{"total":137,"rows":[{"id":"2111.01690","title":"Recent Advances in End-to-End Automatic Speech Recognition","created":"2021-11-02","cited_by_count":140,"area":null},{"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":"2305.11013","title":"FunASR: A Fundamental End-to-End Speech Recognition Toolkit","created":"2023-05-18","cited_by_count":95,"area":null},{"id":"2310.09424","title":"SALM: Speech-augmented Language Model with In-context Learning for Speech Recognition and Translation","created":"2023-10-13","cited_by_count":76,"area":null},{"id":"2205.13660","title":"Contextual Adapters for Personalized Speech Recognition in Neural Transducers","created":"2022-05-26","cited_by_count":57,"area":null},{"id":"2111.03250","title":"Context-Aware Transformer Transducer for Speech Recognition","created":"2021-11-05","cited_by_count":56,"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":"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":"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":"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":"2102.07739","title":"Personalization Strategies for End-to-End Speech Recognition Systems","created":"2021-02-15","cited_by_count":26,"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":"2309.10917","title":"End-to-End Speech Recognition Contextualization with Large Language Models","created":"2023-09-19","cited_by_count":22,"area":null},{"id":"2306.01942","title":"Can Contextual Biasing Remain Effective with Whisper and GPT-2?","created":"2023-06-02","cited_by_count":21,"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":"2411.06437","title":"CTC-Assisted LLM-Based Contextual ASR","created":"2024-11-10","cited_by_count":19,"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":"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},{"id":"2207.00857","title":"Tree-constrained Pointer Generator with Graph Neural Network Encodings for Contextual Speech Recognition","created":"2022-07-02","cited_by_count":17,"area":null},{"id":"2209.01250","title":"Improving Contextual Recognition of Rare Words with an Alternate Spelling Prediction Model","created":"2022-09-02","cited_by_count":17,"area":null},{"id":"2401.08835","title":"Improving ASR Contextual Biasing with Guided Attention","created":"2024-01-16","cited_by_count":17,"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":"2305.12839","title":"CopyNE: Better Contextual ASR by Copying Named Entities","created":"2023-05-22","cited_by_count":14,"area":null},{"id":"2312.09582","title":"Phoneme-aware Encoding for Prefix-tree-based Contextual ASR","created":"2023-12-15","cited_by_count":13,"area":null},{"id":"2301.06735","title":"Two Stage Contextual Word Filtering for Context bias in Unified Streaming and Non-streaming Transducer","created":"2023-01-17","cited_by_count":12,"area":null},{"id":"2306.00804","title":"Adaptive Contextual Biasing for Transducer Based Streaming Speech Recognition","created":"2023-06-01","cited_by_count":12,"area":null},{"id":"2108.07493","title":"A Light-weight contextual spelling correction model for customizing transducer-based speech recognition systems","created":"2021-08-17","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":"2407.10303","title":"Improving Neural Biasing for Contextual Speech Recognition by Early Context Injection and Text Perturbation","created":"2024-07-14","cited_by_count":11,"area":null},{"id":"2110.02791","title":"Spell my name: keyword boosted speech recognition","created":"2021-10-06","cited_by_count":10,"area":null},{"id":"2406.16120","title":"Contextualized End-to-end Automatic Speech Recognition with Intermediate Biasing Loss","created":"2024-06-23","cited_by_count":10,"area":null},{"id":"2409.15353","title":"Contextualization of ASR with LLM using phonetic retrieval-based augmentation","created":"2024-09-11","cited_by_count":10,"area":null},{"id":"2302.11192","title":"Improving Contextual Spelling Correction by External Acoustics Attention and Semantic Aware Data Augmentation","created":"2023-02-22","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":"2304.08862","title":"Approximate Nearest Neighbour Phrase Mining for Contextual Speech Recognition","created":"2023-04-18","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":"2110.04891","title":"Have best of both worlds: two-pass hybrid and E2E cascading framework for speech recognition","created":"2021-10-10","cited_by_count":7,"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":"2309.00723","title":"Contextual Biasing of Named-Entities with Large Language Models","created":"2023-09-01","cited_by_count":7,"area":null},{"id":"2310.05129","title":"ed-cec: improving rare word recognition using asr postprocessing based on error detection and context-aware error correction","created":"2023-10-08","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":"2402.15307","title":"Representing Online Handwriting for Recognition in Large Vision-Language Models","created":"2024-02-23","cited_by_count":7,"area":"mllm"},{"id":"2406.07096","title":"Fast Context-Biasing for CTC and Transducer ASR models with CTC-based Word Spotter","created":"2024-06-11","cited_by_count":7,"area":null},{"id":"2505.22857","title":"NGPU-LM: GPU-Accelerated N-Gram Language Model for Context-Biasing in Greedy ASR Decoding","created":"2025-05-28","cited_by_count":7,"area":null},{"id":"2506.05671","title":"Low-Resource Domain Adaptation for Speech LLMs via Text-Only Fine-Tuning","created":"2025-06-06","cited_by_count":7,"area":null},{"id":"2210.16554","title":"End-to-end Spoken Language Understanding with Tree-constrained Pointer Generator","created":"2022-10-29","cited_by_count":6,"area":null},{"id":"2305.18824","title":"Graph Neural Networks for Contextual ASR with the Tree-Constrained Pointer Generator","created":"2023-05-30","cited_by_count":6,"area":null},{"id":"2310.09988","title":"Personalization of CTC-based End-to-End Speech Recognition Using Pronunciation-Driven Subword Tokenization","created":"2023-10-16","cited_by_count":6,"area":null},{"id":"2311.08966","title":"Improving Large-scale Deep Biasing with Phoneme Features and Text-only Data in Streaming Transducer","created":"2023-11-15","cited_by_count":6,"area":null},{"id":"2112.06743","title":"Attentive Contextual Carryover for Multi-Turn End-to-End Spoken Language Understanding","created":"2021-12-13","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":"2404.10180","title":"Deferred NAM: Low-latency Top-K Context Injection via Deferred Context Encoding for Non-Streaming ASR","created":"2024-04-15","cited_by_count":5,"area":null},{"id":"2406.02649","title":"Keyword-Guided Adaptation of Automatic Speech Recognition","created":"2024-06-04","cited_by_count":5,"area":null},{"id":"2210.11981","title":"Named Entity Detection and Injection for Direct Speech Translation","created":"2022-10-21","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":"2303.17799","title":"Dialog act guided contextual adapter for personalized speech recognition","created":"2023-03-31","cited_by_count":4,"area":null},{"id":"2306.02317","title":"SpellMapper: A non-autoregressive neural spellchecker for ASR customization with candidate retrieval based on n-gram mappings","created":"2023-06-04","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":"2403.14168","title":"M$^3$AV: A Multimodal, Multigenre, and Multipurpose Audio-Visual Academic Lecture Dataset","created":"2024-03-21","cited_by_count":4,"area":null},{"id":"2403.17645","title":"DANCER: Entity Description Augmented Named Entity Corrector for Automatic Speech Recognition","created":"2024-03-26","cited_by_count":4,"area":null},{"id":"2506.09448","title":"OWSM-Biasing: Contextualizing Open Whisper-Style Speech Models for Automatic Speech Recognition with Dynamic Vocabulary","created":"2025-06-11","cited_by_count":4,"area":null},{"id":"2508.07014","title":"TurboBias: Universal ASR Context-Biasing powered by GPU-accelerated Phrase-Boosting Tree","created":"2025-08-09","cited_by_count":4,"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":"2307.01764","title":"Knowledge-Aware Audio-Grounded Generative Slot Filling for Limited Annotated Data","created":"2023-07-04","cited_by_count":3,"area":null},{"id":"2401.07360","title":"Promptformer: Prompted Conformer Transducer for ASR","created":"2024-01-14","cited_by_count":3,"area":null},{"id":"2401.13146","title":"Locality enhanced dynamic biasing and sampling strategies for contextual ASR","created":"2024-01-23","cited_by_count":3,"area":null},{"id":"2406.02921","title":"Text Injection for Neural Contextual Biasing","created":"2024-06-05","cited_by_count":3,"area":null},{"id":"2411.00664","title":"Optimizing Contextual Speech Recognition Using Vector Quantization for Efficient Retrieval","created":"2024-11-01","cited_by_count":3,"area":null},{"id":"2506.01263","title":"WCTC-Biasing: Retraining-free Contextual Biasing ASR with Wildcard CTC-based Keyword Spotting and Inter-layer Biasing","created":"2025-06-02","cited_by_count":3,"area":null},{"id":"2508.17796","title":"Zero-shot Context Biasing with Trie-based Decoding using Synthetic Multi-Pronunciation","created":"2025-08-25","cited_by_count":3,"area":null},{"id":"2512.23686","title":"PROFASR-BENCH: A Benchmark for Context-Conditioned ASR in High-Stakes Professional Speech","created":"2025-12-29","cited_by_count":3,"area":null},{"id":"2606.19157","title":"IndicContextEval: A Benchmark for Evaluating Context Utilisation in Audio Large Language Models Across 8 Indic Languages","created":"2026-06-17","cited_by_count":3,"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":"2212.03817","title":"A Transformer-Based User Satisfaction Prediction for Proactive Interaction Mechanism in DuerOS","created":"2022-12-05","cited_by_count":2,"area":null},{"id":"2304.01905","title":"Dual-Attention Neural Transducers for Efficient Wake Word Spotting in Speech Recognition","created":"2023-04-03","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":"2306.08588","title":"Improving Code-Switching and Named Entity Recognition in ASR with Speech Editing based Data Augmentation","created":"2023-06-14","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":"2409.17603","title":"Deep CLAS: Deep Contextual Listen, Attend and Spell","created":"2024-09-26","cited_by_count":2,"area":null},{"id":"2501.07102","title":"AdaCS: Adaptive Normalization for Enhanced Code-Switching ASR","created":"2025-01-13","cited_by_count":2,"area":null},{"id":"2506.00422","title":"DYNAC: Dynamic Vocabulary based Non-Autoregressive Contextualization for Speech Recognition","created":"2025-05-31","cited_by_count":2,"area":null},{"id":"2603.26246","title":"Distilling Conversations: Abstract Compression of Conversational Audio Context for LLM-based ASR","created":"2026-03-27","cited_by_count":2,"area":null},{"id":"2102.08147","title":"Large-Context Conversational Representation Learning: Self-Supervised Learning for Conversational Documents","created":"2021-02-16","cited_by_count":1,"area":null},{"id":"2108.00082","title":"Towards Continual Entity Learning in Language Models for Conversational Agents","created":"2021-07-30","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":"2310.09680","title":"Improved Contextual Recognition In Automatic Speech Recognition Systems By Semantic Lattice Rescoring","created":"2023-10-14","cited_by_count":1,"area":null},{"id":"2402.06592","title":"Self-consistent context aware conformer transducer for speech recognition","created":"2024-02-09","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":"2408.08027","title":"Enhancing Large Language Model-based Speech Recognition by Contextualization for Rare and Ambiguous Words","created":"2024-08-15","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":"2409.06468","title":"An Effective Context-Balanced Adaptation Approach for Long-Tailed Speech Recognition","created":"2024-09-10","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":"2409.16469","title":"Spelling Correction through Rewriting of Non-Autoregressive ASR Lattices","created":"2024-09-24","cited_by_count":1,"area":null},{"id":"2505.23077","title":"Contextualized Automatic Speech Recognition with Dynamic Vocabulary Prediction and Activation","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2506.06252","title":"Lightweight Prompt Biasing for Contextualized End-to-End ASR Systems","created":"2025-06-06","cited_by_count":1,"area":null},{"id":"2506.11064","title":"PMF-CEC: Phoneme-augmented Multimodal Fusion for Context-aware ASR Error Correction with Error-specific Selective Decoding","created":"2025-05-31","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":"2509.04393","title":"Contextualized Token Discrimination for Speech Search Query Correction","created":"2025-09-04","cited_by_count":1,"area":null}],"next_cursor":"100"}