{"total":59,"rows":[{"id":"2312.15821","title":"Audiobox: Unified Audio Generation with Natural Language Prompts","created":"2023-12-25","cited_by_count":120,"area":"diffusion"},{"id":"2402.01912","title":"Natural language guidance of high-fidelity text-to-speech with synthetic annotations","created":"2024-02-02","cited_by_count":67,"area":null},{"id":"2505.15670","title":"SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model","created":"2025-05-21","cited_by_count":34,"area":null},{"id":"2502.05236","title":"Koel-TTS: Enhancing LLM based Speech Generation with Preference Alignment and Classifier Free Guidance","created":"2025-02-07","cited_by_count":27,"area":"alignment"},{"id":"2507.05911","title":"Differentiable Reward Optimization for LLM based TTS system","created":"2025-07-08","cited_by_count":15,"area":"alignment"},{"id":"2508.05835","title":"NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference","created":"2025-08-07","cited_by_count":15,"area":null},{"id":"2408.13040","title":"SpeechPrompt: Prompting Speech Language Models for Speech Processing Tasks","created":"2024-08-23","cited_by_count":12,"area":null},{"id":"2409.12117","title":"Low Frame-rate Speech Codec: a Codec Designed for Fast High-quality Speech LLM Training and Inference","created":"2024-09-18","cited_by_count":11,"area":null},{"id":"2506.02863","title":"CapSpeech: Enabling Downstream Applications in Style-Captioned Text-to-Speech","created":"2025-06-03","cited_by_count":11,"area":null},{"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":"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":"2411.12719","title":"Rethinking MUSHRA: Addressing Modern Challenges in Text-to-Speech Evaluation","created":"2024-11-19","cited_by_count":7,"area":null},{"id":"2509.20060","title":"Discrete Diffusion for Generative Modeling of Text-Aligned Speech Tokens","created":"2025-09-24","cited_by_count":7,"area":"diffusion"},{"id":"2309.08030","title":"AV2Wav: Diffusion-Based Re-synthesis from Continuous Self-supervised Features for Audio-Visual Speech Enhancement","created":"2023-09-14","cited_by_count":5,"area":"diffusion"},{"id":"2407.11828","title":"Vibravox: A Dataset of French Speech Captured with Body-conduction Audio Sensors","created":"2024-07-16","cited_by_count":5,"area":null},{"id":"2601.13319","title":"Arab Voices: Mapping Standard and Dialectal Arabic Speech Technology","created":"2026-01-19","cited_by_count":4,"area":null},{"id":"2609.21967","title":"NemotronLabs VoiceChat: An Open Full-duplex Speech-to-Speech Model with Tool Calling Capabilities","created":"2026-09-18","cited_by_count":4,"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":"2507.09750","title":"MB-RIRs: a Synthetic Room Impulse Response Dataset with Frequency-Dependent Absorption Coefficients","created":"2025-07-13","cited_by_count":3,"area":null},{"id":"2607.04941","title":"DuplexChat: Constructing Speaker-Separated Full-Duplex Dialogue Speech at Scale for Spoken Dialogue Language Modeling","created":"2026-07-06","cited_by_count":3,"area":null},{"id":"2608.13831","title":"VoiceChat-TTS: A Low-Latency Continuous Speech Synthesis Model for Interactive Agents","created":"2026-08-13","cited_by_count":3,"area":"agents"},{"id":"2407.04578","title":"Resource-Efficient Speech Quality Prediction through Quantization Aware Training and Binary Activation Maps","created":"2024-07-05","cited_by_count":2,"area":null},{"id":"2408.07234","title":"Direction of Arrival Correction through Speech Quality Feedback","created":"2024-08-13","cited_by_count":2,"area":null},{"id":"2504.00750","title":"$C^2$AV-TSE: Context and Confidence-aware Audio Visual Target Speaker Extraction","created":"2025-04-01","cited_by_count":2,"area":null},{"id":"2508.02210","title":"WhiSQA: Non-Intrusive Speech Quality Prediction Using Whisper Encoder Features","created":"2025-08-04","cited_by_count":2,"area":null},{"id":"2508.16198","title":"OMHBench: Benchmarking Balanced and Grounded Omni-Modal Multi-Hop Reasoning","created":"2025-08-22","cited_by_count":2,"area":"lr"},{"id":"2511.00256","title":"NaturalVoices: A Large-Scale, Spontaneous and Emotional Podcast Dataset for Voice Conversion","created":"2025-10-31","cited_by_count":2,"area":null},{"id":"2602.10666","title":"From Diet to Free Lunch: Estimating Auxiliary Signal Properties using Dynamic Pruning Masks in Speech Enhancement Networks","created":"2026-02-11","cited_by_count":2,"area":null},{"id":"2609.13150","title":"The Limits of Reference-Free Speech Quality Metrics as Evaluators and Rewards on Modern Text-to-Speech","created":"2026-07-02","cited_by_count":2,"area":"alignment"},{"id":"2409.13499","title":"Fast Streaming Transducer ASR Prototyping via Knowledge Distillation with Whisper","created":"2024-09-20","cited_by_count":1,"area":"distill"},{"id":"2505.18972","title":"Revival with Voice: Multi-modal Controllable Text-to-Speech Synthesis","created":"2025-05-25","cited_by_count":1,"area":null},{"id":"2505.19534","title":"Training-Free Multi-Step Audio Source Separation","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2509.21718","title":"Align2Speak: Improving TTS for Low Resource Languages via ASR-Guided Online Preference Optimization","created":"2025-09-26","cited_by_count":1,"area":"alignment"},{"id":"2601.19399","title":"Residual Tokens Enhance Masked Autoencoders for Speech Modeling","created":"2026-01-27","cited_by_count":1,"area":null},{"id":"2603.10175","title":"Calibration-Reasoning Framework for Descriptive Speech Quality Assessment","created":"2026-03-10","cited_by_count":1,"area":"lr"},{"id":"2603.23938","title":"OmniACBench: A Benchmark for Evaluating Context-Grounded Acoustic Control in Omni-Modal Models","created":"2026-03-25","cited_by_count":1,"area":null},{"id":"2608.27848","title":"Is Prosody Lost in Translation? Fine-Grained Cross-Lingual Prosody Similarity Across Languages","created":"2026-08-28","cited_by_count":1,"area":null},{"id":"2402.01413","title":"Objective and subjective evaluation of speech enhancement methods in the UDASE task of the 7th CHiME challenge","created":"2024-02-02","cited_by_count":0,"area":null},{"id":"2406.10223","title":"Diffusion Synthesizer for Efficient Multilingual Speech to Speech Translation","created":"2024-06-14","cited_by_count":0,"area":null},{"id":"2410.22805","title":"Run-Time Adaptation of Neural Beamforming for Robust Speech Dereverberation and Denoising","created":"2024-10-30","cited_by_count":0,"area":null},{"id":"2501.19258","title":"VisualSpeech: Enhancing Prosody Modeling in TTS Using Video","created":"2025-01-31","cited_by_count":0,"area":null},{"id":"2507.02755","title":"Multi-agent Auditory Scene Analysis","created":"2025-07-03","cited_by_count":0,"area":null},{"id":"2507.10827","title":"Supporting SENCOTEN Language Documentation Efforts with Automatic Speech Recognition","created":"2025-07-14","cited_by_count":0,"area":null},{"id":"2508.18006","title":"Unseen Speaker and Language Adaptation for Lightweight Text-To-Speech with Adapters","created":"2025-08-25","cited_by_count":0,"area":null},{"id":"2509.05863","title":"LatinX: Aligning a Multilingual TTS Model with Direct Preference Optimization","created":"2025-09-06","cited_by_count":0,"area":"alignment"},{"id":"2509.24457","title":"Assessing speech quality metrics for evaluation of neural audio codecs under clean speech conditions","created":"2025-09-29","cited_by_count":0,"area":null},{"id":"2603.10904","title":"When Fine-Tuning Fails and when it Generalises: Role of Data Diversity and Mixed Training in LLM-based TTS","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2603.15326","title":"Tagarela - A Portuguese speech dataset from podcasts","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2604.16108","title":"Polyglot: Multilingual Style Preserving Speech-Driven Facial Animation","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2605.30469","title":"3DAE: Binaural Quality Assessment for Audio Novel View Synthesis with Spatial Maps and Benchmark","created":"2026-05-28","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":"2606.04418","title":"CleanCodec: Efficient and Robust Speech Tokenization via Perceptually Guided Encoding","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.19325","title":"Reference-Driven Multi-Speaker Audio Scene Generation from In-the-Wild Priors","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2606.31729","title":"Is Natural Always Appropriate? Investigating Naturalness and Appropriateness Across Different Domains for TTS Evaluation","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2609.30483","title":"AcoustiClaim: A Numeric Claim Benchmark with Instrument Ground Truth","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.30625","title":"Audio LLMs Know When They Can't Hear You","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.36737","title":"Reconstructing the Vocal Tract with Differentiable Acoustic Simulation","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.00538","title":"Multi-agent Auditory Scene Analysis: Improved Localization Speed and Robustness by Multi-beamformed Speech Quality Feedback","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.06057","title":"A Comprehensive Objective Evaluation of Modern Text-to-Speech for Turkish Using Speech Quality Assessment Models","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}