{"total":107,"rows":[{"id":"2303.03329","title":"End-to-End Speech Recognition: A Survey","created":"2023-03-03","cited_by_count":129,"area":null},{"id":"2104.02194","title":"Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion","created":"2021-04-05","cited_by_count":101,"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":"2111.03250","title":"Context-Aware Transformer Transducer for Speech Recognition","created":"2021-11-05","cited_by_count":56,"area":null},{"id":"2306.16007","title":"Prompting Large Language Models for Zero-Shot Domain Adaptation in Speech Recognition","created":"2023-06-28","cited_by_count":48,"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":"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":"2102.07739","title":"Personalization Strategies for End-to-End Speech Recognition Systems","created":"2021-02-15","cited_by_count":26,"area":null},{"id":"2204.09715","title":"Scaling Language Model Size in Cross-Device Federated Learning","created":"2022-03-31","cited_by_count":25,"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":"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":"2205.10839","title":"Deep Learning for Visual Speech Analysis: A Survey","created":"2022-05-22","cited_by_count":21,"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":"2202.08533","title":"AISHELL-NER: Named Entity Recognition from Chinese Speech","created":"2022-02-17","cited_by_count":19,"area":null},{"id":"2309.07414","title":"PromptASR for contextualized ASR with controllable style","created":"2023-09-14","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":"2110.01857","title":"ASR Rescoring and Confidence Estimation with ELECTRA","created":"2021-10-05","cited_by_count":16,"area":null},{"id":"2208.12666","title":"Effectiveness of Mining Audio and Text Pairs from Public Data for Improving ASR Systems for Low-Resource Languages","created":"2022-08-26","cited_by_count":16,"area":null},{"id":"2112.07254","title":"Improving Hybrid CTC/Attention End-to-end Speech Recognition with Pretrained Acoustic and Language Model","created":"2021-12-14","cited_by_count":15,"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":"2210.10027","title":"Maestro-U: Leveraging joint speech-text representation learning for zero supervised speech ASR","created":"2022-10-18","cited_by_count":13,"area":null},{"id":"2310.11532","title":"Multi-stage Large Language Model Correction for Speech Recognition","created":"2023-10-17","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":"2401.12789","title":"Multilingual and Fully Non-Autoregressive ASR with Large Language Model Fusion: A Comprehensive Study","created":"2024-01-23","cited_by_count":12,"area":null},{"id":"2104.01604","title":"Timers and Such: A Practical Benchmark for Spoken Language Understanding with Numbers","created":"2021-04-04","cited_by_count":11,"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":"2212.01992","title":"Fast and accurate factorized neural transducer for text adaption of end-to-end speech recognition models","created":"2022-12-05","cited_by_count":11,"area":null},{"id":"2304.09607","title":"CB-Conformer: Contextual biasing Conformer for biased word recognition","created":"2023-04-19","cited_by_count":11,"area":null},{"id":"2204.09606","title":"Detecting Unintended Memorization in Language-Model-Fused ASR","created":"2022-04-20","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":"2104.04552","title":"Lookup-Table Recurrent Language Models for Long Tail Speech Recognition","created":"2021-04-09","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":"2309.08628","title":"Recovering from Privacy-Preserving Masking with Large Language Models","created":"2023-09-12","cited_by_count":9,"area":null},{"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":"2310.14534","title":"Improving Seq2Seq Grammatical Error Correction via Decoding Interventions","created":"2023-10-23","cited_by_count":8,"area":null},{"id":"2405.13344","title":"Contextualized Automatic Speech Recognition with Dynamic Vocabulary","created":"2024-05-22","cited_by_count":8,"area":null},{"id":"2408.16542","title":"SALSA: Speedy ASR-LLM Synchronous Aggregation","created":"2024-08-29","cited_by_count":8,"area":null},{"id":"2202.09003","title":"End-to-end contextual asr based on posterior distribution adaptation for hybrid ctc/attention system","created":"2022-02-18","cited_by_count":7,"area":null},{"id":"2206.13240","title":"A Simple Baseline for Domain Adaptation in End to End ASR Systems Using Synthetic Data","created":"2022-06-22","cited_by_count":7,"area":null},{"id":"2307.06530","title":"Exploring the Integration of Large Language Models into Automatic Speech Recognition Systems: An Empirical Study","created":"2023-07-13","cited_by_count":7,"area":null},{"id":"2308.05269","title":"A Novel Self-training Approach for Low-resource Speech Recognition","created":"2023-08-10","cited_by_count":7,"area":null},{"id":"2311.08402","title":"Retrieve and Copy: Scaling ASR Personalization to Large Catalogs","created":"2023-11-14","cited_by_count":7,"area":null},{"id":"2201.11867","title":"Neural-FST Class Language Model for End-to-End Speech Recognition","created":"2022-01-28","cited_by_count":6,"area":null},{"id":"2207.00706","title":"UserLibri: A Dataset for ASR Personalization Using Only Text","created":"2022-07-02","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":"2210.05785","title":"Scaling Up Deliberation for Multilingual ASR","created":"2022-10-11","cited_by_count":6,"area":null},{"id":"2309.16082","title":"Forgetting Private Textual Sequences in Language Models via Leave-One-Out Ensemble","created":"2023-09-28","cited_by_count":6,"area":null},{"id":"2310.07062","title":"Acoustic Model Fusion for End-to-end Speech Recognition","created":"2023-10-10","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":"2202.01405","title":"Joint Speech Recognition and Audio Captioning","created":"2022-02-03","cited_by_count":5,"area":null},{"id":"2211.00174","title":"Joint Audio/Text Training for Transformer Rescorer of Streaming Speech Recognition","created":"2022-10-31","cited_by_count":5,"area":null},{"id":"2305.17846","title":"Retraining-free Customized ASR for Enharmonic Words Based on a Named-Entity-Aware Model and Phoneme Similarity Estimation","created":"2023-05-29","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":"2103.15722","title":"Transformer-based end-to-end speech recognition with residual Gaussian-based self-attention","created":"2021-03-29","cited_by_count":4,"area":null},{"id":"2110.07879","title":"Advances and Challenges in Deep Lip Reading","created":"2021-10-15","cited_by_count":4,"area":null},{"id":"2110.10026","title":"Private Language Model Adaptation for Speech Recognition","created":"2021-09-28","cited_by_count":4,"area":null},{"id":"2307.00759","title":"Multilingual Contextual Adapters To Improve Custom Word Recognition In Low-resource Languages","created":"2023-07-03","cited_by_count":4,"area":null},{"id":"2405.14259","title":"Let's Fuse Step by Step: A Generative Fusion Decoding Algorithm with LLMs for Robust and Instruction-Aware ASR and OCR","created":"2024-05-23","cited_by_count":4,"area":null},{"id":"2409.20301","title":"Alignment-Free Training for Transducer-based Multi-Talker ASR","created":"2024-09-30","cited_by_count":4,"area":null},{"id":"2210.06772","title":"Mitigating Unintended Memorization in Language Models via Alternating Teaching","created":"2022-10-13","cited_by_count":3,"area":null},{"id":"2210.13189","title":"Can Visual Context Improve Automatic Speech Recognition for an Embodied Agent?","created":"2022-10-21","cited_by_count":3,"area":null},{"id":"2308.13345","title":"Decoupled Structure for Improved Adaptability of End-to-End Models","created":"2023-08-25","cited_by_count":3,"area":null},{"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":"2510.12827","title":"Automatic Speech Recognition in the Modern Era: Architectures, Training, and Evaluation","created":"2025-10-11","cited_by_count":3,"area":null},{"id":"2203.16776","title":"An Empirical Study of Language Model Integration for Transducer based Speech Recognition","created":"2022-03-31","cited_by_count":2,"area":null},{"id":"2206.12829","title":"On Comparison of Encoders for Attention based End to End Speech Recognition in Standalone and Rescoring Mode","created":"2022-06-26","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":"2211.05121","title":"Adaptive Multi-Corpora Language Model Training for Speech Recognition","created":"2022-11-09","cited_by_count":2,"area":null},{"id":"2309.09524","title":"Improved Factorized Neural Transducer Model For text-only Domain Adaptation","created":"2023-09-18","cited_by_count":2,"area":null},{"id":"2310.11003","title":"Correction Focused Language Model Training for Speech Recognition","created":"2023-10-17","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":"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":"2208.02250","title":"Adversarial Attacks on ASR Systems: An Overview","created":"2022-08-03","cited_by_count":1,"area":null},{"id":"2210.15285","title":"SAN: a robust end-to-end ASR model architecture","created":"2022-10-27","cited_by_count":1,"area":null},{"id":"2210.16892","title":"Partitioned Gradient Matching-based Data Subset Selection for Compute-Efficient Robust ASR Training","created":"2022-10-30","cited_by_count":1,"area":null},{"id":"2301.00066","title":"Memory Augmented Lookup Dictionary based Language Modeling for Automatic Speech Recognition","created":"2022-12-30","cited_by_count":1,"area":null},{"id":"2302.00836","title":"Improving Rare Words Recognition through Homophone Extension and Unified Writing for Low-resource Cantonese Speech Recognition","created":"2023-02-02","cited_by_count":1,"area":null},{"id":"2302.09723","title":"Emphasizing Unseen Words: New Vocabulary Acquisition for End-to-End Speech Recognition","created":"2023-02-20","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":"2305.19972","title":"VILAS: Exploring the Effects of Vision and Language Context in Automatic Speech Recognition","created":"2023-05-31","cited_by_count":1,"area":null},{"id":"2308.07395","title":"Text Injection for Capitalization and Turn-Taking Prediction in Speech Models","created":"2023-08-14","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":"2403.00370","title":"Post-decoder Biasing for End-to-End Speech Recognition of Multi-turn Medical Interview","created":"2024-03-01","cited_by_count":1,"area":null},{"id":"2406.03274","title":"Enhancing CTC-based speech recognition with diverse modeling units","created":"2024-06-05","cited_by_count":1,"area":null},{"id":"2408.10524","title":"XCB: an effective contextual biasing approach to bias cross-lingual phrases in speech recognition","created":"2024-08-20","cited_by_count":1,"area":null},{"id":"2409.13514","title":"Unifying Global and Near-Context Biasing in a Single Trie Pass","created":"2024-09-20","cited_by_count":1,"area":null},{"id":"2501.12979","title":"FlanEC: Exploring Flan-T5 for Post-ASR Error Correction","created":"2025-01-22","cited_by_count":1,"area":null},{"id":"2608.05759","title":"How to Recognize New Words: A Comparison Between Context Biasing Methods and Speech LLMs","created":"2026-08-06","cited_by_count":1,"area":null},{"id":"2210.09510","title":"Towards Personalization of CTC Speech Recognition Models with Contextual Adapters and Adaptive Boosting","created":"2022-10-18","cited_by_count":0,"area":null},{"id":"2309.02459","title":"Text-Only Domain Adaptation for End-to-End Speech Recognition through Down-Sampling Acoustic Representation","created":"2023-09-04","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":"2506.10779","title":"Improving Speech Recognition of Named Entities in Classroom Speech with LLM Revision and Phonetic-Semantic Context","created":"2025-06-12","cited_by_count":0,"area":null},{"id":"2506.18703","title":"Context Biasing for Pronunciation-Orthography Mismatch in Automatic Speech Recognition","created":"2025-06-23","cited_by_count":0,"area":null},{"id":"2507.00669","title":"Audio-3DVG: Unified Audio -- Point Cloud Fusion for 3D Visual Grounding","created":"2025-07-01","cited_by_count":0,"area":null},{"id":"2507.10827","title":"Supporting SENCOTEN Language Documentation Efforts with Automatic Speech Recognition","created":"2025-07-14","cited_by_count":0,"area":null}],"next_cursor":"100"}