{"total":183,"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":"2209.03143","title":"AudioLM: a Language Modeling Approach to Audio Generation","created":"2022-09-07","cited_by_count":616,"area":null},{"id":"2103.03841","title":"Generating Images with Sparse Representations","created":"2021-03-05","cited_by_count":266,"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":"2104.08378","title":"Accelerating Sparse Deep Neural Networks","created":"2021-04-16","cited_by_count":223,"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":"2305.07185","title":"MEGABYTE: Predicting Million-byte Sequences with Multiscale Transformers","created":"2023-05-12","cited_by_count":170,"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":"2307.10802","title":"Meta-Transformer: A Unified Framework for Multimodal Learning","created":"2023-07-20","cited_by_count":136,"area":null},{"id":"2106.03517","title":"Top-KAST: Top-K Always Sparse Training","created":"2021-06-07","cited_by_count":79,"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":"2203.03022","title":"HEAR: Holistic Evaluation of Audio Representations","created":"2022-03-06","cited_by_count":78,"area":null},{"id":"2107.08661","title":"Translatotron 2: High-quality direct speech-to-speech translation with voice preservation","created":"2021-07-19","cited_by_count":71,"area":null},{"id":"2201.03713","title":"CVSS Corpus and Massively Multilingual Speech-to-Speech Translation","created":"2022-01-11","cited_by_count":71,"area":null},{"id":"2204.00628","title":"Learning Neural Acoustic Fields","created":"2022-04-04","cited_by_count":65,"area":null},{"id":"2107.05677","title":"Codified audio language modeling learns useful representations for music information retrieval","created":"2021-07-12","cited_by_count":64,"area":null},{"id":"2206.10369","title":"The State of Sparse Training in Deep Reinforcement Learning","created":"2022-06-17","cited_by_count":61,"area":null},{"id":"2103.15060","title":"PnG BERT: Augmented BERT on Phonemes and Graphemes for Neural TTS","created":"2021-03-28","cited_by_count":52,"area":null},{"id":"2305.15719","title":"Efficient Neural Music Generation","created":"2023-05-25","cited_by_count":50,"area":null},{"id":"2110.00296","title":"Powerpropagation: A sparsity inducing weight reparameterisation","created":"2021-10-01","cited_by_count":49,"area":null},{"id":"2106.14568","title":"Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity","created":"2021-06-28","cited_by_count":44,"area":null},{"id":"2210.14889","title":"Perfectly Secure Steganography Using Minimum Entropy Coupling","created":"2022-10-24","cited_by_count":44,"area":null},{"id":"2112.11231","title":"Accurate online training of dynamical spiking neural networks through Forward Propagation Through Time","created":"2021-12-20","cited_by_count":34,"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":"2105.09564","title":"Dual-side Sparse Tensor Core","created":"2021-05-20","cited_by_count":29,"area":null},{"id":"2407.10387","title":"Masked Generative Video-to-Audio Transformers with Enhanced Synchronicity","created":"2024-07-15","cited_by_count":28,"area":null},{"id":"2101.09048","title":"Selfish Sparse RNN Training","created":"2021-01-22","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":"2106.02297","title":"Fre-GAN: Adversarial Frequency-consistent Audio Synthesis","created":"2021-06-04","cited_by_count":24,"area":null},{"id":"2111.12890","title":"V2C: Visual Voice Cloning","created":"2021-11-25","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":"2303.01664","title":"Miipher: A Robust Speech Restoration Model Integrating Self-Supervised Speech and Text Representations","created":"2023-03-03","cited_by_count":22,"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":"2106.16036","title":"A Generative Model for Raw Audio Using Transformer Architectures","created":"2021-06-30","cited_by_count":18,"area":null},{"id":"2103.16809","title":"Limited Data Emotional Voice Conversion Leveraging Text-to-Speech: Two-stage Sequence-to-Sequence Training","created":"2021-03-31","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":"2105.14713","title":"1xN Pattern for Pruning Convolutional Neural Networks","created":"2021-05-31","cited_by_count":16,"area":null},{"id":"2202.07190","title":"Pruning Networks with Cross-Layer Ranking & k-Reciprocal Nearest Filters","created":"2022-02-15","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":"2405.15743","title":"Sparse maximal update parameterization: A holistic approach to sparse training dynamics","created":"2024-05-24","cited_by_count":16,"area":null},{"id":"2103.02644","title":"Compute and memory efficient universal sound source separation","created":"2021-03-03","cited_by_count":15,"area":null},{"id":"2106.12896","title":"Non-Autoregressive TTS with Explicit Duration Modelling for Low-Resource Highly Expressive Speech","created":"2021-06-24","cited_by_count":14,"area":null},{"id":"2111.05095","title":"Speaker Generation","created":"2021-11-07","cited_by_count":14,"area":null},{"id":"2208.09646","title":"An Initial Investigation for Detecting Vocoder Fingerprints of Fake Audio","created":"2022-08-20","cited_by_count":14,"area":null},{"id":"2110.03342","title":"VisualTTS: TTS with Accurate Lip-Speech Synchronization for Automatic Voice Over","created":"2021-10-07","cited_by_count":13,"area":null},{"id":"2304.14082","title":"JaxPruner: A concise library for sparsity research","created":"2023-04-27","cited_by_count":13,"area":null},{"id":"2409.10847","title":"BAD: Bidirectional Auto-regressive Diffusion for Text-to-Motion Generation","created":"2024-09-17","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":"2305.17547","title":"Translatotron 3: Speech to Speech Translation with Monolingual Data","created":"2023-05-27","cited_by_count":12,"area":null},{"id":"2209.07617","title":"Training Recipe for N:M Structured Sparsity with Decaying Pruning Mask","created":"2022-09-15","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":"2107.09355","title":"Approximation Theory of Convolutional Architectures for Time Series Modelling","created":"2021-07-20","cited_by_count":10,"area":null},{"id":"2204.01672","title":"Residual-guided Personalized Speech Synthesis based on Face Image","created":"2022-04-01","cited_by_count":10,"area":null},{"id":"2209.14458","title":"The Chamber Ensemble Generator: Limitless High-Quality MIR Data via Generative Modeling","created":"2022-09-28","cited_by_count":10,"area":null},{"id":"2210.15868","title":"Residual Adapters for Few-Shot Text-to-Speech Speaker Adaptation","created":"2022-10-28","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":"2110.02952","title":"Hierarchical prosody modeling and control in non-autoregressive parallel neural TTS","created":"2021-10-06","cited_by_count":9,"area":null},{"id":"2110.03012","title":"Emphasis control for parallel neural TTS","created":"2021-10-06","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":"2210.15975","title":"Lightweight and High-Fidelity End-to-End Text-to-Speech with Multi-Band Generation and Inverse Short-Time Fourier Transform","created":"2022-10-28","cited_by_count":9,"area":null},{"id":"2212.01076","title":"Are Straight-Through gradients and Soft-Thresholding all you need for Sparse Training?","created":"2022-12-02","cited_by_count":9,"area":null},{"id":"2106.08352","title":"Ctrl-P: Temporal Control of Prosodic Variation for Speech Synthesis","created":"2021-06-15","cited_by_count":8,"area":null},{"id":"2112.03099","title":"VocBench: A Neural Vocoder Benchmark for Speech Synthesis","created":"2021-12-06","cited_by_count":8,"area":null},{"id":"2203.03324","title":"Dynamic ConvNets on Tiny Devices via Nested Sparsity","created":"2022-03-07","cited_by_count":8,"area":null},{"id":"2102.07786","title":"PeriodNet: A non-autoregressive waveform generation model with a structure separating periodic and aperiodic components","created":"2021-02-15","cited_by_count":7,"area":null},{"id":"2203.10750","title":"WeSinger: Data-augmented Singing Voice Synthesis with Auxiliary Losses","created":"2022-03-21","cited_by_count":7,"area":null},{"id":"2206.07373","title":"NatiQ: An End-to-end Text-to-Speech System for Arabic","created":"2022-06-15","cited_by_count":7,"area":null},{"id":"2312.14880","title":"SutraNets: Sub-series Autoregressive Networks for Long-Sequence, Probabilistic Forecasting","created":"2023-12-22","cited_by_count":7,"area":null},{"id":"2409.08346","title":"Towards Quantifying and Reducing Language Mismatch Effects in Cross-Lingual Speech Anti-Spoofing","created":"2024-09-12","cited_by_count":7,"area":null},{"id":"2101.05313","title":"Whispered and Lombard Neural Speech Synthesis","created":"2021-01-13","cited_by_count":6,"area":null},{"id":"2203.15873","title":"An Overview & Analysis of Sequence-to-Sequence Emotional Voice Conversion","created":"2022-03-29","cited_by_count":6,"area":null},{"id":"2208.10913","title":"Deepfake: Definitions, Performance Metrics and Standards, Datasets and Benchmarks, and a Meta-Review","created":"2022-08-21","cited_by_count":6,"area":null},{"id":"2210.11096","title":"Robust One-Shot Singing Voice Conversion","created":"2022-10-20","cited_by_count":6,"area":null},{"id":"2309.02836","title":"BigVSAN: Enhancing GAN-based Neural Vocoders with Slicing Adversarial Network","created":"2023-09-06","cited_by_count":6,"area":null},{"id":"2412.19279","title":"Improving Generalization for AI-Synthesized Voice Detection","created":"2024-12-26","cited_by_count":6,"area":null},{"id":"2103.14512","title":"Continual Speaker Adaptation for Text-to-Speech Synthesis","created":"2021-03-26","cited_by_count":5,"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":"2104.11051","title":"Protecting gender and identity with disentangled speech representations","created":"2021-04-22","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":"2111.00962","title":"RefineGAN: Universally Generating Waveform Better than Ground Truth with Highly Accurate Pitch and Intensity Responses","created":"2021-11-01","cited_by_count":5,"area":null},{"id":"2203.11562","title":"A Text-to-Speech Pipeline, Evaluation Methodology, and Initial Fine-Tuning Results for Child Speech Synthesis","created":"2022-03-22","cited_by_count":5,"area":null},{"id":"2204.11304","title":"Dictionary Attacks on Speaker Verification","created":"2022-04-24","cited_by_count":5,"area":null},{"id":"2205.06053","title":"Unified Source-Filter GAN with Harmonic-plus-Noise Source Excitation Generation","created":"2022-05-12","cited_by_count":5,"area":null},{"id":"2211.01751","title":"Iterative autoregression: a novel trick to improve your low-latency speech enhancement model","created":"2022-11-03","cited_by_count":5,"area":null},{"id":"2306.00998","title":"Towards Selection of Text-to-speech Data to Augment ASR Training","created":"2023-05-30","cited_by_count":5,"area":null},{"id":"2106.12699","title":"Distilling the Knowledge from Conditional Normalizing Flows","created":"2021-06-24","cited_by_count":4,"area":null},{"id":"2110.07187","title":"Revisiting IPA-based Cross-lingual Text-to-speech","created":"2021-10-14","cited_by_count":4,"area":null},{"id":"2111.10003","title":"Differentiable Wavetable Synthesis","created":"2021-11-19","cited_by_count":4,"area":null},{"id":"2303.13909","title":"Wave-U-Net Discriminator: Fast and Lightweight Discriminator for Generative Adversarial Network-Based Speech Synthesis","created":"2023-03-24","cited_by_count":4,"area":null},{"id":"2308.07117","title":"iSTFTNet2: Faster and More Lightweight iSTFT-Based Neural Vocoder Using 1D-2D CNN","created":"2023-08-14","cited_by_count":4,"area":null},{"id":"2404.10824","title":"Decoupled Weight Decay for Any $p$ Norm","created":"2024-04-16","cited_by_count":4,"area":null}],"next_cursor":"100"}