{"total":242,"rows":[{"id":"2405.17428","title":"NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models","created":"2024-05-27","cited_by_count":472,"area":null},{"id":"2306.15687","title":"Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale","created":"2023-06-23","cited_by_count":379,"area":null},{"id":"2106.15561","title":"A Survey on Neural Speech Synthesis","created":"2021-06-29","cited_by_count":184,"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":"2202.08433","title":"ADD 2022: the First Audio Deep Synthesis Detection Challenge","created":"2022-02-17","cited_by_count":96,"area":null},{"id":"2106.03153","title":"Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation","created":"2021-06-06","cited_by_count":93,"area":null},{"id":"2209.07556","title":"ZeroEGGS: Zero-shot Example-based Gesture Generation from Speech","created":"2022-09-15","cited_by_count":84,"area":null},{"id":"2210.15418","title":"FreeVC: Towards High-Quality Text-Free One-Shot Voice Conversion","created":"2022-10-27","cited_by_count":80,"area":null},{"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":"2301.05339","title":"A Comprehensive Review of Data-Driven Co-Speech Gesture Generation","created":"2023-01-13","cited_by_count":66,"area":null},{"id":"2103.15060","title":"PnG BERT: Augmented BERT on Phonemes and Graphemes for Neural TTS","created":"2021-03-28","cited_by_count":52,"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":"2104.03617","title":"Half-Truth: A Partially Fake Audio Detection Dataset","created":"2021-04-08","cited_by_count":44,"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":"2404.02677","title":"The VoicePrivacy 2024 Challenge Evaluation Plan","created":"2024-04-03","cited_by_count":41,"area":null},{"id":"2203.09690","title":"A$^3$T: Alignment-Aware Acoustic and Text Pretraining for Speech Synthesis and Editing","created":"2022-03-18","cited_by_count":40,"area":null},{"id":"2103.04088","title":"Investigating on Incorporating Pretrained and Learnable Speaker Representations for Multi-Speaker Multi-Style Text-to-Speech","created":"2021-03-06","cited_by_count":37,"area":null},{"id":"2201.03967","title":"Emotion Intensity and its Control for Emotional Voice Conversion","created":"2022-01-10","cited_by_count":35,"area":null},{"id":"2311.12454","title":"HierSpeech++: Bridging the Gap between Semantic and Acoustic Representation of Speech by Hierarchical Variational Inference for Zero-shot Speech Synthesis","created":"2023-11-21","cited_by_count":35,"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":"2208.05890","title":"Speech Synthesis with Mixed Emotions","created":"2022-08-11","cited_by_count":28,"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":"2110.11479","title":"Synt++: Utilizing Imperfect Synthetic Data to Improve Speech Recognition","created":"2021-10-21","cited_by_count":24,"area":null},{"id":"2111.12890","title":"V2C: Visual Voice Cloning","created":"2021-11-25","cited_by_count":24,"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":"2110.07840","title":"ESPnet2-TTS: Extending the Edge of TTS Research","created":"2021-10-15","cited_by_count":22,"area":null},{"id":"2202.07816","title":"ProsoSpeech: Enhancing Prosody With Quantized Vector Pre-training in Text-to-Speech","created":"2022-02-16","cited_by_count":22,"area":null},{"id":"2302.04215","title":"A Vector Quantized Approach for Text to Speech Synthesis on Real-World Spontaneous Speech","created":"2023-02-08","cited_by_count":22,"area":null},{"id":"2205.07211","title":"GenerSpeech: Towards Style Transfer for Generalizable Out-Of-Domain Text-to-Speech","created":"2022-05-15","cited_by_count":21,"area":null},{"id":"2104.01408","title":"Reinforcement Learning for Emotional Text-to-Speech Synthesis with Improved Emotion Discriminability","created":"2021-04-03","cited_by_count":19,"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":"2411.02625","title":"EmoSphere++: Emotion-Controllable Zero-Shot Text-to-Speech via Emotion-Adaptive Spherical Vector","created":"2024-11-04","cited_by_count":19,"area":null},{"id":"2103.09474","title":"STYLER: Style Factor Modeling with Rapidity and Robustness via Speech Decomposition for Expressive and Controllable Neural Text to Speech","created":"2021-03-17","cited_by_count":18,"area":null},{"id":"2104.03521","title":"Towards Multi-Scale Style Control for Expressive Speech Synthesis","created":"2021-04-08","cited_by_count":18,"area":null},{"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":"2312.11947","title":"Emotion Rendering for Conversational Speech Synthesis with Heterogeneous Graph-Based Context Modeling","created":"2023-12-19","cited_by_count":17,"area":null},{"id":"2202.09950","title":"CampNet: Context-Aware Mask Prediction for End-to-End Text-Based Speech Editing","created":"2022-02-21","cited_by_count":16,"area":null},{"id":"2106.06233","title":"Enhancing Speaking Styles in Conversational Text-to-Speech Synthesis with Graph-based Multi-modal Context Modeling","created":"2021-06-11","cited_by_count":15,"area":null},{"id":"2110.06306","title":"Fine-grained style control in Transformer-based Text-to-speech Synthesis","created":"2021-10-12","cited_by_count":15,"area":null},{"id":"2210.12223","title":"Low-Resource Multilingual and Zero-Shot Multispeaker TTS","created":"2022-10-21","cited_by_count":15,"area":null},{"id":"2307.00024","title":"EmoSpeech: Guiding FastSpeech2 Towards Emotional Text to Speech","created":"2023-06-28","cited_by_count":15,"area":null},{"id":"2312.09651","title":"What to Remember: Self-Adaptive Continual Learning for Audio Deepfake Detection","created":"2023-12-15","cited_by_count":15,"area":null},{"id":"2102.00184","title":"Adversarially learning disentangled speech representations for robust multi-factor voice conversion","created":"2021-01-30","cited_by_count":14,"area":null},{"id":"2106.04283","title":"NWT: Towards natural audio-to-video generation with representation learning","created":"2021-06-08","cited_by_count":14,"area":null},{"id":"2111.05095","title":"Speaker Generation","created":"2021-11-07","cited_by_count":14,"area":null},{"id":"2207.06366","title":"N-Grammer: Augmenting Transformers with latent n-grams","created":"2022-07-13","cited_by_count":14,"area":null},{"id":"2305.13831","title":"ZET-Speech: Zero-shot adaptive Emotion-controllable Text-to-Speech Synthesis with Diffusion and Style-based Models","created":"2023-05-23","cited_by_count":14,"area":null},{"id":"2206.12229","title":"Exact Prosody Cloning in Zero-Shot Multispeaker Text-to-Speech","created":"2022-06-24","cited_by_count":13,"area":null},{"id":"2106.15123","title":"FastPitchFormant: Source-filter based Decomposed Modeling for Speech Synthesis","created":"2021-06-29","cited_by_count":12,"area":null},{"id":"2111.04730","title":"Emotional Prosody Control for Speech Generation","created":"2021-11-07","cited_by_count":12,"area":null},{"id":"2111.10139","title":"More than Words: In-the-Wild Visually-Driven Prosody for Text-to-Speech","created":"2021-11-19","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":"2102.00151","title":"Expressive Neural Voice Cloning","created":"2021-01-30","cited_by_count":11,"area":null},{"id":"2104.00931","title":"Assem-VC: Realistic Voice Conversion by Assembling Modern Speech Synthesis Techniques","created":"2021-04-02","cited_by_count":11,"area":null},{"id":"2110.02891","title":"Style Equalization: Unsupervised Learning of Controllable Generative Sequence Models","created":"2021-10-06","cited_by_count":11,"area":null},{"id":"2301.10606","title":"A Holistic Cascade System, benchmark, and Human Evaluation Protocol for Expressive Speech-to-Speech Translation","created":"2023-01-25","cited_by_count":11,"area":null},{"id":"2308.03300","title":"Do You Remember? Overcoming Catastrophic Forgetting for Fake Audio Detection","created":"2023-08-07","cited_by_count":11,"area":null},{"id":"2206.12559","title":"Self-supervised Context-aware Style Representation for Expressive Speech Synthesis","created":"2022-06-25","cited_by_count":10,"area":null},{"id":"2207.01718","title":"BERT, can HE predict contrastive focus? Predicting and controlling prominence in neural TTS using a language model","created":"2022-07-04","cited_by_count":10,"area":null},{"id":"2304.11976","title":"Zero-shot text-to-speech synthesis conditioned using self-supervised speech representation model","created":"2023-04-24","cited_by_count":10,"area":null},{"id":"2107.12562","title":"Cross-speaker Style Transfer with Prosody Bottleneck in Neural Speech Synthesis","created":"2021-07-27","cited_by_count":9,"area":null},{"id":"2110.02952","title":"Hierarchical prosody modeling and control in non-autoregressive parallel neural TTS","created":"2021-10-06","cited_by_count":9,"area":null},{"id":"2110.03012","title":"Emphasis control for parallel neural TTS","created":"2021-10-06","cited_by_count":9,"area":null},{"id":"2201.02490","title":"Audio representations for deep learning in sound synthesis: A review","created":"2022-01-07","cited_by_count":9,"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":"2203.14757","title":"STUDIES: Corpus of Japanese Empathetic Dialogue Speech Towards Friendly Voice Agent","created":"2022-03-28","cited_by_count":9,"area":null},{"id":"2211.00585","title":"Adapter-Based Extension of Multi-Speaker Text-to-Speech Model for New Speakers","created":"2022-11-01","cited_by_count":9,"area":null},{"id":"2406.06406","title":"Controlling Emotion in Text-to-Speech with Natural Language Prompts","created":"2024-06-10","cited_by_count":9,"area":null},{"id":"2104.05379","title":"Comparing the Benefit of Synthetic Training Data for Various Automatic Speech Recognition Architectures","created":"2021-04-12","cited_by_count":8,"area":null},{"id":"2106.08352","title":"Ctrl-P: Temporal Control of Prosodic Variation for Speech Synthesis","created":"2021-06-15","cited_by_count":8,"area":null},{"id":"2107.08248","title":"Learning De-identified Representations of Prosody from Raw Audio","created":"2021-07-17","cited_by_count":8,"area":null},{"id":"2111.10177","title":"Prosodic Clustering for Phoneme-level Prosody Control in End-to-End Speech Synthesis","created":"2021-11-19","cited_by_count":8,"area":null},{"id":"2204.10020","title":"Cross-Speaker Emotion Transfer for Low-Resource Text-to-Speech Using Non-Parallel Voice Conversion with Pitch-Shift Data Augmentation","created":"2022-04-21","cited_by_count":8,"area":null},{"id":"2211.06892","title":"OverFlow: Putting flows on top of neural transducers for better TTS","created":"2022-11-13","cited_by_count":8,"area":null},{"id":"2212.06972","title":"Disentangling Prosody Representations with Unsupervised Speech Reconstruction","created":"2022-12-14","cited_by_count":8,"area":null},{"id":"2303.07682","title":"QI-TTS: Questioning Intonation Control for Emotional Speech Synthesis","created":"2023-03-14","cited_by_count":8,"area":null},{"id":"2409.16681","title":"Emotional Dimension Control in Language Model-Based Text-to-Speech: Spanning a Broad Spectrum of Human Emotions","created":"2024-09-25","cited_by_count":8,"area":null},{"id":"2601.11846","title":"The Third VoicePrivacy Challenge: Preserving Emotional Expressiveness and Linguistic Content in Voice Anonymization","created":"2026-01-17","cited_by_count":8,"area":null},{"id":"2212.06397","title":"Style-Label-Free: Cross-Speaker Style Transfer by Quantized VAE and Speaker-wise Normalization in Speech Synthesis","created":"2022-12-13","cited_by_count":7,"area":null},{"id":"2303.07711","title":"Improving Prosody for Cross-Speaker Style Transfer by Semi-Supervised Style Extractor and Hierarchical Modeling in Speech Synthesis","created":"2023-03-14","cited_by_count":7,"area":null},{"id":"2404.06674","title":"VoiceShop: A Unified Speech-to-Speech Framework for Identity-Preserving Zero-Shot Voice Editing","created":"2024-04-10","cited_by_count":7,"area":null},{"id":"2407.14056","title":"Rasa: Building Expressive Speech Synthesis Systems for Indian Languages in Low-resource Settings","created":"2024-07-19","cited_by_count":7,"area":null},{"id":"2409.08907","title":"Affective Computing Has Changed: The Foundation Model Disruption","created":"2024-09-13","cited_by_count":7,"area":null},{"id":"2505.01319","title":"Model See Model Do: Speech-Driven Facial Animation with Style Control","created":"2025-05-02","cited_by_count":7,"area":null},{"id":"2101.05313","title":"Whispered and Lombard Neural Speech Synthesis","created":"2021-01-13","cited_by_count":6,"area":null},{"id":"2104.09995","title":"Review of end-to-end speech synthesis technology based on deep learning","created":"2021-04-20","cited_by_count":6,"area":null},{"id":"2105.01891","title":"Exploring emotional prototypes in a high dimensional TTS latent space","created":"2021-05-05","cited_by_count":6,"area":null},{"id":"2106.08519","title":"Global Rhythm Style Transfer Without Text Transcriptions","created":"2021-06-16","cited_by_count":6,"area":null},{"id":"2110.14422","title":"Zero-shot Voice Conversion via Self-supervised Prosody Representation Learning","created":"2021-10-27","cited_by_count":6,"area":null},{"id":"2203.15563","title":"Attacker Attribution of Audio Deepfakes","created":"2022-03-28","cited_by_count":6,"area":null},{"id":"2207.06000","title":"Text-driven Emotional Style Control and Cross-speaker Style Transfer in Neural TTS","created":"2022-07-13","cited_by_count":6,"area":null},{"id":"2210.06877","title":"Pre-Avatar: An Automatic Presentation Generation Framework Leveraging Talking Avatar","created":"2022-10-13","cited_by_count":6,"area":null},{"id":"2210.17222","title":"Combining Automatic Speaker Verification and Prosody Analysis for Synthetic Speech Detection","created":"2022-10-31","cited_by_count":6,"area":null},{"id":"2305.02269","title":"M2-CTTS: End-to-End Multi-scale Multi-modal Conversational Text-to-Speech Synthesis","created":"2023-05-03","cited_by_count":6,"area":null},{"id":"2307.10550","title":"SC VALL-E: Style-Controllable Zero-Shot Text to Speech Synthesizer","created":"2023-07-20","cited_by_count":6,"area":null},{"id":"2309.11725","title":"FluentEditor: Text-based Speech Editing by Considering Acoustic and Prosody Consistency","created":"2023-09-21","cited_by_count":6,"area":null}],"next_cursor":"100"}