{"total":157,"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":"2306.05284","title":"Simple and Controllable Music Generation","created":"2023-06-08","cited_by_count":488,"area":null},{"id":"2305.13516","title":"Scaling Speech Technology to 1,000+ Languages","created":"2023-05-22","cited_by_count":411,"area":null},{"id":"2112.02418","title":"YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone","created":"2021-12-04","cited_by_count":278,"area":null},{"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":"2406.04904","title":"XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model","created":"2024-06-07","cited_by_count":179,"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":"2211.12171","title":"PromptTTS: Controllable Text-to-Speech with Text Descriptions","created":"2022-11-22","cited_by_count":110,"area":null},{"id":"2402.08093","title":"BASE TTS: Lessons from building a billion-parameter Text-to-Speech model on 100K hours of data","created":"2024-02-12","cited_by_count":75,"area":null},{"id":"2301.05339","title":"A Comprehensive Review of Data-Driven Co-Speech Gesture Generation","created":"2023-01-13","cited_by_count":66,"area":null},{"id":"2406.06185","title":"EARS: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberation","created":"2024-06-10","cited_by_count":64,"area":null},{"id":"2306.03509","title":"Mega-TTS: Zero-Shot Text-to-Speech at Scale with Intrinsic Inductive Bias","created":"2023-06-06","cited_by_count":51,"area":null},{"id":"2309.02285","title":"PromptTTS 2: Describing and Generating Voices with Text Prompt","created":"2023-09-05","cited_by_count":48,"area":null},{"id":"2204.00436","title":"AdaSpeech 4: Adaptive Text to Speech in Zero-Shot Scenarios","created":"2022-04-01","cited_by_count":41,"area":null},{"id":"2303.11607","title":"Transformers in Speech Processing: A Survey","created":"2023-03-21","cited_by_count":39,"area":null},{"id":"2406.07855","title":"VALL-E R: Robust and Efficient Zero-Shot Text-to-Speech Synthesis via Monotonic Alignment","created":"2024-06-12","cited_by_count":38,"area":null},{"id":"2205.15439","title":"StyleTTS: A Style-Based Generative Model for Natural and Diverse Text-to-Speech Synthesis","created":"2022-05-30","cited_by_count":33,"area":null},{"id":"2210.03538","title":"An Overview of Affective Speech Synthesis and Conversion in the Deep Learning Era","created":"2022-10-06","cited_by_count":33,"area":null},{"id":"2111.07402","title":"Textless Speech Emotion Conversion using Discrete and Decomposed Representations","created":"2021-11-14","cited_by_count":29,"area":null},{"id":"2208.05890","title":"Speech Synthesis with Mixed Emotions","created":"2022-08-11","cited_by_count":28,"area":null},{"id":"2211.09536","title":"Towards Building Text-To-Speech Systems for the Next Billion Users","created":"2022-11-17","cited_by_count":27,"area":null},{"id":"2309.08140","title":"PromptTTS++: Controlling Speaker Identity in Prompt-Based Text-to-Speech Using Natural Language Descriptions","created":"2023-09-15","cited_by_count":25,"area":null},{"id":"2109.06912","title":"fairseq S^2: A Scalable and Integrable Speech Synthesis Toolkit","created":"2021-09-14","cited_by_count":24,"area":null},{"id":"2301.08810","title":"Phoneme-Level BERT for Enhanced Prosody of Text-to-Speech with Grapheme Predictions","created":"2023-01-20","cited_by_count":23,"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":"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":"2404.13066","title":"Leveraging Large Language Model as Simulated Patients for Clinical Education","created":"2024-04-13","cited_by_count":21,"area":null},{"id":"2409.09272","title":"SafeEar: Content Privacy-Preserving Audio Deepfake Detection","created":"2024-09-14","cited_by_count":21,"area":null},{"id":"2207.09542","title":"Controllable Data Generation by Deep Learning: A Review","created":"2022-07-19","cited_by_count":20,"area":null},{"id":"2211.16934","title":"VideoDubber: Machine Translation with Speech-Aware Length Control for Video Dubbing","created":"2022-11-30","cited_by_count":20,"area":null},{"id":"2309.08836","title":"Bias and Fairness in Chatbots: An Overview","created":"2023-09-16","cited_by_count":20,"area":null},{"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":"2110.12612","title":"DelightfulTTS: The Microsoft Speech Synthesis System for Blizzard Challenge 2021","created":"2021-10-25","cited_by_count":19,"area":null},{"id":"2203.16930","title":"WavThruVec: Latent speech representation as intermediate features for neural speech synthesis","created":"2022-03-31","cited_by_count":17,"area":null},{"id":"2306.11503","title":"The Age of Synthetic Realities: Challenges and Opportunities","created":"2023-06-09","cited_by_count":15,"area":null},{"id":"2404.06690","title":"CoVoMix: Advancing Zero-Shot Speech Generation for Human-like Multi-talker Conversations","created":"2024-04-10","cited_by_count":15,"area":null},{"id":"2508.04195","title":"NVSpeech: An Integrated and Scalable Pipeline for Human-Like Speech Modeling with Paralinguistic Vocalizations","created":"2025-08-06","cited_by_count":15,"area":null},{"id":"2203.17190","title":"Mixed-Phoneme BERT: Improving BERT with Mixed Phoneme and Sup-Phoneme Representations for Text to Speech","created":"2022-03-31","cited_by_count":13,"area":null},{"id":"2306.09417","title":"Diff-TTSG: Denoising probabilistic integrated speech and gesture synthesis","created":"2023-06-15","cited_by_count":13,"area":null},{"id":"2107.02621","title":"Energy Consumption of Deep Generative Audio Models","created":"2021-07-06","cited_by_count":12,"area":null},{"id":"2202.06034","title":"Deep Performer: Score-to-Audio Music Performance Synthesis","created":"2022-02-12","cited_by_count":12,"area":null},{"id":"2204.02524","title":"Simple and Effective Unsupervised Speech Synthesis","created":"2022-04-06","cited_by_count":12,"area":null},{"id":"2107.02530","title":"AdaSpeech 3: Adaptive Text to Speech for Spontaneous Style","created":"2021-07-06","cited_by_count":11,"area":null},{"id":"2308.14328","title":"Reinforcement Learning for Generative AI: A Survey","created":"2023-08-28","cited_by_count":11,"area":null},{"id":"2201.05771","title":"KazakhTTS2: Extending the Open-Source Kazakh TTS Corpus With More Data, Speakers, and Topics","created":"2022-01-15","cited_by_count":10,"area":null},{"id":"2204.02804","title":"Federated Self-supervised Speech Representations: Are We There Yet?","created":"2022-04-06","cited_by_count":10,"area":null},{"id":"2206.06637","title":"RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks","created":"2022-06-14","cited_by_count":10,"area":null},{"id":"2202.05083","title":"Cross-speaker style transfer for text-to-speech using data augmentation","created":"2022-02-10","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":"2306.08374","title":"SpeechGLUE: How Well Can Self-Supervised Speech Models Capture Linguistic Knowledge?","created":"2023-06-14","cited_by_count":9,"area":null},{"id":"2509.09716","title":"VStyle: A Benchmark for Voice Style Adaptation with Spoken Instructions","created":"2025-09-09","cited_by_count":9,"area":null},{"id":"2108.13320","title":"Neural HMMs are all you need (for high-quality attention-free TTS)","created":"2021-08-30","cited_by_count":8,"area":null},{"id":"2207.03800","title":"FastLTS: Non-Autoregressive End-to-End Unconstrained Lip-to-Speech Synthesis","created":"2022-07-08","cited_by_count":8,"area":null},{"id":"2301.08846","title":"Regeneration Learning: A Learning Paradigm for Data Generation","created":"2023-01-21","cited_by_count":8,"area":null},{"id":"2406.08644","title":"Toward Fully-End-to-End Listened Speech Decoding from EEG Signals","created":"2024-06-12","cited_by_count":8,"area":null},{"id":"2407.13509","title":"Spontaneous Style Text-to-Speech Synthesis with Controllable Spontaneous Behaviors Based on Language Models","created":"2024-07-18","cited_by_count":8,"area":null},{"id":"2407.18517","title":"SLIM: Style-Linguistics Mismatch Model for Generalized Audio Deepfake Detection","created":"2024-07-26","cited_by_count":8,"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":"2210.15964","title":"Period VITS: Variational Inference with Explicit Pitch Modeling for End-to-end Emotional Speech Synthesis","created":"2022-10-28","cited_by_count":6,"area":null},{"id":"2404.18094","title":"USAT: A Universal Speaker-Adaptive Text-to-Speech Approach","created":"2024-04-28","cited_by_count":6,"area":null},{"id":"2406.08820","title":"DisfluencySpeech -- Single-Speaker Conversational Speech Dataset with Paralanguage","created":"2024-06-13","cited_by_count":6,"area":null},{"id":"2508.07944","title":"SCDF: A Speaker Characteristics DeepFake Speech Dataset for Bias Analysis","created":"2025-08-11","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":"2308.13007","title":"Generalizable Zero-Shot Speaker Adaptive Speech Synthesis with Disentangled Representations","created":"2023-08-24","cited_by_count":5,"area":null},{"id":"2404.18398","title":"UMETTS: A Unified Framework for Emotional Text-to-Speech Synthesis with Multimodal Prompts","created":"2024-04-29","cited_by_count":5,"area":null},{"id":"2404.19622","title":"Fake it to make it: Using synthetic data to remedy the data shortage in joint multimodal speech-and-gesture synthesis","created":"2024-04-30","cited_by_count":5,"area":null},{"id":"2406.00146","title":"A Survey of Deep Learning Audio Generation Methods","created":"2024-05-31","cited_by_count":5,"area":null},{"id":"2406.19135","title":"DEX-TTS: Diffusion-based EXpressive Text-to-Speech with Style Modeling on Time Variability","created":"2024-06-27","cited_by_count":5,"area":null},{"id":"2408.01808","title":"ALIF: Low-Cost Adversarial Audio Attacks on Black-Box Speech Platforms using Linguistic Features","created":"2024-08-03","cited_by_count":5,"area":null},{"id":"2503.08954","title":"An Exhaustive Evaluation of TTS- and VC-based Data Augmentation for ASR","created":"2025-03-11","cited_by_count":5,"area":null},{"id":"2503.23536","title":"A Survey on Unlearnable Data","created":"2025-03-30","cited_by_count":5,"area":null},{"id":"2303.01261","title":"ParrotTTS: Text-to-Speech synthesis by exploiting self-supervised representations","created":"2023-03-01","cited_by_count":4,"area":null},{"id":"2305.12107","title":"EE-TTS: Emphatic Expressive TTS with Linguistic Information","created":"2023-05-20","cited_by_count":4,"area":null},{"id":"2306.17005","title":"High-Quality Automatic Voice Over with Accurate Alignment: Supervision through Self-Supervised Discrete Speech Units","created":"2023-06-29","cited_by_count":4,"area":null},{"id":"2307.05132","title":"On the Use of Self-Supervised Speech Representations in Spontaneous Speech Synthesis","created":"2023-07-11","cited_by_count":4,"area":null},{"id":"2308.16593","title":"Towards Spontaneous Style Modeling with Semi-supervised Pre-training for Conversational Text-to-Speech Synthesis","created":"2023-08-31","cited_by_count":4,"area":null},{"id":"2406.05699","title":"An Investigation of Noise Robustness for Flow-Matching-Based Zero-Shot TTS","created":"2024-06-09","cited_by_count":4,"area":null},{"id":"2408.14713","title":"StyleSpeech: Parameter-efficient Fine Tuning for Pre-trained Controllable Text-to-Speech","created":"2024-08-27","cited_by_count":4,"area":null},{"id":"2410.00441","title":"ReXplain: Translating Radiology into Patient-Friendly Video Reports","created":"2024-10-01","cited_by_count":4,"area":null},{"id":"2505.00579","title":"Voice Cloning: Comprehensive Survey","created":"2025-05-01","cited_by_count":4,"area":null},{"id":"2508.04179","title":"The State Of TTS: A Case Study with Human Fooling Rates","created":"2025-08-06","cited_by_count":4,"area":null},{"id":"2110.01147","title":"On the Interplay Between Sparsity, Naturalness, Intelligibility, and Prosody in Speech Synthesis","created":"2021-10-04","cited_by_count":3,"area":null},{"id":"2110.04005","title":"KaraSinger: Score-Free Singing Voice Synthesis with VQ-VAE using Mel-spectrograms","created":"2021-10-08","cited_by_count":3,"area":null},{"id":"2206.12563","title":"Generating Diverse Vocal Bursts with StyleGAN2 and MEL-Spectrograms","created":"2022-06-25","cited_by_count":3,"area":null},{"id":"2303.02719","title":"A Comparative Study of Self-Supervised Speech Representations in Read and Spontaneous TTS","created":"2023-03-05","cited_by_count":3,"area":null},{"id":"2305.19396","title":"Resource-Efficient Fine-Tuning Strategies for Automatic MOS Prediction in Text-to-Speech for Low-Resource Languages","created":"2023-05-30","cited_by_count":3,"area":null},{"id":"2312.06613","title":"Neural Text to Articulate Talk: Deep Text to Audiovisual Speech Synthesis achieving both Auditory and Photo-realism","created":"2023-12-11","cited_by_count":3,"area":null},{"id":"2404.19363","title":"Expressivity and Speech Synthesis","created":"2024-04-30","cited_by_count":3,"area":null},{"id":"2406.14176","title":"A Multi-Stream Fusion Approach with One-Class Learning for Audio-Visual Deepfake Detection","created":"2024-06-20","cited_by_count":3,"area":null},{"id":"2407.21476","title":"On the Problem of Text-To-Speech Model Selection for Synthetic Data Generation in Automatic Speech Recognition","created":"2024-07-31","cited_by_count":3,"area":null},{"id":"2408.10771","title":"kNN Retrieval for Simple and Effective Zero-Shot Multi-speaker Text-to-Speech","created":"2024-08-20","cited_by_count":3,"area":null},{"id":"2508.02038","title":"Marco-Voice Technical Report","created":"2025-08-04","cited_by_count":3,"area":null},{"id":"2509.20378","title":"Beyond Global Emotion: Fine-Grained Emotional Speech Synthesis with Dynamic Word-Level Modulation","created":"2025-09-20","cited_by_count":3,"area":null},{"id":"2112.12006","title":"Catch Me If You GAN: Using Artificial Intelligence for Fake Log Generation","created":"2021-12-22","cited_by_count":2,"area":null},{"id":"2203.09825","title":"AdaVocoder: Adaptive Vocoder for Custom Voice","created":"2022-03-18","cited_by_count":2,"area":null},{"id":"2203.12201","title":"Towards Expressive Speaking Style Modelling with Hierarchical Context Information for Mandarin Speech Synthesis","created":"2022-03-23","cited_by_count":2,"area":null},{"id":"2209.10848","title":"MnTTS: An Open-Source Mongolian Text-to-Speech Synthesis Dataset and Accompanied Baseline","created":"2022-09-22","cited_by_count":2,"area":null},{"id":"2306.12040","title":"Strategies in Transfer Learning for Low-Resource Speech Synthesis: Phone Mapping, Features Input, and Source Language Selection","created":"2023-06-21","cited_by_count":2,"area":null},{"id":"2309.14329","title":"Innovative Digital Storytelling with AIGC: Exploration and Discussion of Recent Advances","created":"2023-09-25","cited_by_count":2,"area":null},{"id":"2312.01107","title":"Rapid Speaker Adaptation in Low Resource Text to Speech Systems using Synthetic Data and Transfer learning","created":"2023-12-02","cited_by_count":2,"area":null}],"next_cursor":"100"}