{"total":29,"rows":[{"id":"2205.10643","title":"Self-Supervised Speech Representation Learning: A Review","created":"2022-05-21","cited_by_count":260,"area":null},{"id":"2111.02674","title":"Voice Conversion Can Improve ASR in Very Low-Resource Settings","created":"2021-11-04","cited_by_count":14,"area":null},{"id":"2410.16726","title":"Enhancing Low-Resource ASR through Versatile TTS: Bridging the Data Gap","created":"2024-10-22","cited_by_count":12,"area":null},{"id":"2204.00803","title":"End-to-end model for named entity recognition from speech without paired training data","created":"2022-04-02","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":"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":"2104.01393","title":"On-the-Fly Aligned Data Augmentation for Sequence-to-Sequence ASR","created":"2021-04-03","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":"2204.02385","title":"Learning Speech Emotion Representations in the Quaternion Domain","created":"2022-04-05","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":"2310.16609","title":"Back Transcription as a Method for Evaluating Robustness of Natural Language Understanding Models to Speech Recognition Errors","created":"2023-10-25","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":"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":"2407.17997","title":"On the Effect of Purely Synthetic Training Data for Different Automatic Speech Recognition Architectures","created":"2024-07-25","cited_by_count":4,"area":null},{"id":"2407.21476","title":"On the Problem of Text-To-Speech Model Selection for Synthetic Data Generation in Automatic Speech Recognition","created":"2024-07-31","cited_by_count":3,"area":null},{"id":"2103.07186","title":"Dynamic Acoustic Unit Augmentation With BPE-Dropout for Low-Resource End-to-End Speech Recognition","created":"2021-03-12","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":"2110.08634","title":"Towards Robust Waveform-Based Acoustic Models","created":"2021-10-16","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":"2104.10328","title":"Label-Synchronous Speech-to-Text Alignment for ASR Using Forward and Backward Transformers","created":"2021-04-21","cited_by_count":0,"area":null},{"id":"2210.02545","title":"JoeyS2T: Minimalistic Speech-to-Text Modeling with JoeyNMT","created":"2022-10-05","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":"2310.05374","title":"Improving End-to-End Speech Processing by Efficient Text Data Utilization with Latent Synthesis","created":"2023-10-09","cited_by_count":0,"area":null},{"id":"2403.08438","title":"Reproducibility and Geometric Intrinsic Dimensionality: An Investigation on Graph Neural Network Research","created":"2024-03-13","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":"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":"2604.01705","title":"Development and multi-center evaluation of domain-adapted speech recognition for human-AI teaming in real-world gastrointestinal endoscopy","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2607.22304","title":"Synthetic Speech, Real Signal: Paralinguistic Preservation and Cross-Lingual Augmentation via Voice Cloning","created":"2026-07-24","cited_by_count":0,"area":null}],"next_cursor":null}