{"total":30,"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":"2104.00355","title":"Speech Resynthesis from Discrete Disentangled Self-Supervised Representations","created":"2021-04-01","cited_by_count":243,"area":null},{"id":"2207.09353","title":"Beyond Transmitting Bits: Context, Semantics, and Task-Oriented Communications","created":"2022-07-19","cited_by_count":175,"area":null},{"id":"2202.09729","title":"It's Raw! Audio Generation with State-Space Models","created":"2022-02-20","cited_by_count":171,"area":null},{"id":"2201.12904","title":"COIN++: Neural Compression Across Modalities","created":"2022-01-30","cited_by_count":82,"area":null},{"id":"2112.09382","title":"Discretization and Re-synthesis: an alternative method to solve the Cocktail Party Problem","created":"2021-12-17","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":"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":"2106.08887","title":"WaveNet-Based Deep Neural Networks for the Characterization of Anomalous Diffusion (WADNet)","created":"2021-06-14","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":"2103.14776","title":"Scalable and Efficient Neural Speech Coding: A Hybrid Design","created":"2021-03-27","cited_by_count":5,"area":null},{"id":"2108.04051","title":"A Streamwise GAN Vocoder for Wideband Speech Coding at Very Low Bit Rate","created":"2021-08-09","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":"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":"2409.17635","title":"FlowMAC: Conditional Flow Matching for Audio Coding at Low Bit Rates","created":"2024-09-26","cited_by_count":3,"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":"2209.06358","title":"Using Rater and System Metadata to Explain Variance in the VoiceMOS Challenge 2022 Dataset","created":"2022-09-14","cited_by_count":1,"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":"2306.12785","title":"MFCCGAN: A Novel MFCC-Based Speech Synthesizer Using Adversarial Learning","created":"2023-06-22","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":"2409.07858","title":"Audio Decoding by Inverse Problem Solving","created":"2024-09-12","cited_by_count":1,"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":"2202.11169","title":"Neural Speech Synthesis on a Shoestring: Improving the Efficiency of LPCNet","created":"2022-02-22","cited_by_count":0,"area":null},{"id":"2602.15082","title":"S-PRESSO: Ultra Low Bitrate Sound Effect Compression With Diffusion Autoencoders And Offline Quantization","created":"2026-02-16","cited_by_count":0,"area":null}],"next_cursor":null}