{"total":262,"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":"2306.06546","title":"High-Fidelity Audio Compression with Improved RVQGAN","created":"2023-06-11","cited_by_count":431,"area":null},{"id":"2102.01192","title":"Generative Spoken Language Modeling from Raw Audio","created":"2021-02-01","cited_by_count":340,"area":null},{"id":"2112.02418","title":"YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone","created":"2021-12-04","cited_by_count":278,"area":null},{"id":"2103.04922","title":"Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models","created":"2021-03-08","cited_by_count":252,"area":null},{"id":"2206.04658","title":"BigVGAN: A Universal Neural Vocoder with Large-Scale Training","created":"2022-06-09","cited_by_count":251,"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":"2106.15561","title":"A Survey on Neural Speech Synthesis","created":"2021-06-29","cited_by_count":184,"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":"2306.00814","title":"Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis","created":"2023-06-01","cited_by_count":153,"area":null},{"id":"2205.04421","title":"NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Quality","created":"2022-05-09","cited_by_count":152,"area":null},{"id":"2103.16877","title":"ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows","created":"2021-03-31","cited_by_count":113,"area":null},{"id":"2106.10410","title":"Deep Generative Learning via Schr\\\"{o}dinger Bridge","created":"2021-06-19","cited_by_count":104,"area":null},{"id":"2305.13009","title":"Textually Pretrained Speech Language Models","created":"2023-05-22","cited_by_count":101,"area":null},{"id":"2410.03751","title":"Recent Advances in Speech Language Models: A Survey","created":"2024-10-01","cited_by_count":87,"area":null},{"id":"2111.02813","title":"WaveFake: A Data Set to Facilitate Audio Deepfake Detection","created":"2021-11-04","cited_by_count":78,"area":null},{"id":"2111.05011","title":"RAVE: A variational autoencoder for fast and high-quality neural audio synthesis","created":"2021-11-09","cited_by_count":73,"area":null},{"id":"2106.09660","title":"WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis","created":"2021-06-17","cited_by_count":65,"area":null},{"id":"2308.12770","title":"WavMark: Watermarking for Audio Generation","created":"2023-08-24","cited_by_count":50,"area":null},{"id":"2401.07333","title":"ELLA-V: Stable Neural Codec Language Modeling with Alignment-guided Sequence Reordering","created":"2024-01-14","cited_by_count":50,"area":null},{"id":"2203.13086","title":"HiFi++: a Unified Framework for Bandwidth Extension and Speech Enhancement","created":"2022-03-24","cited_by_count":49,"area":null},{"id":"2301.00591","title":"Analysing Discrete Self Supervised Speech Representation for Spoken Language Modeling","created":"2023-01-02","cited_by_count":47,"area":null},{"id":"2202.06875","title":"Visual Acoustic Matching","created":"2022-02-14","cited_by_count":45,"area":null},{"id":"2205.06924","title":"A Tale of Two Flows: Cooperative Learning of Langevin Flow and Normalizing Flow Toward Energy-Based Model","created":"2022-05-13","cited_by_count":44,"area":null},{"id":"2204.01726","title":"Lip to Speech Synthesis with Visual Context Attentional GAN","created":"2022-04-04","cited_by_count":41,"area":null},{"id":"2203.09690","title":"A$^3$T: Alignment-Aware Acoustic and Text Pretraining for Speech Synthesis and Editing","created":"2022-03-18","cited_by_count":40,"area":null},{"id":"2110.08243","title":"Neural Dubber: Dubbing for Videos According to Scripts","created":"2021-10-15","cited_by_count":39,"area":null},{"id":"2303.11607","title":"Transformers in Speech Processing: A Survey","created":"2023-03-21","cited_by_count":39,"area":null},{"id":"2210.03538","title":"An Overview of Affective Speech Synthesis and Conversion in the Deep Learning Era","created":"2022-10-06","cited_by_count":33,"area":null},{"id":"2309.01728","title":"Generative-based Fusion Mechanism for Multi-Modal Tracking","created":"2023-09-04","cited_by_count":33,"area":null},{"id":"2311.05908","title":"FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores","created":"2023-11-10","cited_by_count":33,"area":null},{"id":"2203.02395","title":"iSTFTNet: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transform","created":"2022-03-04","cited_by_count":32,"area":null},{"id":"2405.04880","title":"The Codecfake Dataset and Countermeasures for the Universally Detection of Deepfake Audio","created":"2024-05-08","cited_by_count":31,"area":null},{"id":"2202.07359","title":"textless-lib: a Library for Textless Spoken Language Processing","created":"2022-02-15","cited_by_count":28,"area":null},{"id":"2103.16211","title":"iVPF: Numerical Invertible Volume Preserving Flow for Efficient Lossless Compression","created":"2021-03-30","cited_by_count":27,"area":null},{"id":"2211.09536","title":"Towards Building Text-To-Speech Systems for the Next Billion Users","created":"2022-11-17","cited_by_count":27,"area":null},{"id":"2111.00965","title":"iFlow: Numerically Invertible Flows for Efficient Lossless Compression via a Uniform Coder","created":"2021-11-01","cited_by_count":26,"area":null},{"id":"2203.16852","title":"JETS: Jointly Training FastSpeech2 and HiFi-GAN for End to End Text to Speech","created":"2022-03-31","cited_by_count":26,"area":null},{"id":"2102.01106","title":"Universal Neural Vocoding with Parallel WaveNet","created":"2021-02-01","cited_by_count":25,"area":null},{"id":"2307.16430","title":"VITS2: Improving Quality and Efficiency of Single-Stage Text-to-Speech with Adversarial Learning and Architecture Design","created":"2023-07-31","cited_by_count":25,"area":null},{"id":"2105.02104","title":"Conditional Invertible Neural Networks for Diverse Image-to-Image Translation","created":"2021-05-05","cited_by_count":24,"area":null},{"id":"2106.02297","title":"Fre-GAN: Adversarial Frequency-consistent Audio Synthesis","created":"2021-06-04","cited_by_count":24,"area":null},{"id":"2109.06912","title":"fairseq S^2: A Scalable and Integrable Speech Synthesis Toolkit","created":"2021-09-14","cited_by_count":24,"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":"2406.10735","title":"How Should We Extract Discrete Audio Tokens from Self-Supervised Models?","created":"2024-06-15","cited_by_count":24,"area":null},{"id":"2412.06602","title":"Towards Controllable Speech Synthesis in the Era of Large Language Models: A Systematic Survey","created":"2024-12-09","cited_by_count":23,"area":null},{"id":"2106.13871","title":"Transflower: probabilistic autoregressive dance generation with multimodal attention","created":"2021-06-25","cited_by_count":22,"area":null},{"id":"2409.17285","title":"SpoofCeleb: Speech Deepfake Detection and SASV In The Wild","created":"2024-09-18","cited_by_count":22,"area":null},{"id":"2203.01993","title":"Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Values","created":"2022-03-03","cited_by_count":21,"area":null},{"id":"2203.03191","title":"Language-Agnostic Meta-Learning for Low-Resource Text-to-Speech with Articulatory Features","created":"2022-03-07","cited_by_count":20,"area":null},{"id":"2105.08164","title":"Parallel and Flexible Sampling from Autoregressive Models via Langevin Dynamics","created":"2021-05-17","cited_by_count":19,"area":null},{"id":"2111.09052","title":"High Quality Streaming Speech Synthesis with Low, Sentence-Length-Independent Latency","created":"2021-11-17","cited_by_count":19,"area":null},{"id":"2203.05940","title":"PD-Flow: A Point Cloud Denoising Framework with Normalizing Flows","created":"2022-03-11","cited_by_count":19,"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":"2102.12841","title":"MaskCycleGAN-VC: Learning Non-parallel Voice Conversion with Filling in Frames","created":"2021-02-25","cited_by_count":18,"area":null},{"id":"2103.09474","title":"STYLER: Style Factor Modeling with Rapidity and Robustness via Speech Decomposition for Expressive and Controllable Neural Text to Speech","created":"2021-03-17","cited_by_count":18,"area":null},{"id":"2106.09317","title":"EMOVIE: A Mandarin Emotion Speech Dataset with a Simple Emotional Text-to-Speech Model","created":"2021-06-17","cited_by_count":18,"area":null},{"id":"2205.06421","title":"Talking Face Generation with Multilingual TTS","created":"2022-05-13","cited_by_count":18,"area":null},{"id":"2206.13404","title":"Avocodo: Generative Adversarial Network for Artifact-free Vocoder","created":"2022-06-27","cited_by_count":18,"area":null},{"id":"2107.05893","title":"PU-Flow: a Point Cloud Upsampling Network with Normalizing Flows","created":"2021-07-13","cited_by_count":17,"area":null},{"id":"2108.04325","title":"AnyoneNet: Synchronized Speech and Talking Head Generation for Arbitrary Person","created":"2021-08-09","cited_by_count":17,"area":null},{"id":"2112.14012","title":"Solving time dependent Fokker-Planck equations via temporal normalizing flow","created":"2021-12-28","cited_by_count":17,"area":null},{"id":"2203.16930","title":"WavThruVec: Latent speech representation as intermediate features for neural speech synthesis","created":"2022-03-31","cited_by_count":17,"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":"2103.05236","title":"GAN Vocoder: Multi-Resolution Discriminator Is All You Need","created":"2021-03-09","cited_by_count":16,"area":null},{"id":"2108.11436","title":"Integrated Speech and Gesture Synthesis","created":"2021-08-25","cited_by_count":16,"area":null},{"id":"2202.09950","title":"CampNet: Context-Aware Mask Prediction for End-to-End Text-Based Speech Editing","created":"2022-02-21","cited_by_count":16,"area":null},{"id":"2209.00130","title":"Evaluating generative audio systems and their metrics","created":"2022-08-31","cited_by_count":16,"area":null},{"id":"2106.06426","title":"Catch-A-Waveform: Learning to Generate Audio from a Single Short Example","created":"2021-06-11","cited_by_count":15,"area":null},{"id":"2110.06306","title":"Fine-grained style control in Transformer-based Text-to-speech Synthesis","created":"2021-10-12","cited_by_count":15,"area":null},{"id":"2306.11503","title":"The Age of Synthetic Realities: Challenges and Opportunities","created":"2023-06-09","cited_by_count":15,"area":null},{"id":"2108.05762","title":"Multimodal analysis of the predictability of hand-gesture properties","created":"2021-08-12","cited_by_count":14,"area":null},{"id":"2211.11220","title":"STGlow: A Flow-based Generative Framework with Dual Graphormer for Pedestrian Trajectory Prediction","created":"2022-11-21","cited_by_count":14,"area":null},{"id":"2102.08328","title":"Context-Aware Prosody Correction for Text-Based Speech Editing","created":"2021-02-16","cited_by_count":13,"area":null},{"id":"2404.13056","title":"Variational Bayesian Optimal Experimental Design with Normalizing Flows","created":"2024-04-08","cited_by_count":13,"area":null},{"id":"2102.06431","title":"VARA-TTS: Non-Autoregressive Text-to-Speech Synthesis based on Very Deep VAE with Residual Attention","created":"2021-02-12","cited_by_count":12,"area":null},{"id":"2107.05050","title":"Neural Waveshaping Synthesis","created":"2021-07-11","cited_by_count":12,"area":null},{"id":"2110.05798","title":"Adapting TTS models For New Speakers using Transfer Learning","created":"2021-10-12","cited_by_count":12,"area":null},{"id":"2111.10139","title":"More than Words: In-the-Wild Visually-Driven Prosody for Text-to-Speech","created":"2021-11-19","cited_by_count":12,"area":null},{"id":"2202.06034","title":"Deep Performer: Score-to-Audio Music Performance Synthesis","created":"2022-02-12","cited_by_count":12,"area":null},{"id":"2308.15256","title":"Let There Be Sound: Reconstructing High Quality Speech from Silent Videos","created":"2023-08-29","cited_by_count":12,"area":null},{"id":"2102.00151","title":"Expressive Neural Voice Cloning","created":"2021-01-30","cited_by_count":11,"area":null},{"id":"2110.02891","title":"Style Equalization: Unsupervised Learning of Controllable Generative Sequence Models","created":"2021-10-06","cited_by_count":11,"area":null},{"id":"2401.10032","title":"FreGrad: Lightweight and Fast Frequency-aware Diffusion Vocoder","created":"2024-01-18","cited_by_count":11,"area":null},{"id":"2410.04324","title":"Where are we in audio deepfake detection? A systematic analysis over generative and detection models","created":"2024-10-06","cited_by_count":11,"area":null},{"id":"2107.00921","title":"Supervised Contrastive Learning for Accented Speech Recognition","created":"2021-07-02","cited_by_count":10,"area":null},{"id":"2107.09355","title":"Approximation Theory of Convolutional Architectures for Time Series Modelling","created":"2021-07-20","cited_by_count":10,"area":null},{"id":"2112.04748","title":"LipSound2: Self-Supervised Pre-Training for Lip-to-Speech Reconstruction and Lip Reading","created":"2021-12-09","cited_by_count":10,"area":null},{"id":"2206.06637","title":"RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks","created":"2022-06-14","cited_by_count":10,"area":null},{"id":"2408.06906","title":"VNet: A GAN-based Multi-Tier Discriminator Network for Speech Synthesis Vocoders","created":"2024-08-13","cited_by_count":10,"area":null},{"id":"2106.00992","title":"NVC-Net: End-to-End Adversarial Voice Conversion","created":"2021-06-02","cited_by_count":9,"area":null},{"id":"2109.08710","title":"On-device neural speech synthesis","created":"2021-09-17","cited_by_count":9,"area":null},{"id":"2201.02490","title":"Audio representations for deep learning in sound synthesis: A review","created":"2022-01-07","cited_by_count":9,"area":null},{"id":"2206.13979","title":"Attack Agnostic Dataset: Towards Generalization and Stabilization of Audio DeepFake Detection","created":"2022-06-27","cited_by_count":9,"area":null},{"id":"2210.06105","title":"SpecRNet: Towards Faster and More Accessible Audio DeepFake Detection","created":"2022-10-12","cited_by_count":9,"area":null},{"id":"2307.16879","title":"Image Synthesis under Limited Data: A Survey and Taxonomy","created":"2023-07-31","cited_by_count":9,"area":null},{"id":"2108.13320","title":"Neural HMMs are all you need (for high-quality attention-free TTS)","created":"2021-08-30","cited_by_count":8,"area":null},{"id":"2110.06546","title":"A Melody-Unsupervision Model for Singing Voice Synthesis","created":"2021-10-13","cited_by_count":8,"area":null},{"id":"2203.10335","title":"TO-FLOW: Efficient Continuous Normalizing Flows with Temporal Optimization adjoint with Moving Speed","created":"2022-03-19","cited_by_count":8,"area":null},{"id":"2211.06892","title":"OverFlow: Putting flows on top of neural transducers for better TTS","created":"2022-11-13","cited_by_count":8,"area":null}],"next_cursor":"100"}