{"total":20,"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":"2108.12226","title":"Injecting Text in Self-Supervised Speech Pretraining","created":"2021-08-27","cited_by_count":24,"area":null},{"id":"2306.02210","title":"GPT-FL: Generative Pre-trained Model-Assisted Federated Learning","created":"2023-06-03","cited_by_count":24,"area":null},{"id":"2202.11823","title":"Differentially Private Speaker Anonymization","created":"2022-02-23","cited_by_count":16,"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":"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":"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":"2207.09889","title":"When Is TTS Augmentation Through a Pivot Language Useful?","created":"2022-07-20","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":"2304.11073","title":"OLISIA: a Cascade System for Spoken Dialogue State Tracking","created":"2023-04-20","cited_by_count":5,"area":null},{"id":"2412.10103","title":"AMuSeD: An Attentive Deep Neural Network for Multimodal Sarcasm Detection Incorporating Bi-modal Data Augmentation","created":"2024-12-13","cited_by_count":5,"area":null},{"id":"2207.08179","title":"End-to-End Spoken Language Understanding: Performance analyses of a voice command task in a low resource setting","created":"2022-07-17","cited_by_count":3,"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":"2110.07040","title":"Data Incubation -- Synthesizing Missing Data for Handwriting Recognition","created":"2021-10-13","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":"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}],"next_cursor":null}