{"total":22,"rows":[{"id":"2309.15505","title":"Finite Scalar Quantization: VQ-VAE Made Simple","created":"2023-09-27","cited_by_count":440,"area":null},{"id":"2203.16502","title":"Generative Spoken Dialogue Language Modeling","created":"2022-03-30","cited_by_count":126,"area":null},{"id":"2201.10326","title":"ShapeFormer: Transformer-based Shape Completion via Sparse Representation","created":"2022-01-25","cited_by_count":106,"area":null},{"id":"2507.07955","title":"Dynamic Chunking for End-to-End Hierarchical Sequence Modeling","created":"2025-07-10","cited_by_count":72,"area":null},{"id":"2111.03017","title":"MT3: Multi-Task Multitrack Music Transcription","created":"2021-11-04","cited_by_count":71,"area":null},{"id":"2410.08368","title":"ElasticTok: Adaptive Tokenization for Image and Video","created":"2024-10-10","cited_by_count":46,"area":null},{"id":"2502.06490","title":"Recent Advances in Discrete Speech Tokens: A Review","created":"2025-02-10","cited_by_count":43,"area":null},{"id":"2412.18603","title":"Long-Form Speech Generation with Spoken Language Models","created":"2024-12-24","cited_by_count":19,"area":null},{"id":"2104.11946","title":"Aligned Contrastive Predictive Coding","created":"2021-04-24","cited_by_count":15,"area":null},{"id":"2206.02211","title":"Variable-rate hierarchical CPC leads to acoustic unit discovery in speech","created":"2022-06-05","cited_by_count":13,"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":"2210.07189","title":"On Compressing Sequences for Self-Supervised Speech Models","created":"2022-10-13","cited_by_count":8,"area":null},{"id":"2306.01108","title":"Towards Learning Discrete Representations via Self-Supervision for Wearables-Based Human Activity Recognition","created":"2023-06-01","cited_by_count":7,"area":null},{"id":"2410.06016","title":"Variable Bitrate Residual Vector Quantization for Audio Coding","created":"2024-10-08","cited_by_count":6,"area":null},{"id":"2206.08094","title":"Deep Neural Imputation: A Framework for Recovering Incomplete Brain Recordings","created":"2022-06-16","cited_by_count":5,"area":null},{"id":"2402.03269","title":"ISPA: Inter-Species Phonetic Alphabet for Transcribing Animal Sounds","created":"2024-02-05","cited_by_count":4,"area":null},{"id":"2406.05547","title":"Exploring the Benefits of Tokenization of Discrete Acoustic Units","created":"2024-06-08","cited_by_count":4,"area":null},{"id":"2601.23174","title":"Beyond Fixed Frames: Dynamic Character-Aligned Speech Tokenization","created":"2026-01-30","cited_by_count":4,"area":null},{"id":"2111.00610","title":"Towards Language Modelling in the Speech Domain Using Sub-word Linguistic Units","created":"2021-10-31","cited_by_count":1,"area":null},{"id":"2210.16659","title":"Learning Dependencies of Discrete Speech Representations with Neural Hidden Markov Models","created":"2022-10-29","cited_by_count":1,"area":null},{"id":"2402.01571","title":"Spiking Music: Audio Compression with Event Based Auto-encoders","created":"2024-02-02","cited_by_count":1,"area":null},{"id":"2404.00856","title":"Removing Speaker Information from Speech Representation using Variable-Length Soft Pooling","created":"2024-04-01","cited_by_count":1,"area":null}],"next_cursor":null}