Rescoring with BERT","created":"2022-02-02","cited_by_count":34,"area":null},{"id":"2109.00627","title":"Tree-constrained Pointer Generator for End-to-end Contextual Speech Recognition","created":"2021-09-01","cited_by_count":32,"area":null},{"id":"2110.01500","title":"Factorized Neural Transducer for Efficient Language Model Adaptation","created":"2021-09-27","cited_by_count":32,"area":null},{"id":"2212.07850","title":"Attention as a Guide for Simultaneous Speech Translation","created":"2022-12-15","cited_by_count":32,"area":null},{"id":"2102.07594","title":"Fast End-to-End Speech Recognition via Non-Autoregressive Models and Cross-Modal Knowledge Transferring from BERT","created":"2021-02-15","cited_by_count":31,"area":null},{"id":"2302.13750","title":"MoLE : Mixture of Language Experts for Multi-Lingual Automatic Speech Recognition","created":"2023-02-27","cited_by_count":31,"area":null},{"id":"2305.12493","title":"Contextualized End-to-End Speech Recognition with Contextual Phrase Prediction Network","created":"2023-05-21","cited_by_count":31,"area":null},{"id":"2102.09527","title":"Vision-Aided 6G Wireless Communications: Blockage Prediction and Proactive Handoff","created":"2021-02-18","cited_by_count":30,"area":null},{"id":"2105.00982","title":"On the limit of English conversational speech recognition","created":"2021-05-03","cited_by_count":30,"area":null},{"id":"2107.02268","title":"Instant One-Shot Word-Learning for Context-Specific Neural Sequence-to-Sequence Speech Recognition","created":"2021-07-05","cited_by_count":30,"area":null},{"id":"2203.15321","title":"Noise-robust Speech Recognition with 10 Minutes Unparalleled In-domain Data","created":"2022-03-29","cited_by_count":30,"area":null},{"id":"2101.11577","title":"Transformer Based Deliberation for Two-Pass Speech Recognition","created":"2021-01-27","cited_by_count":29,"area":null},{"id":"2204.13154","title":"Attention Mechanism in Neural Networks: Where it Comes and Where it Goes","created":"2022-04-27","cited_by_count":29,"area":null},{"id":"2107.05876","title":"A Configurable Multilingual Model is All You Need to Recognize All Languages","created":"2021-07-13","cited_by_count":28,"area":null},{"id":"2110.05249","title":"A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generation","created":"2021-10-11","cited_by_count":28,"area":null},{"id":"2304.14535","title":"Deep Transfer Learning for Automatic Speech Recognition: Towards Better Generalization","created":"2023-04-27","cited_by_count":28,"area":null},{"id":"2102.08036","title":"Exploring Transformers in Natural Language Generation: GPT, BERT, and XLNet","created":"2021-02-16","cited_by_count":27,"area":null},{"id":"2104.02775","title":"Looking into Your Speech: Learning Cross-modal Affinity for Audio-visual Speech Separation","created":"2021-03-25","cited_by_count":27,"area":null},{"id":"2509.08753","title":"Streaming Sequence-to-Sequence Learning with Delayed Streams Modeling","created":"2025-09-10","cited_by_count":27,"area":null},{"id":"2205.01086","title":"Wav2Seq: Pre-training Speech-to-Text Encoder-Decoder Models Using Pseudo Languages","created":"2022-05-02","cited_by_count":26,"area":null},{"id":"2307.05956","title":"Language-Routing Mixture of Experts for Multilingual and Code-Switching Speech Recognition","created":"2023-07-12","cited_by_count":26,"area":"moe"},{"id":"2104.05544","title":"Investigating Methods to Improve Language Model Integration for Attention-based Encoder-Decoder ASR Models","created":"2021-04-12","cited_by_count":25,"area":null},{"id":"2104.09426","title":"Advanced Long-context End-to-end Speech Recognition Using Context-expanded Transformers","created":"2021-04-19","cited_by_count":25,"area":null},{"id":"2110.02220","title":"Fast Contextual Adaptation with Neural Associative Memory for On-Device Personalized Speech Recognition","created":"2021-10-05","cited_by_count":25,"area":null},{"id":"2207.00555","title":"FitHuBERT: Going Thinner and Deeper for Knowledge Distillation of Speech Self-Supervised Learning","created":"2022-07-01","cited_by_count":25,"area":"distill"},{"id":"2210.05200","title":"CTC Alignments Improve Autoregressive Translation","created":"2022-10-11","cited_by_count":25,"area":null},{"id":"2103.09013","title":"Dense Interaction Learning for Video-based Person Re-identification","created":"2021-03-16","cited_by_count":24,"area":null},{"id":"2111.00161","title":"Pseudo-Labeling for Massively Multilingual Speech Recognition","created":"2021-10-30","cited_by_count":24,"area":null},{"id":"2409.09554","title":"ASR Error Correction using Large Language Models","created":"2024-09-14","cited_by_count":24,"area":null},{"id":"2201.02495","title":"Sign Language Video Retrieval with Free-Form Textual Queries","created":"2022-01-07","cited_by_count":23,"area":null},{"id":"2104.07253","title":"Integration of Pre-trained Networks with Continuous Token Interface for End-to-End Spoken Language Understanding","created":"2021-04-15","cited_by_count":22,"area":null},{"id":"2303.05759","title":"An Overview on Language Models: Recent Developments and Outlook","created":"2023-03-10","cited_by_count":22,"area":null},{"id":"2104.01616","title":"Towards Lifelong Learning of End-to-end ASR","created":"2021-04-04","cited_by_count":21,"area":null},{"id":"2205.10839","title":"Deep Learning for Visual Speech Analysis: A Survey","created":"2022-05-22","cited_by_count":21,"area":null},{"id":"2107.04954","title":"ReconVAT: A Semi-Supervised Automatic Music Transcription Framework for Low-Resource Real-World Data","created":"2021-07-11","cited_by_count":20,"area":null},{"id":"2111.10202","title":"Multimodal Emotion Recognition with High-level Speech and Text Features","created":"2021-09-29","cited_by_count":20,"area":null},{"id":"2206.14580","title":"Language-specific Characteristic Assistance for Code-switching Speech Recognition","created":"2022-06-29","cited_by_count":20,"area":null},{"id":"2104.02207","title":"Dissecting User-Perceived Latency of On-Device E2E Speech Recognition","created":"2021-04-06","cited_by_count":19,"area":null},{"id":"2104.11127","title":"Fast Text-Only Domain Adaptation of RNN-Transducer Prediction Network","created":"2021-04-22","cited_by_count":19,"area":null},{"id":"2105.00858","title":"On Addressing Practical Challenges for RNN-Transducer","created":"2021-04-27","cited_by_count":19,"area":null},{"id":"2106.02302","title":"Minimum Word Error Rate Training with Language Model Fusion for End-to-End Speech Recognition","created":"2021-06-04","cited_by_count":19,"area":null},{"id":"2202.07894","title":"Knowledge Transfer from Large-scale Pretrained Language Models to End-to-end Speech Recognizers","created":"2022-02-16","cited_by_count":19,"area":null},{"id":"2202.10290","title":"Speaker Adaptation Using Spectro-Temporal Deep Features for Dysarthric and Elderly Speech Recognition","created":"2022-02-21","cited_by_count":19,"area":null},{"id":"2401.10449","title":"Contextualized Automatic Speech Recognition with Attention-Based Bias Phrase Boosted Beam Search","created":"2024-01-19","cited_by_count":19,"area":null},{"id":"2401.15295","title":"Shortcuts Everywhere and Nowhere: Exploring Multi-Trigger Backdoor Attacks","created":"2024-01-27","cited_by_count":19,"area":null},{"id":"2406.06097","title":"StreamAtt: Direct Streaming Speech-to-Text Translation with Attention-based Audio History Selection","created":"2024-06-10","cited_by_count":19,"area":null},{"id":"2406.19954","title":"BESTOW: Efficient and Streamable Speech Language Model with the Best of Two Worlds in GPT and T5","created":"2024-06-28","cited_by_count":19,"area":null},{"id":"2210.13352","title":"ESB: A Benchmark For Multi-Domain End-to-End Speech Recognition","created":"2022-10-24","cited_by_count":18,"area":null},{"id":"2305.05271","title":"Robust Acoustic and Semantic Contextual Biasing in Neural Transducers for Speech Recognition","created":"2023-05-09","cited_by_count":18,"area":null},{"id":"2308.03266","title":"SeACo-Paraformer: A Non-Autoregressive ASR System with Flexible and Effective Hotword Customization Ability","created":"2023-08-07","cited_by_count":18,"area":null},{"id":"2410.20081","title":"emg2qwerty: A Large Dataset with Baselines for Touch Typing using Surface Electromyography","created":"2024-10-26","cited_by_count":18,"area":null},{"id":"2101.00240","title":"A Survey on Deep Reinforcement Learning for Audio-Based Applications","created":"2021-01-01","cited_by_count":17,"area":null},{"id":"2110.06841","title":"On Language Model Integration for RNN Transducer based Speech Recognition","created":"2021-10-13","cited_by_count":17,"area":null},{"id":"2111.00556","title":"Revealing and Protecting Labels in Distributed Training","created":"2021-10-31","cited_by_count":17,"area":null},{"id":"2201.05845","title":"Recent Progress in the CUHK Dysarthric Speech Recognition System","created":"2022-01-15","cited_by_count":17,"area":null},{"id":"2203.00888","title":"Towards Contextual Spelling Correction for Customization of End-to-end Speech Recognition Systems","created":"2022-03-02","cited_by_count":17,"area":null}],"next_cursor":"100"}