{"total":40,"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":"2302.04062","title":"Machine Learning for Synthetic Data Generation: A Review","created":"2023-02-08","cited_by_count":120,"area":null},{"id":"2106.07803","title":"SynthASR: Unlocking Synthetic Data for Speech Recognition","created":"2021-06-14","cited_by_count":34,"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":"2110.11479","title":"Synt++: Utilizing Imperfect Synthetic Data to Improve Speech Recognition","created":"2021-10-21","cited_by_count":24,"area":null},{"id":"2406.02925","title":"Task Arithmetic can Mitigate Synthetic-to-Real Gap in Automatic Speech Recognition","created":"2024-06-05","cited_by_count":14,"area":null},{"id":"2201.10240","title":"Improving the fusion of acoustic and text representations in RNN-T","created":"2022-01-25","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":"2302.14036","title":"Text-only domain adaptation for end-to-end ASR using integrated text-to-mel-spectrogram generator","created":"2023-02-27","cited_by_count":11,"area":null},{"id":"2302.08583","title":"JEIT: Joint End-to-End Model and Internal Language Model Training for Speech Recognition","created":"2023-02-16","cited_by_count":9,"area":null},{"id":"2408.09215","title":"Generating Data with Text-to-Speech and Large-Language Models for Conversational Speech Recognition","created":"2024-08-17","cited_by_count":9,"area":null},{"id":"2205.06755","title":"Who Are We Talking About? Handling Person Names in Speech Translation","created":"2022-05-13","cited_by_count":8,"area":null},{"id":"2207.09889","title":"When Is TTS Augmentation Through a Pivot Language Useful?","created":"2022-07-20","cited_by_count":8,"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":"2506.11130","title":"A Self-Refining Framework for Enhancing ASR Using TTS-Synthesized Data","created":"2025-06-10","cited_by_count":7,"area":null},{"id":"2304.11073","title":"OLISIA: a Cascade System for Spoken Dialogue State Tracking","created":"2023-04-20","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":"2407.04047","title":"Improving Accented Speech Recognition using Data Augmentation based on Unsupervised Text-to-Speech Synthesis","created":"2024-07-04","cited_by_count":5,"area":null},{"id":"2310.08132","title":"On the Relevance of Phoneme Duration Variability of Synthesized Training Data for Automatic Speech Recognition","created":"2023-10-12","cited_by_count":4,"area":null},{"id":"2210.15876","title":"Random Utterance Concatenation Based Data Augmentation for Improving Short-video Speech Recognition","created":"2022-10-28","cited_by_count":3,"area":null},{"id":"2211.09731","title":"Stutter-TTS: Controlled Synthesis and Improved Recognition of Stuttered Speech","created":"2022-11-04","cited_by_count":3,"area":null},{"id":"2308.07393","title":"Using Text Injection to Improve Recognition of Personal Identifiers in Speech","created":"2023-08-14","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":"2409.09009","title":"Optimizing Rare Word Accuracy in Direct Speech Translation with a Retrieval-and-Demonstration Approach","created":"2024-09-13","cited_by_count":3,"area":null},{"id":"2410.00511","title":"Pre-training with Synthetic Patterns for Audio","created":"2024-10-01","cited_by_count":3,"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":"2309.09524","title":"Improved Factorized Neural Transducer Model For text-only Domain Adaptation","created":"2023-09-18","cited_by_count":2,"area":null},{"id":"2110.07040","title":"Data Incubation -- Synthesizing Missing Data for Handwriting Recognition","created":"2021-10-13","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":"2406.05923","title":"Contrastive Learning from Synthetic Audio Doppelg\\\"angers","created":"2024-06-09","cited_by_count":1,"area":null},{"id":"2411.13159","title":"Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM","created":"2024-11-20","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":"2108.10791","title":"Ensuring the Inclusive Use of Natural Language Processing in the Global Response to COVID-19","created":"2021-08-11","cited_by_count":0,"area":null},{"id":"2206.04305","title":"Context-based out-of-vocabulary word recovery for ASR systems in Indian languages","created":"2022-06-09","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":"2403.10937","title":"Initial Decoding with Minimally Augmented Language Model for Improved Lattice Rescoring in Low Resource ASR","created":"2024-03-16","cited_by_count":0,"area":null},{"id":"2410.18444","title":"Evaluating Automatic Speech Recognition Systems for Korean Meteorological Experts","created":"2024-10-24","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":"2509.10452","title":"WhisTLE: Deeply Supervised, Text-Only Domain Adaptation for Small Pretrained Speech Recognition Transformers","created":"2025-09-12","cited_by_count":0,"area":null}],"next_cursor":null}