{"total":100,"rows":[{"id":"2102.01192","title":"Generative Spoken Language Modeling from Raw Audio","created":"2021-02-01","cited_by_count":340,"area":null},{"id":"2205.10643","title":"Self-Supervised Speech Representation Learning: A Review","created":"2022-05-21","cited_by_count":260,"area":null},{"id":"2105.11084","title":"Unsupervised Speech Recognition","created":"2021-05-24","cited_by_count":148,"area":null},{"id":"2408.08252","title":"Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-Based Decoding","created":"2024-08-15","cited_by_count":136,"area":"diffusion"},{"id":"2303.03329","title":"End-to-End Speech Recognition: A Survey","created":"2023-03-03","cited_by_count":129,"area":null},{"id":"2306.17806","title":"Stay on topic with Classifier-Free Guidance","created":"2023-06-30","cited_by_count":91,"area":null},{"id":"2106.04149","title":"To Smooth or Not? When Label Smoothing Meets Noisy Labels","created":"2021-06-08","cited_by_count":70,"area":null},{"id":"2104.00676","title":"Is Label Smoothing Truly Incompatible with Knowledge Distillation: An Empirical Study","created":"2021-04-01","cited_by_count":51,"area":"distill"},{"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":"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":"2503.02039","title":"Dynamic Search for Inference-Time Alignment in Diffusion Models","created":"2025-03-03","cited_by_count":37,"area":"diffusion"},{"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":"2206.14532","title":"Revisiting Label Smoothing and Knowledge Distillation Compatibility: What was Missing?","created":"2022-06-29","cited_by_count":32,"area":"distill"},{"id":"2104.05788","title":"Spatially Varying Label Smoothing: Capturing Uncertainty from Expert Annotations","created":"2021-04-12","cited_by_count":31,"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":"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":"2210.07353","title":"JOIST: A Joint Speech and Text Streaming Model For ASR","created":"2022-10-13","cited_by_count":24,"area":null},{"id":"2103.06716","title":"Learning Word-Level Confidence For Subword End-to-End ASR","created":"2021-03-11","cited_by_count":22,"area":null},{"id":"2204.12031","title":"Boundary Smoothing for Named Entity Recognition","created":"2022-04-26","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":"2402.05457","title":"It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition","created":"2024-02-08","cited_by_count":22,"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":"2110.01857","title":"ASR Rescoring and Confidence Estimation with ELECTRA","created":"2021-10-05","cited_by_count":16,"area":null},{"id":"2305.12839","title":"CopyNE: Better Contextual ASR by Copying Named Entities","created":"2023-05-22","cited_by_count":14,"area":null},{"id":"2306.08133","title":"Large-scale Language Model Rescoring on Long-form Data","created":"2023-06-13","cited_by_count":14,"area":null},{"id":"2402.05467","title":"Rapid Optimization for Jailbreaking LLMs via Subconscious Exploitation and Echopraxia","created":"2024-02-08","cited_by_count":14,"area":"safety"},{"id":"2310.06549","title":"Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion Attacks","created":"2023-10-10","cited_by_count":13,"area":null},{"id":"2204.07553","title":"Improving Rare Word Recognition with LM-aware MWER Training","created":"2022-04-15","cited_by_count":12,"area":null},{"id":"2205.09058","title":"Minimising Biasing Word Errors for Contextual ASR with the Tree-Constrained Pointer Generator","created":"2022-05-18","cited_by_count":11,"area":null},{"id":"2210.16663","title":"BERT Meets CTC: New Formulation of End-to-End Speech Recognition with Pre-trained Masked Language Model","created":"2022-10-29","cited_by_count":11,"area":null},{"id":"2104.02219","title":"Understanding Medical Conversations: Rich Transcription, Confidence Scores & Information Extraction","created":"2021-04-06","cited_by_count":10,"area":null},{"id":"2110.14432","title":"Iterative Teaching by Label Synthesis","created":"2021-10-27","cited_by_count":10,"area":null},{"id":"2302.08917","title":"Massively Multilingual Shallow Fusion with Large Language Models","created":"2023-02-17","cited_by_count":10,"area":null},{"id":"2103.14152","title":"Residual Energy-Based Models for End-to-End Speech Recognition","created":"2021-03-25","cited_by_count":9,"area":null},{"id":"2201.11627","title":"Internal Language Model Estimation Through Explicit Context Vector Learning for Attention-based Encoder-decoder ASR","created":"2022-01-26","cited_by_count":9,"area":null},{"id":"2310.00178","title":"Contextual Biasing with the Knuth-Morris-Pratt Matching Algorithm","created":"2023-09-29","cited_by_count":9,"area":null},{"id":"2406.07698","title":"Label Smoothing Improves Machine Unlearning","created":"2024-06-11","cited_by_count":9,"area":"safety"},{"id":"2104.04487","title":"Language model fusion for streaming end to end speech recognition","created":"2021-04-09","cited_by_count":8,"area":null},{"id":"2305.11558","title":"Blank-regularized CTC for Frame Skipping in Neural Transducer","created":"2023-05-19","cited_by_count":8,"area":null},{"id":"2406.11025","title":"Large Language Models for Dysfluency Detection in Stuttered Speech","created":"2024-06-16","cited_by_count":8,"area":null},{"id":"2202.06045","title":"USTED: Improving ASR with a Unified Speech and Text Encoder-Decoder","created":"2022-02-12","cited_by_count":7,"area":null},{"id":"2203.14962","title":"Learning to segment fetal brain tissue from noisy annotations","created":"2022-03-25","cited_by_count":7,"area":null},{"id":"2509.09987","title":"Whisper Has an Internal Word Aligner","created":"2025-09-12","cited_by_count":7,"area":null},{"id":"2106.05111","title":"A Comparative Study on Neural Architectures and Training Methods for Japanese Speech Recognition","created":"2021-06-09","cited_by_count":6,"area":null},{"id":"2209.02030","title":"Distilling the Knowledge of BERT for CTC-based ASR","created":"2022-09-05","cited_by_count":6,"area":null},{"id":"2209.04062","title":"Non-autoregressive Error Correction for CTC-based ASR with Phone-conditioned Masked LM","created":"2022-09-08","cited_by_count":6,"area":null},{"id":"2201.03655","title":"A Likelihood Ratio based Domain Adaptation Method for E2E Models","created":"2022-01-10","cited_by_count":5,"area":null},{"id":"2210.12214","title":"Optimizing Bilingual Neural Transducer with Synthetic Code-switching Text Generation","created":"2022-10-21","cited_by_count":5,"area":null},{"id":"2212.10258","title":"In and Out-of-Domain Text Adversarial Robustness via Label Smoothing","created":"2022-12-20","cited_by_count":5,"area":null},{"id":"2405.15216","title":"Revisiting ASR Error Correction with Specialized Models","created":"2024-05-24","cited_by_count":5,"area":null},{"id":"2107.01275","title":"Relaxed Attention: A Simple Method to Boost Performance of End-to-End Automatic Speech Recognition","created":"2021-07-02","cited_by_count":4,"area":null},{"id":"2107.01569","title":"Cross-Modal Transformer-Based Neural Correction Models for Automatic Speech Recognition","created":"2021-07-04","cited_by_count":4,"area":null},{"id":"2109.04783","title":"Self-Attention Channel Combinator Frontend for End-to-End Multichannel Far-field Speech Recognition","created":"2021-09-10","cited_by_count":4,"area":null},{"id":"2109.06253","title":"Multi-Sentence Resampling: A Simple Approach to Alleviate Dataset Length Bias and Beam-Search Degradation","created":"2021-09-13","cited_by_count":4,"area":null},{"id":"2112.00499","title":"Structure-Aware Label Smoothing for Graph Neural Networks","created":"2021-12-01","cited_by_count":4,"area":null},{"id":"2206.07277","title":"A Gift from Label Smoothing: Robust Training with Adaptive Label Smoothing via Auxiliary Classifier under Label Noise","created":"2022-06-15","cited_by_count":4,"area":null},{"id":"2211.00325","title":"Speech-text based multi-modal training with bidirectional attention for improved speech recognition","created":"2022-11-01","cited_by_count":4,"area":null},{"id":"2212.04205","title":"DC-MBR: Distributional Cooling for Minimum Bayesian Risk Decoding","created":"2022-12-08","cited_by_count":4,"area":null},{"id":"2212.09512","title":"Rethinking Label Smoothing on Multi-hop Question Answering","created":"2022-12-19","cited_by_count":4,"area":null},{"id":"2303.10942","title":"On-the-fly Text Retrieval for End-to-End ASR Adaptation","created":"2023-03-20","cited_by_count":4,"area":null},{"id":"2408.16180","title":"Benchmarking Japanese Speech Recognition on ASR-LLM Setups with Multi-Pass Augmented Generative Error Correction","created":"2024-08-29","cited_by_count":4,"area":null},{"id":"2102.09928","title":"Do End-to-End Speech Recognition Models Care About Context?","created":"2021-02-17","cited_by_count":3,"area":null},{"id":"2106.13913","title":"Midpoint Regularization: from High Uncertainty Training to Conservative Classification","created":"2021-06-26","cited_by_count":3,"area":null},{"id":"2112.02353","title":"Label Hierarchy Transition: Delving into Class Hierarchies to Enhance Deep Classifiers","created":"2021-12-04","cited_by_count":3,"area":null},{"id":"2212.09982","title":"Joint Speech Transcription and Translation: Pseudo-Labeling with Out-of-Distribution Data","created":"2022-12-20","cited_by_count":3,"area":null},{"id":"2401.11700","title":"Keep Decoding Parallel with Effective Knowledge Distillation from Language Models to End-to-end Speech Recognisers","created":"2024-01-22","cited_by_count":3,"area":"distill"},{"id":"2412.15299","title":"LAMA-UT: Language Agnostic Multilingual ASR through Orthography Unification and Language-Specific Transliteration","created":"2024-12-19","cited_by_count":3,"area":null},{"id":"2110.08731","title":"Improving End-To-End Modeling for Mispronunciation Detection with Effective Augmentation Mechanisms","created":"2021-10-17","cited_by_count":2,"area":null},{"id":"2203.08390","title":"Reducing Flipping Errors in Deep Neural Networks","created":"2022-03-16","cited_by_count":2,"area":null},{"id":"2203.15176","title":"Improving Generalization of Deep Neural Network Acoustic Models with Length Perturbation and N-best Based Label Smoothing","created":"2022-03-29","cited_by_count":2,"area":null},{"id":"2206.14623","title":"Contextual Density Ratio for Language Model Biasing of Sequence to Sequence ASR Systems","created":"2022-06-29","cited_by_count":2,"area":null},{"id":"2301.12589","title":"Confidence-Aware Calibration and Scoring Functions for Curriculum Learning","created":"2023-01-29","cited_by_count":2,"area":null},{"id":"2305.08501","title":"Label Smoothing is Robustification against Model Misspecification","created":"2023-05-15","cited_by_count":2,"area":null},{"id":"2305.17304","title":"External Language Model Integration for Factorized Neural Transducers","created":"2023-05-26","cited_by_count":2,"area":null},{"id":"2310.03283","title":"A Formalism and Approach for Improving Robustness of Large Language Models Using Risk-Adjusted Confidence Scores","created":"2023-10-05","cited_by_count":2,"area":null},{"id":"2406.09950","title":"An efficient text augmentation approach for contextualized Mandarin speech recognition","created":"2024-06-14","cited_by_count":2,"area":null},{"id":"2102.05131","title":"Label Smoothed Embedding Hypothesis for Out-of-Distribution Detection","created":"2021-02-09","cited_by_count":1,"area":null},{"id":"2107.00635","title":"StableEmit: Selection Probability Discount for Reducing Emission Latency of Streaming Monotonic Attention ASR","created":"2021-07-01","cited_by_count":1,"area":null},{"id":"2110.10429","title":"Knowledge distillation from language model to acoustic model: a hierarchical multi-task learning approach","created":"2021-10-20","cited_by_count":1,"area":"distill"},{"id":"2204.02023","title":"A Complementary Joint Training Approach Using Unpaired Speech and Text for Low-Resource Automatic Speech Recognition","created":"2022-04-05","cited_by_count":1,"area":null},{"id":"2208.02402","title":"Fusing Sentence Embeddings Into LSTM-based Autoregressive Language Models","created":"2022-08-04","cited_by_count":1,"area":null},{"id":"2303.15293","title":"A Deliberation-based Joint Acoustic and Text Decoder","created":"2023-03-23","cited_by_count":1,"area":null},{"id":"2305.19498","title":"Perception and Semantic Aware Regularization for Sequential Confidence Calibration","created":"2023-05-31","cited_by_count":1,"area":null},{"id":"2310.11010","title":"Iterative Shallow Fusion of Backward Language Model for End-to-End Speech Recognition","created":"2023-10-17","cited_by_count":1,"area":null},{"id":"2402.06614","title":"The Complexity of Sequential Prediction in Dynamical Systems","created":"2024-02-09","cited_by_count":1,"area":null},{"id":"2502.05232","title":"Aligner-Encoders: Self-Attention Transformers Can Be Self-Transducers","created":"2025-02-06","cited_by_count":1,"area":null},{"id":"2503.18023","title":"Regularization of ML models for Earth systems by using longer model timesteps","created":"2025-03-23","cited_by_count":1,"area":null},{"id":"2507.12252","title":"Improving Contextual ASR via Multi-grained Fusion with Large Language Models","created":"2025-07-16","cited_by_count":1,"area":null},{"id":"2104.05547","title":"WHOSe Heritage: Classification of UNESCO World Heritage \"Outstanding Universal Value\" Documents with Soft Labels","created":"2021-04-12","cited_by_count":0,"area":null},{"id":"2107.09625","title":"Learning ULMFiT and Self-Distillation with Calibration for Medical Dialogue System","created":"2021-07-20","cited_by_count":0,"area":"distill"},{"id":"2108.13822","title":"Chi-square Loss for Softmax: an Echo of Neural Network Structure","created":"2021-08-31","cited_by_count":0,"area":null},{"id":"2111.12495","title":"Altering Backward Pass Gradients improves Convergence","created":"2021-11-24","cited_by_count":0,"area":null},{"id":"2211.00795","title":"InterMPL: Momentum Pseudo-Labeling with Intermediate CTC Loss","created":"2022-11-02","cited_by_count":0,"area":null},{"id":"2305.04971","title":"LABO: Towards Learning Optimal Label Regularization via Bi-level Optimization","created":"2023-05-08","cited_by_count":0,"area":null},{"id":"2306.06954","title":"Multi-View Frequency-Attention Alternative to CNN Frontends for Automatic Speech Recognition","created":"2023-06-12","cited_by_count":0,"area":null},{"id":"2410.21885","title":"Self-Relaxed Joint Training: Sample Selection for Severity Estimation with Ordinal Noisy Labels","created":"2024-10-29","cited_by_count":0,"area":null},{"id":"2501.03257","title":"Breaking Through the Spike: Spike Window Decoding for Accelerated and Precise Automatic Speech Recognition","created":"2025-01-01","cited_by_count":0,"area":null},{"id":"2502.10058","title":"MTLM: Incorporating Bidirectional Text Information to Enhance Language Model Training in Speech Recognition Systems","created":"2025-02-14","cited_by_count":0,"area":null},{"id":"2508.14077","title":"Label Smoothing is a Pragmatic Information Bottleneck","created":"2025-08-12","cited_by_count":0,"area":null},{"id":"2510.18638","title":"Optimality and NP-Hardness of Transformers in Learning Markovian Dynamical Functions","created":"2025-10-21","cited_by_count":0,"area":null}],"next_cursor":null}