{"total":17,"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":"2102.01192","title":"Generative Spoken Language Modeling from Raw Audio","created":"2021-02-01","cited_by_count":340,"area":null},{"id":"2205.10643","title":"Self-Supervised Speech Representation Learning: A Review","created":"2022-05-21","cited_by_count":260,"area":null},{"id":"2205.08180","title":"SAMU-XLSR: Semantically-Aligned Multimodal Utterance-level Cross-Lingual Speech Representation","created":"2022-05-17","cited_by_count":32,"area":null},{"id":"2111.07402","title":"Textless Speech Emotion Conversion using Discrete and Decomposed Representations","created":"2021-11-14","cited_by_count":29,"area":null},{"id":"2103.06089","title":"Variable-rate discrete representation learning","created":"2021-03-10","cited_by_count":24,"area":null},{"id":"2104.11946","title":"Aligned Contrastive Predictive Coding","created":"2021-04-24","cited_by_count":15,"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":"2107.00594","title":"Pretext Tasks selection for multitask self-supervised speech representation learning","created":"2021-07-01","cited_by_count":7,"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":"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":"2102.00850","title":"On Scaling Contrastive Representations for Low-Resource Speech Recognition","created":"2021-02-01","cited_by_count":3,"area":null},{"id":"2104.07388","title":"Conditional independence for pretext task selection in Self-supervised speech representation learning","created":"2021-04-15","cited_by_count":3,"area":null},{"id":"2201.02397","title":"Neural calibration of hidden inhomogeneous Markov chains -- Information decompression in life insurance","created":"2022-01-07","cited_by_count":0,"area":null},{"id":"2210.08182","title":"Learning Invariant Representation and Risk Minimized for Unsupervised Accent Domain Adaptation","created":"2022-10-15","cited_by_count":0,"area":null},{"id":"2308.08027","title":"End-to-End Open Vocabulary Keyword Search With Multilingual Neural Representations","created":"2023-08-15","cited_by_count":0,"area":null},{"id":"2407.04601","title":"Written Term Detection Improves Spoken Term Detection","created":"2024-07-05","cited_by_count":0,"area":null}],"next_cursor":null}