{"total":172,"rows":[{"id":"2412.10117","title":"CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models","created":"2024-12-13","cited_by_count":288,"area":"diffusion"},{"id":"2407.05361","title":"Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation","created":"2024-07-07","cited_by_count":204,"area":null},{"id":"2208.05830","title":"Speech Enhancement and Dereverberation with Diffusion-based Generative Models","created":"2022-08-11","cited_by_count":197,"area":"diffusion"},{"id":"2505.17589","title":"CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training","created":"2025-05-23","cited_by_count":150,"area":"diffusion"},{"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":"2210.17327","title":"Diffusion-based Generative Speech Source Separation","created":"2022-10-31","cited_by_count":41,"area":"diffusion"},{"id":"2406.14294","title":"DASB - Discrete Audio and Speech Benchmark","created":"2024-06-20","cited_by_count":32,"area":"mllm"},{"id":"2205.05474","title":"DeepFilterNet2: Towards Real-Time Speech Enhancement on Embedded Devices for Full-Band Audio","created":"2022-05-11","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":"2209.11112","title":"CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancement","created":"2022-09-22","cited_by_count":23,"area":null},{"id":"2501.15417","title":"AnyEnhance: A Unified Generative Model with Prompt-Guidance and Self-Critic for Voice Enhancement","created":"2025-01-26","cited_by_count":23,"area":null},{"id":"2508.06840","title":"FlowSE: Flow Matching-based Speech Enhancement","created":"2025-08-09","cited_by_count":21,"area":"diffusion"},{"id":"2501.15907","title":"Emilia: A Large-Scale, Extensive, Multilingual, and Diverse Dataset for Speech Generation","created":"2025-01-27","cited_by_count":20,"area":null},{"id":"2407.12229","title":"Laugh Now Cry Later: Controlling Time-Varying Emotional States of Flow-Matching-Based Zero-Shot Text-to-Speech","created":"2024-07-17","cited_by_count":19,"area":null},{"id":"2110.05866","title":"MetricGAN-U: Unsupervised speech enhancement/ dereverberation based only on noisy/ reverberated speech","created":"2021-10-12","cited_by_count":18,"area":null},{"id":"2502.04465","title":"FocalCodec: Low-Bitrate Speech Coding via Focal Modulation Networks","created":"2025-02-06","cited_by_count":18,"area":null},{"id":"2511.05516","title":"Ming-UniAudio: Speech LLM for Joint Understanding, Generation and Editing with Unified Representation","created":"2025-10-26","cited_by_count":17,"area":null},{"id":"2507.05727","title":"ContextASR-Bench: A Massive Contextual Speech Recognition Benchmark","created":"2025-07-08","cited_by_count":15,"area":null},{"id":"2507.05911","title":"Differentiable Reward Optimization for LLM based TTS system","created":"2025-07-08","cited_by_count":15,"area":"alignment"},{"id":"2511.07931","title":"SpeechJudge: Towards Human-Level Judgment for Speech Naturalness","created":"2025-11-11","cited_by_count":15,"area":"alignment"},{"id":"2210.17287","title":"Diffiner: A Versatile Diffusion-based Generative Refiner for Speech Enhancement","created":"2022-10-27","cited_by_count":14,"area":"diffusion"},{"id":"2603.18090","title":"MOSS-TTS Technical Report","created":"2026-03-18","cited_by_count":14,"area":null},{"id":"2204.00771","title":"Fast Real-time Personalized Speech Enhancement: End-to-End Enhancement Network (E3Net) and Knowledge Distillation","created":"2022-04-02","cited_by_count":12,"area":"distill"},{"id":"2309.10450","title":"Unsupervised speech enhancement with diffusion-based generative models","created":"2023-09-19","cited_by_count":12,"area":"diffusion"},{"id":"2406.03460","title":"The PESQetarian: On the Relevance of Goodhart's Law for Speech Enhancement","created":"2024-06-05","cited_by_count":12,"area":null},{"id":"2504.02386","title":"VoiceCraft-Dub: Automated Video Dubbing with Neural Codec Language Models","created":"2025-04-03","cited_by_count":11,"area":null},{"id":"2509.02521","title":"FLM-Audio: Natural Monologues Improves Native Full-Duplex Chatbots via Dual Training","created":"2025-09-02","cited_by_count":11,"area":null},{"id":"2211.02542","title":"Self-Supervised Learning for Speech Enhancement through Synthesis","created":"2022-11-04","cited_by_count":10,"area":null},{"id":"2303.07624","title":"I3D: Transformer architectures with input-dependent dynamic depth for speech recognition","created":"2023-03-14","cited_by_count":10,"area":null},{"id":"2304.12023","title":"Multi-channel Speech Separation Using Spatially Selective Deep Non-linear Filters","created":"2023-04-24","cited_by_count":10,"area":null},{"id":"2409.07841","title":"TSELM: Target Speaker Extraction using Discrete Tokens and Language Models","created":"2024-09-12","cited_by_count":10,"area":null},{"id":"2412.08237","title":"TouchTTS: An Embarrassingly Simple TTS Framework that Everyone Can Touch","created":"2024-12-11","cited_by_count":10,"area":null},{"id":"2309.08144","title":"Two-Step Knowledge Distillation for Tiny Speech Enhancement","created":"2023-09-15","cited_by_count":9,"area":"distill"},{"id":"2504.02433","title":"OmniTalker: One-shot Real-time Text-Driven Talking Audio-Video Generation With Multimodal Style Mimicking","created":"2025-04-03","cited_by_count":9,"area":null},{"id":"2505.19314","title":"SoloSpeech: Enhancing Intelligibility and Quality in Target Speech Extraction through a Cascaded Generative Pipeline","created":"2025-05-25","cited_by_count":9,"area":null},{"id":"2509.16195","title":"FocalCodec-Stream: Streaming Low-Bitrate Speech Coding via Causal Distillation","created":"2025-09-19","cited_by_count":9,"area":null},{"id":"2309.13874","title":"DDTSE: Discriminative Diffusion Model for Target Speech Extraction","created":"2023-09-25","cited_by_count":8,"area":"diffusion"},{"id":"2406.13471","title":"Diffusion-based Generative Modeling with Discriminative Guidance for Streamable Speech Enhancement","created":"2024-06-19","cited_by_count":8,"area":"diffusion"},{"id":"2410.21131","title":"Towards Unifying Evaluation of Counterfactual Explanations: Leveraging Large Language Models for Human-Centric Assessments","created":"2024-10-28","cited_by_count":8,"area":null},{"id":"2505.16119","title":"Source Separation by Flow Matching","created":"2025-05-22","cited_by_count":8,"area":"diffusion"},{"id":"2506.19441","title":"TTSDS2: Resources and Benchmark for Evaluating Human-Quality Text to Speech Systems","created":"2025-06-24","cited_by_count":8,"area":null},{"id":"2309.07828","title":"EMOCONV-DIFF: Diffusion-based Speech Emotion Conversion for Non-parallel and In-the-wild Data","created":"2023-09-14","cited_by_count":7,"area":"diffusion"},{"id":"2309.10457","title":"Diffusion-based speech enhancement with a weighted generative-supervised learning loss","created":"2023-09-19","cited_by_count":7,"area":"diffusion"},{"id":"2410.05920","title":"FINALLY: fast and universal speech enhancement with studio-like quality","created":"2024-10-08","cited_by_count":7,"area":null},{"id":"2503.08533","title":"ESPnet-SDS: Unified Toolkit and Demo for Spoken Dialogue Systems","created":"2025-03-11","cited_by_count":7,"area":null},{"id":"2505.21198","title":"Universal Speech Enhancement with Regression and Generative Mamba","created":"2025-05-27","cited_by_count":7,"area":"ssm"},{"id":"2507.09318","title":"ZipVoice-Dialog: Non-Autoregressive Spoken Dialogue Generation with Flow Matching","created":"2025-07-12","cited_by_count":7,"area":"diffusion"},{"id":"2508.17229","title":"Multi-Metric Preference Alignment for Generative Speech Restoration","created":"2025-08-24","cited_by_count":7,"area":"alignment"},{"id":"2301.04320","title":"Rethinking complex-valued deep neural networks for monaural speech enhancement","created":"2023-01-11","cited_by_count":6,"area":null},{"id":"2306.03014","title":"On the Behavior of Intrusive and Non-intrusive Speech Enhancement Metrics in Predictive and Generative Settings","created":"2023-06-05","cited_by_count":6,"area":null},{"id":"2306.03177","title":"DeepVQE: Real Time Deep Voice Quality Enhancement for Joint Acoustic Echo Cancellation, Noise Suppression and Dereverberation","created":"2023-06-05","cited_by_count":6,"area":null},{"id":"2504.09381","title":"DiTSE: High-Fidelity Generative Speech Enhancement via Latent Diffusion Transformers","created":"2025-04-13","cited_by_count":6,"area":"diffusion"},{"id":"2505.14465","title":"FlowTSE: Target Speaker Extraction with Flow Matching","created":"2025-05-20","cited_by_count":6,"area":"diffusion"},{"id":"2507.23511","title":"MECAT: A Multi-Experts Constructed Benchmark for Fine-Grained Audio Understanding Tasks","created":"2025-07-31","cited_by_count":6,"area":null},{"id":"2509.14858","title":"MeanFlowSE: one-step generative speech enhancement via conditional mean flow","created":"2025-09-18","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":"2603.22677","title":"MuQ-Eval: An Open-Source Per-Sample Quality Metric for AI Music Generation Evaluation","created":"2026-03-24","cited_by_count":6,"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":"2307.14464","title":"Single Channel Speech Enhancement Using U-Net Spiking Neural Networks","created":"2023-07-26","cited_by_count":5,"area":null},{"id":"2408.04267","title":"Distil-DCCRN: A Small-footprint DCCRN Leveraging Feature-based Knowledge Distillation in Speech Enhancement","created":"2024-08-08","cited_by_count":5,"area":"distill"},{"id":"2504.07402","title":"LauraTSE: Target Speaker Extraction using Auto-Regressive Decoder-Only Language Models","created":"2025-04-10","cited_by_count":5,"area":null},{"id":"2511.13300","title":"PASE: Leveraging the Phonological Prior of WavLM for Low-Hallucination Generative Speech Enhancement","created":"2025-11-17","cited_by_count":5,"area":null},{"id":"2601.13742","title":"Hearing Between the Lines: Unlocking the Reasoning Power of LLMs for Speech Evaluation","created":"2026-01-20","cited_by_count":5,"area":"lr"},{"id":"2601.16483","title":"FlowSE-GRPO: Training Flow Matching Speech Enhancement via Online Reinforcement Learning","created":"2026-01-23","cited_by_count":5,"area":"diffusion"},{"id":"2606.23190","title":"FlowTTS-GRPO: Online Reinforcement Learning with Multi-Objective Reward Optimization for Flow-Matching Based Text-to-Speech","created":"2026-06-22","cited_by_count":5,"area":"diffusion"},{"id":"2204.03232","title":"Leveraging Real Conversational Data for Multi-Channel Continuous Speech Separation","created":"2022-04-07","cited_by_count":4,"area":null},{"id":"2305.16665","title":"ABC-KD: Attention-Based-Compression Knowledge Distillation for Deep Learning-Based Noise Suppression","created":"2023-05-26","cited_by_count":4,"area":"distill"},{"id":"2410.12399","title":"SF-Speech: Straightened Flow for Zero-Shot Voice Clone","created":"2024-10-16","cited_by_count":4,"area":"diffusion"},{"id":"2505.11200","title":"Audio Turing Test: Benchmarking the Human-likeness of Large Language Model-based Text-to-Speech Systems in Chinese","created":"2025-05-16","cited_by_count":4,"area":null},{"id":"2507.05688","title":"Robust One-step Speech Enhancement via Consistency Distillation","created":"2025-07-08","cited_by_count":4,"area":"diffusion"},{"id":"2508.02013","title":"SpeechRole: A Large-Scale Dataset and Benchmark for Evaluating Speech Role-Playing Agents","created":"2025-08-04","cited_by_count":4,"area":"agents"},{"id":"2508.07558","title":"UniFlow: Unifying Speech Front-End Tasks via Continuous Generative Modeling","created":"2025-08-11","cited_by_count":4,"area":"diffusion"},{"id":"2510.20441","title":"UniSE: A Unified Framework for Decoder-Only Autoregressive LM-Based Speech Enhancement","created":"2025-10-23","cited_by_count":4,"area":null},{"id":"2512.08238","title":"SpeechQualityLLM: LLM-Based Multimodal Assessment of Speech Quality","created":"2025-12-09","cited_by_count":4,"area":null},{"id":"2601.23174","title":"Beyond Fixed Frames: Dynamic Character-Aligned Speech Tokenization","created":"2026-01-30","cited_by_count":4,"area":null},{"id":"2605.05611","title":"X-Voice: Enabling Everyone to Speak 30 Languages via Zero-Shot Cross-Lingual Voice Cloning","created":"2026-05-07","cited_by_count":4,"area":null},{"id":"2608.10716","title":"DuplexWorld: Can voice agents help you get through the day?","created":"2026-08-11","cited_by_count":4,"area":"agents"},{"id":"2305.05857","title":"Diffusion-based Signal Refiner for Speech Enhancement and Separation","created":"2023-05-10","cited_by_count":3,"area":"diffusion"},{"id":"2401.18045","title":"SpeechComposer: Unifying Multiple Speech Tasks with Prompt Composition","created":"2024-01-31","cited_by_count":3,"area":null},{"id":"2409.01217","title":"A multilingual training strategy for low resource Text to Speech","created":"2024-09-02","cited_by_count":3,"area":null},{"id":"2501.05332","title":"AnCoGen: Analysis, Control and Generation of Speech with a Masked Autoencoder","created":"2025-01-09","cited_by_count":3,"area":null},{"id":"2501.10052","title":"Conditional Latent Diffusion-Based Speech Enhancement Via Dual Context Learning","created":"2025-01-17","cited_by_count":3,"area":"diffusion"},{"id":"2501.13375","title":"Bridging The Multi-Modality Gaps of Audio, Visual and Linguistic for Speech Enhancement","created":"2025-01-23","cited_by_count":3,"area":null},{"id":"2502.02603","title":"SEAL: Speech Embedding Alignment Learning for Speech Large Language Model with Retrieval-Augmented Generation","created":"2025-01-26","cited_by_count":3,"area":"mllm"},{"id":"2507.21138","title":"TTS-1 Technical Report","created":"2025-07-22","cited_by_count":3,"area":null},{"id":"2508.08957","title":"QAMRO: Quality-aware Adaptive Margin Ranking Optimization for Human-aligned Assessment of Audio Generation Systems","created":"2025-08-12","cited_by_count":3,"area":null},{"id":"2604.24199","title":"Speech Enhancement Based on Drifting Models","created":"2026-04-27","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":"2211.06508","title":"On the robustness of non-intrusive speech quality model by adversarial examples","created":"2022-11-11","cited_by_count":2,"area":null},{"id":"2302.08088","title":"TAPLoss: A Temporal Acoustic Parameter Loss for Speech Enhancement","created":"2023-02-16","cited_by_count":2,"area":null},{"id":"2302.08095","title":"PAAPLoss: A Phonetic-Aligned Acoustic Parameter Loss for Speech Enhancement","created":"2023-02-16","cited_by_count":2,"area":null},{"id":"2303.08674","title":"Speech Signal Improvement Using Causal Generative Diffusion Models","created":"2023-03-15","cited_by_count":2,"area":"diffusion"},{"id":"2404.16743","title":"Automatic Speech Recognition System-Independent Word Error Rate Estimation","created":"2024-04-25","cited_by_count":2,"area":null},{"id":"2410.21641","title":"RDSinger: Reference-based Diffusion Network for Singing Voice Synthesis","created":"2024-10-29","cited_by_count":2,"area":"diffusion"},{"id":"2502.20040","title":"CleanMel: Mel-Spectrogram Enhancement for Improving Both Speech Quality and ASR","created":"2025-02-27","cited_by_count":2,"area":null},{"id":"2505.13843","title":"A Semantic Information-based Hierarchical Speech Enhancement Method Using Factorized Codec and Diffusion Model","created":"2025-05-20","cited_by_count":2,"area":"diffusion"},{"id":"2505.17426","title":"UniTTS: An end-to-end TTS system without decoupling of acoustic and semantic information","created":"2025-05-23","cited_by_count":2,"area":null},{"id":"2505.18533","title":"TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network","created":"2025-05-24","cited_by_count":2,"area":null},{"id":"2507.00966","title":"MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech Enhancement","created":"2025-07-01","cited_by_count":2,"area":"ssm"},{"id":"2508.01847","title":"Test-Time Training for Speech Enhancement","created":"2025-08-03","cited_by_count":2,"area":null}],"next_cursor":"100"}