{"total":79,"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":"2306.06546","title":"High-Fidelity Audio Compression with Improved RVQGAN","created":"2023-06-11","cited_by_count":431,"area":null},{"id":"2209.15352","title":"AudioGen: Textually Guided Audio Generation","created":"2022-09-30","cited_by_count":295,"area":null},{"id":"2104.09494","title":"NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced Datasets","created":"2021-04-19","cited_by_count":192,"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":"2408.06500","title":"Music2Latent: Consistency Autoencoders for Latent Audio Compression","created":"2024-08-12","cited_by_count":33,"area":"diffusion"},{"id":"2406.11427","title":"DiTTo-TTS: Diffusion Transformers for Scalable Text-to-Speech without Domain-Specific Factors","created":"2024-06-17","cited_by_count":32,"area":"diffusion"},{"id":"2107.04174","title":"EasyCom: An Augmented Reality Dataset to Support Algorithms for Easy Communication in Noisy Environments","created":"2021-07-09","cited_by_count":31,"area":null},{"id":"2308.02560","title":"From Discrete Tokens to High-Fidelity Audio Using Multi-Band Diffusion","created":"2023-08-02","cited_by_count":22,"area":null},{"id":"2501.04926","title":"FLowHigh: Towards Efficient and High-Quality Audio Super-Resolution with Single-Step Flow Matching","created":"2025-01-09","cited_by_count":18,"area":"diffusion"},{"id":"2504.07053","title":"TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling","created":"2025-04-09","cited_by_count":16,"area":null},{"id":"2509.17609","title":"Audio Super-Resolution with Latent Bridge Models","created":"2025-09-22","cited_by_count":14,"area":null},{"id":"2306.12957","title":"Siamese SIREN: Audio Compression with Implicit Neural Representations","created":"2023-06-22","cited_by_count":13,"area":null},{"id":"2404.07336","title":"PEAVS: Perceptual Evaluation of Audio-Visual Synchrony Grounded in Viewers' Opinion Scores","created":"2024-04-10","cited_by_count":13,"area":null},{"id":"2310.04567","title":"DPM-TSE: A Diffusion Probabilistic Model for Target Sound Extraction","created":"2023-10-06","cited_by_count":12,"area":"diffusion"},{"id":"2409.08425","title":"SoloAudio: Target Sound Extraction with Language-oriented Audio Diffusion Transformer","created":"2024-09-12","cited_by_count":11,"area":"diffusion"},{"id":"2501.11311","title":"A2SB: Audio-to-Audio Schrodinger Bridges","created":"2025-01-20","cited_by_count":11,"area":null},{"id":"2403.05010","title":"RFWave: Multi-band Rectified Flow for Audio Waveform Reconstruction","created":"2024-03-08","cited_by_count":9,"area":"diffusion"},{"id":"2211.10999","title":"LA-VocE: Low-SNR Audio-visual Speech Enhancement using Neural Vocoders","created":"2022-11-20","cited_by_count":8,"area":null},{"id":"2308.10415","title":"TokenSplit: Using Discrete Speech Representations for Direct, Refined, and Transcript-Conditioned Speech Separation and Recognition","created":"2023-08-21","cited_by_count":8,"area":null},{"id":"2402.16321","title":"Self-Supervised Speech Quality Estimation and Enhancement Using Only Clean Speech","created":"2024-02-26","cited_by_count":7,"area":null},{"id":"2506.00385","title":"MagiCodec: Simple Masked Gaussian-Injected Codec for High-Fidelity Reconstruction and Generation","created":"2025-05-31","cited_by_count":7,"area":null},{"id":"2509.09836","title":"CoDiCodec: Unifying Continuous and Discrete Compressed Representations of Audio","created":"2025-09-11","cited_by_count":7,"area":null},{"id":"2203.15578","title":"Disentangling speech from surroundings with neural embeddings","created":"2022-03-29","cited_by_count":6,"area":null},{"id":"2410.06016","title":"Variable Bitrate Residual Vector Quantization for Audio Coding","created":"2024-10-08","cited_by_count":6,"area":null},{"id":"2505.14470","title":"PAST: Phonetic-Acoustic Speech Tokenizer","created":"2025-05-20","cited_by_count":6,"area":null},{"id":"2601.01373","title":"UltraEval-Audio: A Unified Framework for Comprehensive Evaluation of Audio Foundation Models","created":"2026-01-04","cited_by_count":6,"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":"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":"2503.00733","title":"UniWav: Towards Unified Pre-training for Speech Representation Learning and Generation","created":"2025-03-02","cited_by_count":5,"area":null},{"id":"2407.07825","title":"RT-LA-VocE: Real-Time Low-SNR Audio-Visual Speech Enhancement","created":"2024-07-10","cited_by_count":4,"area":null},{"id":"2501.17578","title":"Music2Latent2: Audio Compression with Summary Embeddings and Autoregressive Decoding","created":"2025-01-29","cited_by_count":4,"area":"diffusion"},{"id":"2505.24576","title":"A Composite Predictive-Generative Approach to Monaural Universal Speech Enhancement","created":"2025-05-30","cited_by_count":4,"area":"diffusion"},{"id":"2508.05207","title":"SpectroStream: A Versatile Neural Codec for General Audio","created":"2025-08-07","cited_by_count":4,"area":null},{"id":"2512.23278","title":"Flow2GAN: Hybrid Flow Matching and GAN with Multi-Resolution Network for Few-step High-Fidelity Audio Generation","created":"2025-12-29","cited_by_count":4,"area":"diffusion"},{"id":"2607.20253","title":"Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering","created":"2026-07-22","cited_by_count":4,"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":"2410.22448","title":"A Closer Look at Neural Codec Resynthesis: Bridging the Gap between Codec and Waveform Generation","created":"2024-10-29","cited_by_count":3,"area":null},{"id":"2502.12759","title":"High-Fidelity Music Vocoder using Neural Audio Codecs","created":"2025-02-18","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":"2506.16231","title":"EDNet: A Versatile Speech Enhancement Framework with Gating Mamba Mechanism and Phase Shift-Invariant Training","created":"2025-06-19","cited_by_count":3,"area":"ssm"},{"id":"2507.21150","title":"WaveVerify: A Novel Audio Watermarking Framework for Media Authentication and Combatting Deepfakes","created":"2025-07-23","cited_by_count":3,"area":"safety"},{"id":"2511.21577","title":"HarmonicAttack: An Adaptive Cross-Domain Audio Watermark Removal","created":"2025-11-26","cited_by_count":3,"area":null},{"id":"2206.13272","title":"Wideband Audio Waveform Evaluation Networks: Efficient, Accurate Estimation of Speech Qualities","created":"2022-06-27","cited_by_count":2,"area":null},{"id":"2407.13435","title":"Enhancing Out-of-Vocabulary Performance of Indian TTS Systems for Practical Applications through Low-Effort Data Strategies","created":"2024-07-18","cited_by_count":2,"area":null},{"id":"2409.15321","title":"WaveTransfer: A Flexible End-to-end Multi-instrument Timbre Transfer with Diffusion","created":"2024-09-06","cited_by_count":2,"area":"diffusion"},{"id":"2509.02244","title":"Spectrogram Patch Codec: A 2D Block-Quantized VQ-VAE and HiFi-GAN for Neural Speech Coding","created":"2025-09-02","cited_by_count":2,"area":null},{"id":"2305.11582","title":"What You Hear Is What You See: Audio Quality Metrics From Image Quality Metrics","created":"2023-05-19","cited_by_count":1,"area":null},{"id":"2404.04405","title":"Dynamic Switch Layers For Unsupervised Learning","created":"2024-04-05","cited_by_count":1,"area":null},{"id":"2410.17834","title":"Non-intrusive Speech Quality Assessment with Diffusion Models Trained on Clean Speech","created":"2024-10-23","cited_by_count":1,"area":"diffusion"},{"id":"2505.13085","title":"Universal Semantic Disentangled Privacy-preserving Speech Representation Learning","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2509.21463","title":"Enhanced Generative Machine Listener","created":"2025-09-25","cited_by_count":1,"area":null},{"id":"2601.12205","title":"Do Neural Codecs Generalize? A Controlled Study Across Unseen Languages and Non-Speech Tasks","created":"2026-01-18","cited_by_count":1,"area":null},{"id":"2601.12950","title":"ImmersiveFlow: Stereo-to-7.1.4 spatial audio generation with flow matching","created":"2026-01-19","cited_by_count":1,"area":"diffusion"},{"id":"2601.19702","title":"SAM Audio Judge: A Unified Multimodal Framework for Perceptual Evaluation of Audio Separation","created":"2026-01-27","cited_by_count":1,"area":null},{"id":"2603.02022","title":"CodecFlow: Efficient Bandwidth Extension via Conditional Flow Matching in Neural Codec Latent Space","created":"2026-03-02","cited_by_count":1,"area":"diffusion"},{"id":"2604.09188","title":"LatentFlowSR: High-Fidelity Audio Super-Resolution via Noise-Robust Latent Flow Matching","created":"2026-04-10","cited_by_count":1,"area":"diffusion"},{"id":"2605.03929","title":"PHALAR: Phasors for Learned Musical Audio Representations","created":"2026-05-05","cited_by_count":1,"area":null},{"id":"2607.05251","title":"Privacy-Preserving Robustness Verification for Neural Networks","created":"2026-07-06","cited_by_count":1,"area":null},{"id":"2112.13366","title":"AIDA: An Active Inference-based Design Agent for Audio Processing Algorithms","created":"2021-12-26","cited_by_count":0,"area":null},{"id":"2506.06732","title":"Neural Spectral Band Generation for Audio Coding","created":"2025-06-07","cited_by_count":0,"area":null},{"id":"2507.13563","title":"Balalaika: Data-Centric, Prosody-Aware Annotation Pipeline for Russian Speech","created":"2025-07-17","cited_by_count":0,"area":null},{"id":"2509.13049","title":"Spiking Vocos: An Energy-Efficient Neural Vocoder","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2509.13670","title":"A High-Quality and Low-Complexity Streamable Neural Speech Codec with Knowledge Distillation","created":"2025-09-17","cited_by_count":0,"area":"distill"},{"id":"2511.05350","title":"Perceptually Aligning Representations of Music via Noise-Augmented Autoencoders","created":"2025-11-07","cited_by_count":0,"area":null},{"id":"2512.04711","title":"Large Speech Model Enabled Semantic Communication","created":"2025-12-04","cited_by_count":0,"area":null},{"id":"2512.21653","title":"Decoder-Side Semantic Conditioning for Low-Bitrate Neural Speech Compression","created":"2025-12-25","cited_by_count":0,"area":null},{"id":"2605.30614","title":"Audio Pirates: Black-box Audio Watermark Removal via Diffusion Priors","created":"2026-05-28","cited_by_count":0,"area":"safety"},{"id":"2606.21365","title":"LambdaMark: Semantic Audio Watermarking for Robustness and Radioactivity","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2607.02799","title":"Conversational Human Audio-visual Talking Dialogue Generation","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.29363","title":"Stable Autoregressive Speech Generation with Low-Frame-Rate High-Dimensional Continuous Tokens","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.03721","title":"On the Geometry of Music Bandwidth Extension in Latent Spaces of Audio Codecs","created":"2026-08-04","cited_by_count":0,"area":"diffusion"},{"id":"2608.30913","title":"Decoupled Latent Flow Matching for Few-Step Joint Vocal-Accompaniment Separation","created":"2026-08-31","cited_by_count":0,"area":"diffusion"},{"id":"2609.24138","title":"P2Flow: Phoneme-aware Progressive Flow Matching for Extreme Speech Super-Resolution","created":"2026-09-21","cited_by_count":0,"area":"diffusion"},{"id":"2609.37116","title":"Multichannel Audio Quality Assessment: Extending Pretrained Perceptual Models to Spatial Audio","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}