{"total":32,"rows":[{"id":"2302.04062","title":"Machine Learning for Synthetic Data Generation: A Review","created":"2023-02-08","cited_by_count":120,"area":null},{"id":"2206.11488","title":"On the Importance and Applicability of Pre-Training for Federated Learning","created":"2022-06-23","cited_by_count":71,"area":null},{"id":"2303.17200","title":"SynthVSR: Scaling Up Visual Speech Recognition With Synthetic Supervision","created":"2023-03-30","cited_by_count":21,"area":null},{"id":"2207.00688","title":"Building African Voices","created":"2022-07-01","cited_by_count":14,"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":"2308.06382","title":"Phoneme Hallucinator: One-shot Voice Conversion via Set Expansion","created":"2023-08-11","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":"2112.09427","title":"Continual Learning for Monolingual End-to-End Automatic Speech Recognition","created":"2021-12-17","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":"2403.06734","title":"Real-Time Multimodal Cognitive Assistant for Emergency Medical Services","created":"2024-03-11","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":"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":"2506.11089","title":"Better Pseudo-labeling with Multi-ASR Fusion and Error Correction by SpeechLLM","created":"2025-06-05","cited_by_count":6,"area":null},{"id":"2305.16333","title":"Text Generation with Speech Synthesis for ASR Data Augmentation","created":"2023-05-22","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":"2207.00774","title":"Computer-assisted Pronunciation Training -- Speech synthesis is almost all you need","created":"2022-07-02","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":"2406.08800","title":"Can Synthetic Audio From Generative Foundation Models Assist Audio Recognition and Speech Modeling?","created":"2024-06-13","cited_by_count":4,"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":"2310.02876","title":"Hate Speech Detection in Limited Data Contexts using Synthetic Data Generation","created":"2023-10-04","cited_by_count":3,"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":"2412.00055","title":"High-precision medical speech recognition through synthetic data and semantic correction: UNITED-MEDASR","created":"2024-11-24","cited_by_count":2,"area":null},{"id":"2406.05923","title":"Contrastive Learning from Synthetic Audio Doppelg\\\"angers","created":"2024-06-09","cited_by_count":1,"area":null},{"id":"2408.00004","title":"Handling Numeric Expressions in Automatic Speech Recognition","created":"2024-07-18","cited_by_count":1,"area":null},{"id":"2505.20606","title":"Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2507.19374","title":"Data Augmentation for Spoken Grammatical Error Correction","created":"2025-07-25","cited_by_count":1,"area":null},{"id":"2508.19210","title":"Interpolating Speaker Identities in Embedding Space for Data Expansion","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2311.04313","title":"Improved Child Text-to-Speech Synthesis through Fastpitch-based Transfer Learning","created":"2023-11-07","cited_by_count":0,"area":null},{"id":"2404.17983","title":"TI-ASU: Toward Robust Automatic Speech Understanding through Text-to-speech Imputation Against Missing Speech Modality","created":"2024-04-27","cited_by_count":0,"area":null},{"id":"2506.04077","title":"A Novel Data Augmentation Approach for Automatic Speaking Assessment on Opinion Expressions","created":"2025-06-04","cited_by_count":0,"area":null},{"id":"2604.19797","title":"Enhancing ASR Performance in the Medical Domain for Dravidian Languages","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2609.10058","title":"NOPE-HYPE: A Structured Simulation Workflow for Robust Speech-to-Text Across Diverse Acoustic Environments","created":"2026-09-09","cited_by_count":0,"area":null}],"next_cursor":null}