{"total":24,"rows":[{"id":"2301.02111","title":"Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers","created":"2023-01-05","cited_by_count":752,"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":"2106.15561","title":"A Survey on Neural Speech Synthesis","created":"2021-06-29","cited_by_count":184,"area":null},{"id":"2305.13009","title":"Textually Pretrained Speech Language Models","created":"2023-05-22","cited_by_count":101,"area":null},{"id":"2209.02842","title":"ASR2K: Speech Recognition for Around 2000 Languages without Audio","created":"2022-09-06","cited_by_count":26,"area":null},{"id":"2107.07402","title":"CLSRIL-23: Cross Lingual Speech Representations for Indic Languages","created":"2021-07-15","cited_by_count":22,"area":null},{"id":"2310.05224","title":"Generative Spoken Language Model based on continuous word-sized audio tokens","created":"2023-10-08","cited_by_count":19,"area":null},{"id":"2209.15483","title":"Augmentation Invariant Discrete Representation for Generative Spoken Language Modeling","created":"2022-09-30","cited_by_count":17,"area":null},{"id":"2207.04356","title":"A Comparative Study of Self-supervised Speech Representation Based Voice Conversion","created":"2022-07-10","cited_by_count":9,"area":null},{"id":"2409.03701","title":"LAST: Language Model Aware Speech Tokenization","created":"2024-09-05","cited_by_count":9,"area":null},{"id":"2407.17852","title":"Scaling A Simple Approach to Zero-Shot Speech Recognition","created":"2024-07-25","cited_by_count":8,"area":null},{"id":"2201.11207","title":"Discovering Phonetic Inventories with Crosslingual Automatic Speech Recognition","created":"2022-01-26","cited_by_count":5,"area":null},{"id":"2206.08790","title":"Self-supervised speech unit discovery from articulatory and acoustic features using VQ-VAE","created":"2022-06-17","cited_by_count":5,"area":null},{"id":"2406.00146","title":"A Survey of Deep Learning Audio Generation Methods","created":"2024-05-31","cited_by_count":5,"area":null},{"id":"2105.05582","title":"Discrete representations in neural models of spoken language","created":"2021-05-12","cited_by_count":3,"area":null},{"id":"2401.03936","title":"Exploratory Evaluation of Speech Content Masking","created":"2024-01-08","cited_by_count":3,"area":null},{"id":"2405.14222","title":"Rate-Adaptive Quantization: A Multi-Rate Codebook Adaptation for Vector Quantization-based Generative Models","created":"2024-05-23","cited_by_count":3,"area":null},{"id":"2506.02599","title":"Assessing the Completeness of Traffic Scenario Categories for Automated Highway Driving Functions via Cluster-based Analysis","created":"2025-06-03","cited_by_count":3,"area":null},{"id":"2511.15055","title":"Learning Human-Like RL Agents Through Trajectory Optimization With Action Quantization","created":"2025-11-19","cited_by_count":3,"area":null},{"id":"2105.01786","title":"Voice Conversion Based Speaker Normalization for Acoustic Unit Discovery","created":"2021-05-04","cited_by_count":0,"area":null},{"id":"2106.13479","title":"Preliminary study on using vector quantization latent spaces for TTS/VC systems with consistent performance","created":"2021-06-25","cited_by_count":0,"area":null},{"id":"2302.01144","title":"UW-CVGAN: UnderWater Image Enhancement with Capsules Vectors Quantization","created":"2023-02-02","cited_by_count":0,"area":null},{"id":"2503.22063","title":"Arch-VQ: Discrete Architecture Representation Learning with Autoregressive Priors","created":"2025-03-28","cited_by_count":0,"area":null}],"next_cursor":null}