{"total":60,"rows":[{"id":"2205.10643","title":"Self-Supervised Speech Representation Learning: A Review","created":"2022-05-21","cited_by_count":260,"area":null},{"id":"2306.00984","title":"StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners","created":"2023-06-01","cited_by_count":177,"area":null},{"id":"2312.04567","title":"Scaling Laws of Synthetic Images for Model Training ... for Now","created":"2023-12-07","cited_by_count":108,"area":null},{"id":"2312.17742","title":"Learning Vision from Models Rivals Learning Vision from Data","created":"2023-12-28","cited_by_count":71,"area":null},{"id":"2311.06753","title":"AudioChatLlama: Towards General-Purpose Speech Abilities for LLMs","created":"2023-11-12","cited_by_count":59,"area":"lr"},{"id":"2305.10951","title":"Making More of Little Data: Improving Low-Resource Automatic Speech Recognition Using Data Augmentation","created":"2023-05-18","cited_by_count":31,"area":null},{"id":"2209.02842","title":"ASR2K: Speech Recognition for Around 2000 Languages without Audio","created":"2022-09-06","cited_by_count":26,"area":null},{"id":"2108.12226","title":"Injecting Text in Self-Supervised Speech Pretraining","created":"2021-08-27","cited_by_count":24,"area":null},{"id":"2109.06912","title":"fairseq S^2: A Scalable and Integrable Speech Synthesis Toolkit","created":"2021-09-14","cited_by_count":24,"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":"2103.07762","title":"OkwuGb\\'e: End-to-End Speech Recognition for Fon and Igbo","created":"2021-03-13","cited_by_count":13,"area":null},{"id":"2503.01167","title":"Enhancing Vision-Language Compositional Understanding with Multimodal Synthetic Data","created":"2025-03-03","cited_by_count":12,"area":"synth"},{"id":"2110.13877","title":"Assessing Evaluation Metrics for Speech-to-Speech Translation","created":"2021-10-26","cited_by_count":10,"area":null},{"id":"2201.11571","title":"Synthesizing Dysarthric Speech Using Multi-talker TTS for Dysarthric Speech Recognition","created":"2022-01-27","cited_by_count":10,"area":null},{"id":"2204.00618","title":"ASR data augmentation in low-resource settings using cross-lingual multi-speaker TTS and cross-lingual voice conversion","created":"2022-03-29","cited_by_count":10,"area":null},{"id":"2303.14885","title":"Text is All You Need: Personalizing ASR Models using Controllable Speech Synthesis","created":"2023-03-27","cited_by_count":10,"area":null},{"id":"2309.15674","title":"Speech collage: code-switched audio generation by collaging monolingual corpora","created":"2023-09-27","cited_by_count":10,"area":null},{"id":"2211.16049","title":"Evaluating and reducing the distance between synthetic and real speech distributions","created":"2022-11-29","cited_by_count":9,"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":"2306.07944","title":"Speech-to-Text Adapter and Speech-to-Entity Retriever Augmented LLMs for Speech Understanding","created":"2023-06-08","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":"2104.05379","title":"Comparing the Benefit of Synthetic Training Data for Various Automatic Speech Recognition Architectures","created":"2021-04-12","cited_by_count":8,"area":null},{"id":"2308.08438","title":"Accurate synthesis of Dysarthric Speech for ASR data augmentation","created":"2023-08-16","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":"2210.15398","title":"Make More of Your Data: Minimal Effort Data Augmentation for Automatic Speech Recognition and Translation","created":"2022-10-27","cited_by_count":6,"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":"2305.16333","title":"Text Generation with Speech Synthesis for ASR Data Augmentation","created":"2023-05-22","cited_by_count":5,"area":null},{"id":"2306.00998","title":"Towards Selection of Text-to-speech Data to Augment ASR Training","created":"2023-05-30","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":"2106.07578","title":"Dynamic Gradient Aggregation for Federated Domain Adaptation","created":"2021-06-14","cited_by_count":4,"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":"2403.13804","title":"Learning from Synthetic Data for Visual Grounding","created":"2024-03-20","cited_by_count":4,"area":"synth"},{"id":"2407.18879","title":"Utilizing TTS Synthesized Data for Efficient Development of Keyword Spotting Model","created":"2024-07-26","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":"2212.03232","title":"Learning the joint distribution of two sequences using little or no paired data","created":"2022-12-06","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":"2410.00511","title":"Pre-training with Synthetic Patterns for Audio","created":"2024-10-01","cited_by_count":3,"area":null},{"id":"2510.12781","title":"Cost Analysis of Human-corrected Transcription for Predominately Oral Languages","created":"2025-10-14","cited_by_count":3,"area":null},{"id":"2211.00968","title":"Internal Language Model Estimation based Adaptive Language Model Fusion for Domain Adaptation","created":"2022-11-02","cited_by_count":2,"area":null},{"id":"2301.02966","title":"SpeeChain: A Speech Toolkit for Large-Scale Machine Speech Chain","created":"2023-01-08","cited_by_count":2,"area":null},{"id":"2512.19400","title":"Kunnafonidilaw ka Cadeau: an ASR dataset of present-day Bambara","created":"2025-12-22","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":"2302.09723","title":"Emphasizing Unseen Words: New Vocabulary Acquisition for End-to-End Speech Recognition","created":"2023-02-20","cited_by_count":1,"area":null},{"id":"2310.17448","title":"Dialect Adaptation and Data Augmentation for Low-Resource ASR: TalTech Systems for the MADASR 2023 Challenge","created":"2023-10-26","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":"2601.06802","title":"Doing More with Less: Data Augmentation for Sudanese Dialect Automatic Speech Recognition","created":"2026-01-11","cited_by_count":1,"area":null},{"id":"2606.29031","title":"How to Leverage Synthetic Speech for LLM-Based ASR Systems?","created":"2026-06-27","cited_by_count":1,"area":null},{"id":"2111.07793","title":"Analysis of Data Augmentation Methods for Low-Resource Maltese ASR","created":"2021-11-15","cited_by_count":0,"area":null},{"id":"2302.03498","title":"MAC: A unified framework boosting low resource automatic speech recognition","created":"2023-02-05","cited_by_count":0,"area":null},{"id":"2303.16621","title":"AraSpot: Arabic Spoken Command Spotting","created":"2023-03-29","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":"2406.15846","title":"Revisiting Interpolation Augmentation for Speech-to-Text Generation","created":"2024-06-22","cited_by_count":0,"area":null},{"id":"2409.12745","title":"Enhancing Synthetic Training Data for Speech Commands: From ASR-Based Filtering to Domain Adaptation in SSL Latent Space","created":"2024-09-19","cited_by_count":0,"area":null},{"id":"2410.12279","title":"Beyond Oversmoothing: Evaluating DDPM and MSE for Scalable Speech Synthesis in ASR","created":"2024-10-16","cited_by_count":0,"area":"diffusion"},{"id":"2508.15801","title":"LingVarBench: Benchmarking LLMs on Entity Recognitions and Linguistic Verbalization Patterns in Phone-Call Transcripts","created":"2025-08-13","cited_by_count":0,"area":null},{"id":"2602.11933","title":"Cross-Modal Robustness Transfer (CMRT): Training Robust Speech Translation Models Using Adversarial Text","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2604.12335","title":"SynMulti: Synthetic-to-Real Learning for Multimodal Video Understanding","created":"2026-04-14","cited_by_count":0,"area":"mllm"},{"id":"2607.08409","title":"When Synthetic Speech Is All You Have: Better Call GRPO","created":"2026-07-09","cited_by_count":0,"area":"lr"},{"id":"2608.09529","title":"Towards Expressive and Faithful Audio-to-Image Generation: A Unified Multimodal Dataset and Synthesis Framework","created":"2026-08-10","cited_by_count":0,"area":null}],"next_cursor":null}