{"total":54,"rows":[{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83,"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":"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":"2401.08835","title":"Improving ASR Contextual Biasing with Guided Attention","created":"2024-01-16","cited_by_count":17,"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":"2307.10274","title":"Zero-shot Domain-sensitive Speech Recognition with Prompt-conditioning Fine-tuning","created":"2023-07-18","cited_by_count":13,"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":"2304.09607","title":"CB-Conformer: Contextual biasing Conformer for biased word recognition","created":"2023-04-19","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":"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":"2304.08862","title":"Approximate Nearest Neighbour Phrase Mining for Contextual Speech Recognition","created":"2023-04-18","cited_by_count":8,"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":"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":"2301.02736","title":"Using External Off-Policy Speech-To-Text Mappings in Contextual End-To-End Automated Speech Recognition","created":"2023-01-06","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":"2309.09552","title":"A Multitask Training Approach to Enhance Whisper with Contextual Biasing and Open-Vocabulary Keyword Spotting","created":"2023-09-18","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":"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":"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":"2402.18275","title":"Exploration of Adapter for Noise Robust Automatic Speech Recognition","created":"2024-02-28","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":"2307.07057","title":"Leveraging Pretrained ASR Encoders for Effective and Efficient End-to-End Speech Intent Classification and Slot Filling","created":"2023-07-13","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":"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":"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":"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":"2307.06832","title":"Personalization for BERT-based Discriminative Speech Recognition Rescoring","created":"2023-07-13","cited_by_count":2,"area":null},{"id":"2210.03255","title":"Damage Control During Domain Adaptation for Transducer Based Automatic Speech Recognition","created":"2022-10-06","cited_by_count":1,"area":null},{"id":"2303.13407","title":"Adaptive Endpointing with Deep Contextual Multi-armed Bandits","created":"2023-03-23","cited_by_count":1,"area":null},{"id":"2401.02417","title":"Task Oriented Dialogue as a Catalyst for Self-Supervised Automatic Speech Recognition","created":"2024-01-04","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":"2406.17257","title":"Leveraging Parameter-Efficient Transfer Learning for Multi-Lingual Text-to-Speech Adaptation","created":"2024-06-25","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":"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":"2509.09197","title":"Improving Synthetic Data Training for Contextual Biasing Models with a Keyword-Aware Cost Function","created":"2025-09-11","cited_by_count":1,"area":null},{"id":"2510.23849","title":"A Neural Model for Contextual Biasing Score Learning and Filtering","created":"2025-10-27","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":"2306.03778","title":"Streaming Speech-to-Confusion Network Speech Recognition","created":"2023-06-02","cited_by_count":0,"area":null},{"id":"2309.07648","title":"Incorporating Class-based Language Model for Named Entity Recognition in Factorized Neural Transducer","created":"2023-09-14","cited_by_count":0,"area":null},{"id":"2309.17267","title":"Wiki-En-ASR-Adapt: Large-scale synthetic dataset for English ASR Customization","created":"2023-09-29","cited_by_count":0,"area":null},{"id":"2310.17664","title":"Cascaded Multi-task Adaptive Learning Based on Neural Architecture Search","created":"2023-10-23","cited_by_count":0,"area":null},{"id":"2409.10515","title":"An Efficient Self-Learning Framework For Interactive Spoken Dialog Systems","created":"2024-09-16","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":"2509.09196","title":"Efficient Trie-based Biasing using K-step Prediction for Rare Word Recognition","created":"2025-09-11","cited_by_count":0,"area":null},{"id":"2601.22792","title":"CALM: Joint Contextual Acoustic-Linguistic Modeling for Personalization of Multi-Speaker ASR","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2607.08117","title":"COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2609.28877","title":"Learning New Words from Unlabeled Test Data in Automatic Speech Recognition","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.36913","title":"BaLEEN: Biasing with Latent Encoded Entities for Context-Aware ASR","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}