{"total":72,"rows":[{"id":"2106.07447","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","created":"2021-06-14","cited_by_count":2342,"area":null},{"id":"2108.06209","title":"W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training","created":"2021-08-07","cited_by_count":347,"area":null},{"id":"2102.01192","title":"Generative Spoken Language Modeling from Raw Audio","created":"2021-02-01","cited_by_count":340,"area":null},{"id":"2207.06405","title":"Masked Autoencoders that Listen","created":"2022-07-13","cited_by_count":273,"area":null},{"id":"2205.10643","title":"Self-Supervised Speech Representation Learning: A Review","created":"2022-05-21","cited_by_count":260,"area":null},{"id":"2206.08496","title":"Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency","created":"2022-06-17","cited_by_count":250,"area":null},{"id":"2303.01037","title":"Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages","created":"2023-03-02","cited_by_count":231,"area":null},{"id":"2306.00107","title":"MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training","created":"2023-05-31","cited_by_count":181,"area":null},{"id":"2110.07205","title":"SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing","created":"2021-10-14","cited_by_count":180,"area":null},{"id":"2202.01855","title":"Self-supervised Learning with Random-projection Quantizer for Speech Recognition","created":"2022-02-03","cited_by_count":162,"area":null},{"id":"2302.10035","title":"Large-scale Multi-Modal Pre-trained Models: A Comprehensive Survey","created":"2023-02-20","cited_by_count":153,"area":null},{"id":"2104.01027","title":"Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training","created":"2021-04-02","cited_by_count":151,"area":null},{"id":"2105.11084","title":"Unsupervised Speech Recognition","created":"2021-05-24","cited_by_count":148,"area":null},{"id":"2110.01900","title":"DistilHuBERT: Speech Representation Learning by Layer-wise Distillation of Hidden-unit BERT","created":"2021-10-05","cited_by_count":144,"area":null},{"id":"2112.08352","title":"Textless Speech-to-Speech Translation on Real Data","created":"2021-12-15","cited_by_count":121,"area":null},{"id":"2109.13226","title":"BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition","created":"2021-09-27","cited_by_count":88,"area":null},{"id":"2303.11717","title":"A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?","created":"2023-03-21","cited_by_count":84,"area":null},{"id":"2109.06870","title":"Performance-Efficiency Trade-offs in Unsupervised Pre-training for Speech Recognition","created":"2021-09-14","cited_by_count":68,"area":null},{"id":"2107.05677","title":"Codified audio language modeling learns useful representations for music information retrieval","created":"2021-07-12","cited_by_count":64,"area":null},{"id":"2106.05933","title":"PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition","created":"2021-06-10","cited_by_count":53,"area":null},{"id":"2104.11462","title":"LeBenchmark: A Reproducible Framework for Assessing Self-Supervised Representation Learning from Speech","created":"2021-04-23","cited_by_count":47,"area":null},{"id":"2111.03945","title":"Towards Building ASR Systems for the Next Billion Users","created":"2021-11-06","cited_by_count":47,"area":null},{"id":"2106.08922","title":"Momentum Pseudo-Labeling for Semi-Supervised Speech Recognition","created":"2021-06-16","cited_by_count":40,"area":null},{"id":"2205.09723","title":"Robust and Efficient Medical Imaging with Self-Supervision","created":"2022-05-19","cited_by_count":40,"area":null},{"id":"2408.14340","title":"Foundation Models for Music: A Survey","created":"2024-08-26","cited_by_count":37,"area":"diffusion"},{"id":"2205.12523","title":"TranSpeech: Speech-to-Speech Translation With Bilateral Perturbation","created":"2022-05-25","cited_by_count":34,"area":null},{"id":"2206.02353","title":"Beyond Just Vision: A Review on Self-Supervised Representation Learning on Multimodal and Temporal Data","created":"2022-06-06","cited_by_count":27,"area":null},{"id":"2302.06419","title":"AV-data2vec: Self-supervised Learning of Audio-Visual Speech Representations with Contextualized Target Representations","created":"2023-02-10","cited_by_count":27,"area":null},{"id":"2201.10207","title":"SPIRAL: Self-supervised Perturbation-Invariant Representation Learning for Speech Pre-Training","created":"2022-01-25","cited_by_count":19,"area":"distill"},{"id":"2106.00273","title":"Improving the Adversarial Robustness for Speaker Verification by Self-Supervised Learning","created":"2021-06-01","cited_by_count":16,"area":null},{"id":"2112.08778","title":"Self-Supervised Learning for speech recognition with Intermediate layer supervision","created":"2021-12-16","cited_by_count":15,"area":null},{"id":"2204.01397","title":"A Study of Gender Impact in Self-supervised Models for Speech-to-Text Systems","created":"2022-04-04","cited_by_count":15,"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":"2104.07474","title":"EAT: Enhanced ASR-TTS for Self-supervised Speech Recognition","created":"2021-04-13","cited_by_count":13,"area":null},{"id":"2203.17113","title":"Pre-Training Transformer Decoder for End-to-End ASR Model with Unpaired Speech Data","created":"2022-03-31","cited_by_count":12,"area":null},{"id":"2103.05149","title":"Contrastive Semi-supervised Learning for ASR","created":"2021-03-09","cited_by_count":11,"area":null},{"id":"2203.01829","title":"A Brief Overview of Unsupervised Neural Speech Representation Learning","created":"2022-03-01","cited_by_count":9,"area":null},{"id":"2206.13654","title":"Wav2Vec-Aug: Improved self-supervised training with limited data","created":"2022-06-27","cited_by_count":9,"area":null},{"id":"2110.13492","title":"TUNet: A Block-online Bandwidth Extension Model based on Transformers and Self-supervised Pretraining","created":"2021-10-26","cited_by_count":8,"area":null},{"id":"2210.02956","title":"Are word boundaries useful for unsupervised language learning?","created":"2022-10-06","cited_by_count":8,"area":null},{"id":"2211.01522","title":"Losses Can Be Blessings: Routing Self-Supervised Speech Representations Towards Efficient Multilingual and Multitask Speech Processing","created":"2022-11-02","cited_by_count":7,"area":null},{"id":"2205.01987","title":"ON-TRAC Consortium Systems for the IWSLT 2022 Dialect and Low-resource Speech Translation Tasks","created":"2022-05-04","cited_by_count":6,"area":null},{"id":"2209.14085","title":"PTSD in the Wild: A Video Database for Studying Post-Traumatic Stress Disorder Recognition in Unconstrained Environments","created":"2022-09-28","cited_by_count":6,"area":null},{"id":"2409.08805","title":"Exploring SSL Discrete Tokens for Multilingual ASR","created":"2024-09-13","cited_by_count":6,"area":null},{"id":"2102.06816","title":"Bi-APC: Bidirectional Autoregressive Predictive Coding for Unsupervised Pre-training and Its Application to Children's ASR","created":"2021-02-12","cited_by_count":5,"area":null},{"id":"2106.04897","title":"Unsupervised Automatic Speech Recognition: A Review","created":"2021-06-09","cited_by_count":5,"area":null},{"id":"2303.09455","title":"Learning Cross-lingual Visual Speech Representations","created":"2023-03-14","cited_by_count":5,"area":null},{"id":"2306.04374","title":"Label Aware Speech Representation Learning For Language Identification","created":"2023-06-07","cited_by_count":4,"area":null},{"id":"2311.04534","title":"Loss Masking Is Not Needed in Decoder-only Transformer for Discrete-token-based ASR","created":"2023-11-08","cited_by_count":4,"area":null},{"id":"2409.02384","title":"STAB: Speech Tokenizer Assessment Benchmark","created":"2024-09-04","cited_by_count":4,"area":null},{"id":"2103.08993","title":"Fast Development of ASR in African Languages using Self Supervised Speech Representation Learning","created":"2021-03-16","cited_by_count":3,"area":null},{"id":"2112.08692","title":"Lacuna Reconstruction: Self-supervised Pre-training for Low-Resource Historical Document Transcription","created":"2021-12-16","cited_by_count":3,"area":null},{"id":"2211.03025","title":"Bridging Speech and Textual Pre-trained Models with Unsupervised ASR","created":"2022-11-06","cited_by_count":3,"area":null},{"id":"2401.06832","title":"XLS-R Deep Learning Model for Multilingual ASR on Low- Resource Languages: Indonesian, Javanese, and Sundanese","created":"2024-01-12","cited_by_count":3,"area":null},{"id":"2410.19935","title":"Do Discrete Self-Supervised Representations of Speech Capture Tone Distinctions?","created":"2024-10-25","cited_by_count":3,"area":null},{"id":"2511.16639","title":"Codec2Vec: Self-Supervised Speech Representation Learning Using Neural Speech Codecs","created":"2025-11-20","cited_by_count":3,"area":null},{"id":"2106.04298","title":"Unsupervised Word Segmentation from Discrete Speech Units in Low-Resource Settings","created":"2021-06-08","cited_by_count":2,"area":null},{"id":"2203.16973","title":"Analyzing the factors affecting usefulness of Self-Supervised Pre-trained Representations for Speech Recognition","created":"2022-03-31","cited_by_count":2,"area":null},{"id":"2308.11589","title":"Indonesian Automatic Speech Recognition with XLSR-53","created":"2023-08-20","cited_by_count":2,"area":null},{"id":"2406.05661","title":"MS-HuBERT: Mitigating Pre-training and Inference Mismatch in Masked Language Modelling methods for learning Speech Representations","created":"2024-06-09","cited_by_count":2,"area":null},{"id":"2409.08797","title":"Exploring SSL Discrete Speech Features for Zipformer-based Contextual ASR","created":"2024-09-13","cited_by_count":2,"area":null},{"id":"2310.00816","title":"Sharingan: A Transformer-based Architecture for Gaze Following","created":"2023-10-01","cited_by_count":1,"area":null},{"id":"2407.03734","title":"Improving Self-supervised Pre-training using Accent-Specific Codebooks","created":"2024-07-04","cited_by_count":1,"area":null},{"id":"2502.00421","title":"Sagalee: an Open Source Automatic Speech Recognition Dataset for Oromo Language","created":"2025-02-01","cited_by_count":1,"area":null},{"id":"2508.04814","title":"Pitch Accent Detection improves Pretrained Automatic Speech Recognition","created":"2025-08-06","cited_by_count":1,"area":null},{"id":"2209.02073","title":"A Study on Representation Transfer for Few-Shot Learning","created":"2022-09-05","cited_by_count":0,"area":null},{"id":"2210.07323","title":"Experiments on Turkish ASR with Self-Supervised Speech Representation Learning","created":"2022-10-13","cited_by_count":0,"area":null},{"id":"2301.04327","title":"Dual Learning for Large Vocabulary On-Device ASR","created":"2023-01-11","cited_by_count":0,"area":null},{"id":"2309.07765","title":"Echotune: A Modular Extractor Leveraging the Variable-Length Nature of Speech in ASR Tasks","created":"2023-09-14","cited_by_count":0,"area":null},{"id":"2405.13274","title":"DiffNorm: Self-Supervised Normalization for Non-autoregressive Speech-to-speech Translation","created":"2024-05-22","cited_by_count":0,"area":null},{"id":"2509.15430","title":"BiRQ: Bi-Level Self-Labeling Random Quantization for Self-Supervised Speech Recognition","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2608.06122","title":"Is Self-Pretraining really useful to improve diagnosis in medical Time Series?","created":"2026-08-06","cited_by_count":0,"area":null}],"next_cursor":null}