{"total":61,"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":"2402.01831","title":"Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities","created":"2024-02-02","cited_by_count":186,"area":null},{"id":"2503.03983","title":"Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities","created":"2025-03-06","cited_by_count":133,"area":"lr"},{"id":"2402.05755","title":"Spirit LM: Interleaved Spoken and Written Language Model","created":"2024-02-08","cited_by_count":126,"area":"mllm"},{"id":"2109.03264","title":"Text-Free Prosody-Aware Generative Spoken Language Modeling","created":"2021-09-07","cited_by_count":119,"area":null},{"id":"2105.14762","title":"Emotional Voice Conversion: Theory, Databases and ESD","created":"2021-05-31","cited_by_count":115,"area":null},{"id":"2503.01710","title":"Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens","created":"2025-03-03","cited_by_count":113,"area":null},{"id":"2308.05725","title":"EXPRESSO: A Benchmark and Analysis of Discrete Expressive Speech Resynthesis","created":"2023-08-10","cited_by_count":98,"area":null},{"id":"2310.04673","title":"LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT","created":"2023-10-07","cited_by_count":78,"area":null},{"id":"2406.13340","title":"SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words","created":"2024-06-19","cited_by_count":68,"area":null},{"id":"2507.02768","title":"DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment","created":"2025-07-03","cited_by_count":50,"area":"synth"},{"id":"2406.07162","title":"EmoBox: Multilingual Multi-corpus Speech Emotion Recognition Toolkit and Benchmark","created":"2024-06-11","cited_by_count":40,"area":null},{"id":"2412.04448","title":"MEMO: Memory-Guided Diffusion for Expressive Talking Video Generation","created":"2024-12-05","cited_by_count":38,"area":"diffusion"},{"id":"2111.07402","title":"Textless Speech Emotion Conversion using Discrete and Decomposed Representations","created":"2021-11-14","cited_by_count":29,"area":null},{"id":"2403.10779","title":"LLM-based Conversational AI Therapist for Daily Functioning Screening and Psychotherapeutic Intervention via Everyday Smart Devices","created":"2024-03-16","cited_by_count":21,"area":null},{"id":"2511.12609","title":"Uni-MoE-2.0-Omni: Scaling Language-Centric Omnimodal Large Model with Advanced MoE, Training and Data","created":"2025-11-16","cited_by_count":21,"area":"moe"},{"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":"2407.02751","title":"Emotion and Intent Joint Understanding in Multimodal Conversation: A Benchmarking Dataset","created":"2024-07-03","cited_by_count":15,"area":null},{"id":"2306.12991","title":"Speech Emotion Diarization: Which Emotion Appears When?","created":"2023-06-22","cited_by_count":13,"area":null},{"id":"2401.08166","title":"ED-TTS: Multi-Scale Emotion Modeling using Cross-Domain Emotion Diarization for Emotional Speech Synthesis","created":"2024-01-16","cited_by_count":9,"area":"diffusion"},{"id":"2305.13137","title":"EMNS /Imz/ Corpus: An emotive single-speaker dataset for narrative storytelling in games, television and graphic novels","created":"2023-05-22","cited_by_count":7,"area":null},{"id":"2404.07616","title":"Audio Dialogues: Dialogues dataset for audio and music understanding","created":"2024-04-11","cited_by_count":7,"area":null},{"id":"2412.07116","title":"A Review of Human Emotion Synthesis Based on Generative Technology","created":"2024-12-10","cited_by_count":7,"area":null},{"id":"2605.27772","title":"Do Audio LLMs Listen or Read? Analyzing and Mitigating Paralinguistic Failures with VoxParadox","created":"2026-05-26","cited_by_count":7,"area":null},{"id":"2106.08519","title":"Global Rhythm Style Transfer Without Text Transcriptions","created":"2021-06-16","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":"2303.01508","title":"Fine-grained Emotional Control of Text-To-Speech: Learning To Rank Inter- And Intra-Class Emotion Intensities","created":"2023-03-02","cited_by_count":5,"area":null},{"id":"2502.18186","title":"Steering Language Model to Stable Speech Emotion Recognition via Contextual Perception and Chain of Thought","created":"2025-02-25","cited_by_count":5,"area":"lr"},{"id":"2306.05709","title":"Learning Emotional Representations from Imbalanced Speech Data for Speech Emotion Recognition and Emotional Text-to-Speech","created":"2023-06-09","cited_by_count":4,"area":null},{"id":"2504.14183","title":"The First VoicePrivacy Attacker Challenge","created":"2025-04-19","cited_by_count":4,"area":null},{"id":"2509.22220","title":"StableToken: A Noise-Robust Semantic Speech Tokenizer for Resilient SpeechLLMs","created":"2025-09-26","cited_by_count":4,"area":null},{"id":"2601.23161","title":"DIFFA-2: A Practical Diffusion Large Language Model for General Audio Understanding","created":"2026-01-30","cited_by_count":3,"area":null},{"id":"2110.04241","title":"Cognitive Coding of Speech","created":"2021-10-08","cited_by_count":2,"area":null},{"id":"2310.00283","title":"Active Learning Based Fine-Tuning Framework for Speech Emotion Recognition","created":"2023-09-30","cited_by_count":2,"area":null},{"id":"2310.11830","title":"CLARA: Multilingual Contrastive Learning for Audio Representation Acquisition","created":"2023-10-18","cited_by_count":2,"area":null},{"id":"2311.08607","title":"Towards Generalizable SER: Soft Labeling and Data Augmentation for Modeling Temporal Emotion Shifts in Large-Scale Multilingual Speech","created":"2023-11-15","cited_by_count":2,"area":null},{"id":"2404.10419","title":"MAD Speech: Measures of Acoustic Diversity of Speech","created":"2024-04-16","cited_by_count":2,"area":null},{"id":"2505.10599","title":"UDDETTS: Unifying Discrete and Dimensional Emotions for Controllable Emotional Text-to-Speech","created":"2025-05-15","cited_by_count":2,"area":null},{"id":"2601.10513","title":"AEQ-Bench: Measuring Empathy of Omni-Modal Large Models","created":"2026-01-15","cited_by_count":2,"area":null},{"id":"2603.08936","title":"VoxEmo: Benchmarking Speech Emotion Recognition with Speech LLMs","created":"2026-03-09","cited_by_count":2,"area":null},{"id":"2211.14548","title":"Contextual Expressive Text-to-Speech","created":"2022-11-26","cited_by_count":1,"area":null},{"id":"2310.11541","title":"MUST&P-SRL: Multi-lingual and Unified Syllabification in Text and Phonetic Domains for Speech Representation Learning","created":"2023-10-17","cited_by_count":1,"area":null},{"id":"2404.06714","title":"Llama-VITS: Enhancing TTS Synthesis with Semantic Awareness","created":"2024-04-10","cited_by_count":1,"area":null},{"id":"2406.09933","title":"What Does it Take to Generalize SER Model Across Datasets? A Comprehensive Benchmark","created":"2024-06-14","cited_by_count":1,"area":null},{"id":"2410.07428","title":"The First VoicePrivacy Attacker Challenge Evaluation Plan","created":"2024-10-09","cited_by_count":1,"area":null},{"id":"2501.03711","title":"Unsupervised Speech Segmentation: A General Approach Using Speech Language Models","created":"2025-01-07","cited_by_count":1,"area":null},{"id":"2501.04904","title":"JELLY: Joint Emotion Recognition and Context Reasoning with LLMs for Conversational Speech Synthesis","created":"2025-01-09","cited_by_count":1,"area":"lr"},{"id":"2506.14767","title":"A Variational Framework for Improving Naturalness in Generative Spoken Language Models","created":"2025-06-17","cited_by_count":1,"area":null},{"id":"2601.19399","title":"Residual Tokens Enhance Masked Autoencoders for Speech Modeling","created":"2026-01-27","cited_by_count":1,"area":null},{"id":"2405.00307","title":"Active Learning with Task Adaptation Pre-training for Speech Emotion Recognition","created":"2024-05-01","cited_by_count":0,"area":null},{"id":"2410.19199","title":"Making Social Platforms Accessible: Emotion-Aware Speech Generation with Integrated Text Analysis","created":"2024-10-24","cited_by_count":0,"area":null},{"id":"2412.00319","title":"Improving speaker verification robustness with synthetic emotional utterances","created":"2024-11-30","cited_by_count":0,"area":null},{"id":"2502.16584","title":"Audio-FLAN: An Instruction-Following Dataset for Unified Audio Understanding and Generation of Speech, Music, and Sound","created":"2025-02-23","cited_by_count":0,"area":null},{"id":"2509.10452","title":"WhisTLE: Deeply Supervised, Text-Only Domain Adaptation for Small Pretrained Speech Recognition Transformers","created":"2025-09-12","cited_by_count":0,"area":null},{"id":"2602.20113","title":"StyleStream: Real-Time Zero-Shot Voice Style Conversion","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2603.11683","title":"Causal Prosody Mediation for Text-to-Speech:Counterfactual Training of Duration, Pitch, and Energy in FastSpeech2","created":"2026-03-12","cited_by_count":0,"area":null},{"id":"2604.13335","title":"SEDTalker: Emotion-Aware 3D Facial Animation Using Frame-Level Speech Emotion Diarization","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2607.02214","title":"Unlocking Speech-Text Compositional Powers: Instruction-Following Speech Language Models without Instruction Tuning","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2608.20387","title":"Poly-InstructTTS: Learning In-the-Wild Expressive Speech Synthesis from Open-Ended Instructions","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2608.22908","title":"Do Spoken Language Models Hear Speech as They Read Text? Bridging Structural Gaps Between Speech and Text","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.32804","title":"Finding Emotions Where They Belong: Rethinking Audio Emotion Recognition through Masked Temporal Affective Grounding","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}