{"total":42,"rows":[{"id":"2106.15561","title":"A Survey on Neural Speech Synthesis","created":"2021-06-29","cited_by_count":184,"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":"2107.08661","title":"Translatotron 2: High-quality direct speech-to-speech translation with voice preservation","created":"2021-07-19","cited_by_count":71,"area":null},{"id":"2108.10447","title":"One TTS Alignment To Rule Them All","created":"2021-08-23","cited_by_count":47,"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":"2212.04054","title":"Learning to Dub Movies via Hierarchical Prosody Models","created":"2022-12-08","cited_by_count":29,"area":null},{"id":"2111.12890","title":"V2C: Visual Voice Cloning","created":"2021-11-25","cited_by_count":24,"area":null},{"id":"2111.09052","title":"High Quality Streaming Speech Synthesis with Low, Sentence-Length-Independent Latency","created":"2021-11-17","cited_by_count":19,"area":null},{"id":"2109.05244","title":"Modeling Concentrated Cross-Attention for Neural Machine Translation with Gaussian Mixture Model","created":"2021-09-11","cited_by_count":18,"area":null},{"id":"2108.04325","title":"AnyoneNet: Synchronized Speech and Talking Head Generation for Arbitrary Person","created":"2021-08-09","cited_by_count":17,"area":null},{"id":"2108.11436","title":"Integrated Speech and Gesture Synthesis","created":"2021-08-25","cited_by_count":16,"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":"2106.12896","title":"Non-Autoregressive TTS with Explicit Duration Modelling for Low-Resource Highly Expressive Speech","created":"2021-06-24","cited_by_count":14,"area":null},{"id":"2111.05095","title":"Speaker Generation","created":"2021-11-07","cited_by_count":14,"area":null},{"id":"2102.06431","title":"VARA-TTS: Non-Autoregressive Text-to-Speech Synthesis based on Very Deep VAE with Residual Attention","created":"2021-02-12","cited_by_count":12,"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":"2410.06796","title":"Diffuse or Confuse: A Diffusion Deepfake Speech Dataset","created":"2024-10-09","cited_by_count":8,"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":"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":"2209.06484","title":"ParaTTS: Learning Linguistic and Prosodic Cross-sentence Information in Paragraph-based TTS","created":"2022-09-14","cited_by_count":5,"area":null},{"id":"2503.22265","title":"DeepAudio-V1:Towards Multi-Modal Multi-Stage End-to-End Video to Speech and Audio Generation","created":"2025-03-28","cited_by_count":5,"area":null},{"id":"2410.22179","title":"Robust and Unbounded Length Generalization in Autoregressive Transformer-Based Text-to-Speech","created":"2024-10-29","cited_by_count":4,"area":null},{"id":"2204.13437","title":"Regotron: Regularizing the Tacotron2 architecture via monotonic alignment loss","created":"2022-04-28","cited_by_count":3,"area":null},{"id":"2211.16307","title":"Controllable speech synthesis by learning discrete phoneme-level prosodic representations","created":"2022-11-29","cited_by_count":3,"area":null},{"id":"2212.03232","title":"Learning the joint distribution of two sequences using little or no paired data","created":"2022-12-06","cited_by_count":3,"area":null},{"id":"2301.03801","title":"UnifySpeech: A Unified Framework for Zero-shot Text-to-Speech and Voice Conversion","created":"2023-01-10","cited_by_count":3,"area":null},{"id":"2108.06270","title":"Enhancing audio quality for expressive Neural Text-to-Speech","created":"2021-08-13","cited_by_count":2,"area":null},{"id":"2201.10375","title":"Zero-Shot Long-Form Voice Cloning with Dynamic Convolution Attention","created":"2022-01-25","cited_by_count":2,"area":null},{"id":"2304.04157","title":"An investigation of phrase break prediction in an End-to-End TTS system","created":"2023-04-09","cited_by_count":2,"area":null},{"id":"2212.05805","title":"Direct Speech-to-speech Translation without Textual Annotation using Bottleneck Features","created":"2022-12-12","cited_by_count":1,"area":null},{"id":"2409.09891","title":"Acquiring Pronunciation Knowledge from Transcribed Speech Audio via Multi-task Learning","created":"2024-09-15","cited_by_count":1,"area":null},{"id":"2102.00247","title":"Triple M: A Practical Text-to-speech Synthesis System With Multi-guidance Attention And Multi-band Multi-time LPCNet","created":"2021-01-30","cited_by_count":0,"area":null},{"id":"2109.13673","title":"Nana-HDR: A Non-attentive Non-autoregressive Hybrid Model for TTS","created":"2021-09-28","cited_by_count":0,"area":null},{"id":"2110.04486","title":"PAMA-TTS: Progression-Aware Monotonic Attention for Stable Seq2Seq TTS With Accurate Phoneme Duration Control","created":"2021-10-09","cited_by_count":0,"area":null},{"id":"2206.15276","title":"R-MelNet: Reduced Mel-Spectral Modeling for Neural TTS","created":"2022-06-30","cited_by_count":0,"area":null},{"id":"2209.10890","title":"EPIC TTS Models: Empirical Pruning Investigations Characterizing Text-To-Speech Models","created":"2022-09-22","cited_by_count":0,"area":null},{"id":"2410.21778","title":"RELATE: A Modern Processing Platform for Romanian Language","created":"2024-10-29","cited_by_count":0,"area":null},{"id":"2505.01450","title":"Towards Film-Making Production Dialogue, Narration, Monologue Adaptive Moving Dubbing Benchmarks","created":"2025-04-30","cited_by_count":0,"area":null},{"id":"2505.16279","title":"MM-MovieDubber: Towards Multi-Modal Learning for Multi-Modal Movie Dubbing","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2507.22612","title":"Adaptive Duration Model for Text Speech Alignment","created":"2025-07-30","cited_by_count":0,"area":null},{"id":"2605.30311","title":"Archon: A Unified Multimodal Model for Holistic Digital Human Generation","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2607.29363","title":"Stable Autoregressive Speech Generation with Low-Frame-Rate High-Dimensional Continuous Tokens","created":"2026-07-31","cited_by_count":0,"area":null}],"next_cursor":null}