{"total":44,"rows":[{"id":"2107.03312","title":"SoundStream: An End-to-End Neural Audio Codec","created":"2021-07-07","cited_by_count":771,"area":null},{"id":"2210.13438","title":"High Fidelity Neural Audio Compression","created":"2022-10-24","cited_by_count":687,"area":null},{"id":"2306.06546","title":"High-Fidelity Audio Compression with Improved RVQGAN","created":"2023-06-11","cited_by_count":431,"area":null},{"id":"2104.00355","title":"Speech Resynthesis from Discrete Disentangled Self-Supervised Representations","created":"2021-04-01","cited_by_count":243,"area":null},{"id":"2307.04686","title":"VampNet: Music Generation via Masked Acoustic Token Modeling","created":"2023-07-10","cited_by_count":57,"area":null},{"id":"2405.00233","title":"SemantiCodec: An Ultra Low Bitrate Semantic Audio Codec for General Sound","created":"2024-04-30","cited_by_count":45,"area":null},{"id":"2410.14411","title":"SNAC: Multi-Scale Neural Audio Codec","created":"2024-10-18","cited_by_count":43,"area":null},{"id":"2309.00169","title":"RepCodec: A Speech Representation Codec for Speech Tokenization","created":"2023-08-31","cited_by_count":27,"area":null},{"id":"2203.17263","title":"Audio-Visual Speech Codecs: Rethinking Audio-Visual Speech Enhancement by Re-Synthesis","created":"2022-03-31","cited_by_count":24,"area":null},{"id":"2310.19180","title":"JEN-1 Composer: A Unified Framework for High-Fidelity Multi-Track Music Generation","created":"2023-10-29","cited_by_count":17,"area":null},{"id":"2106.02797","title":"Neural Distributed Source Coding","created":"2021-06-05","cited_by_count":13,"area":null},{"id":"2409.12117","title":"Low Frame-rate Speech Codec: a Codec Designed for Fast High-quality Speech LLM Training and Inference","created":"2024-09-18","cited_by_count":11,"area":null},{"id":"2211.11960","title":"Disentangled Feature Learning for Real-Time Neural Speech Coding","created":"2022-11-22","cited_by_count":10,"area":null},{"id":"2209.10887","title":"A Multi-Stage Multi-Codebook VQ-VAE Approach to High-Performance Neural TTS","created":"2022-09-22","cited_by_count":9,"area":null},{"id":"2102.06610","title":"Enhancing into the codec: Noise Robust Speech Coding with Vector-Quantized Autoencoders","created":"2021-02-12","cited_by_count":7,"area":null},{"id":"2107.10843","title":"HARP-Net: Hyper-Autoencoded Reconstruction Propagation for Scalable Neural Audio Coding","created":"2021-07-22","cited_by_count":7,"area":null},{"id":"2201.09429","title":"End-to-End Neural Speech Coding for Real-Time Communications","created":"2022-01-24","cited_by_count":7,"area":null},{"id":"2207.08363","title":"Latent-Domain Predictive Neural Speech Coding","created":"2022-07-18","cited_by_count":7,"area":null},{"id":"2409.12139","title":"Takin: A Cohort of Superior Quality Zero-shot Speech Generation Models","created":"2024-09-18","cited_by_count":7,"area":null},{"id":"2110.14182","title":"Evidential Softmax for Sparse Multimodal Distributions in Deep Generative Models","created":"2021-10-27","cited_by_count":6,"area":null},{"id":"2203.15578","title":"Disentangling speech from surroundings with neural embeddings","created":"2022-03-29","cited_by_count":6,"area":null},{"id":"2409.11228","title":"Learning Source Disentanglement in Neural Audio Codec","created":"2024-09-17","cited_by_count":6,"area":null},{"id":"2103.14776","title":"Scalable and Efficient Neural Speech Coding: A Hybrid Design","created":"2021-03-27","cited_by_count":5,"area":null},{"id":"2207.02262","title":"Ultra-Low-Bitrate Speech Coding with Pretrained Transformers","created":"2022-07-05","cited_by_count":5,"area":null},{"id":"2404.04947","title":"Gull: A Generative Multifunctional Audio Codec","created":"2024-04-07","cited_by_count":5,"area":null},{"id":"2508.02849","title":"SecoustiCodec: Cross-Modal Aligned Streaming Single-Codecbook Speech Codec","created":"2025-08-04","cited_by_count":5,"area":null},{"id":"2207.03697","title":"End-to-End Binaural Speech Synthesis","created":"2022-07-08","cited_by_count":4,"area":null},{"id":"2207.03067","title":"Cross-Scale Vector Quantization for Scalable Neural Speech Coding","created":"2022-07-07","cited_by_count":3,"area":null},{"id":"2207.03282","title":"NESC: Robust Neural End-2-End Speech Coding with GANs","created":"2022-07-07","cited_by_count":3,"area":null},{"id":"2404.02702","title":"PSCodec: A Series of High-Fidelity Low-bitrate Neural Speech Codecs Leveraging Prompt Encoders","created":"2024-04-03","cited_by_count":3,"area":null},{"id":"2503.12115","title":"Universal Speech Token Learning via Low-Bitrate Neural Codec and Pretrained Representations","created":"2025-03-15","cited_by_count":3,"area":null},{"id":"2503.12814","title":"Versatile Physics-based Character Control with Hybrid Latent Representation","created":"2025-03-17","cited_by_count":3,"area":null},{"id":"2110.04241","title":"Cognitive Coding of Speech","created":"2021-10-08","cited_by_count":2,"area":null},{"id":"2211.06733","title":"Deep Reinforcement Learning with Vector Quantized Encoding","created":"2022-11-12","cited_by_count":2,"area":null},{"id":"2408.06954","title":"Neural Speech and Audio Coding: Modern AI Technology Meets Traditional Codecs","created":"2024-08-13","cited_by_count":2,"area":null},{"id":"2211.08715","title":"Conditional variational autoencoder to improve neural audio synthesis for polyphonic music sound","created":"2022-11-16","cited_by_count":1,"area":null},{"id":"2308.07221","title":"AudioFormer: Audio Transformer learns audio feature representations from discrete acoustic codes","created":"2023-08-14","cited_by_count":1,"area":null},{"id":"2309.00126","title":"QS-TTS: Towards Semi-Supervised Text-to-Speech Synthesis via Vector-Quantized Self-Supervised Speech Representation Learning","created":"2023-08-31","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":"2505.13085","title":"Universal Semantic Disentangled Privacy-preserving Speech Representation Learning","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2102.02640","title":"Low Bit-Rate Wideband Speech Coding: A Deep Generative Model based Approach","created":"2021-02-04","cited_by_count":0,"area":null},{"id":"2109.11168","title":"Unified Signal Compression Using a GAN with Iterative Latent Representation Optimization","created":"2021-09-23","cited_by_count":0,"area":null},{"id":"2506.18544","title":"Normality Prior Guided Multi-Semantic Fusion Network for Unsupervised Image Anomaly Detection","created":"2025-06-23","cited_by_count":0,"area":null},{"id":"2610.19401","title":"Train to Stitch: Topology-Preserving Regularization for Interoperable Representations","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}