{"total":25,"rows":[{"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":"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":"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":"2208.08706","title":"Musika! Fast Infinite Waveform Music Generation","created":"2022-08-18","cited_by_count":24,"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":"2204.03594","title":"Heterogeneous Target Speech Separation","created":"2022-04-07","cited_by_count":13,"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":"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":"2503.04724","title":"LLMVoX: Autoregressive Streaming Text-to-Speech Model for Any LLM","created":"2025-03-06","cited_by_count":7,"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":"2310.06930","title":"Prosody Analysis of Audiobooks","created":"2023-10-10","cited_by_count":3,"area":null},{"id":"2203.09825","title":"AdaVocoder: Adaptive Vocoder for Custom Voice","created":"2022-03-18","cited_by_count":2,"area":null},{"id":"2303.06078","title":"An End-to-End Neural Network for Image-to-Audio Transformation","created":"2023-03-10","cited_by_count":2,"area":null},{"id":"2204.04127","title":"Karaoker: Alignment-free singing voice synthesis with speech training data","created":"2022-04-08","cited_by_count":1,"area":null},{"id":"2205.04120","title":"Cross-Utterance Conditioned VAE for Non-Autoregressive Text-to-Speech","created":"2022-05-09","cited_by_count":1,"area":null},{"id":"2309.04156","title":"Cross-Utterance Conditioned VAE for Speech Generation","created":"2023-09-08","cited_by_count":1,"area":null},{"id":"2505.19119","title":"CloneShield: A Framework for Universal Perturbation Against Zero-Shot Voice Cloning","created":"2025-05-25","cited_by_count":1,"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":"2203.11049","title":"AutoTTS: End-to-End Text-to-Speech Synthesis through Differentiable Duration Modeling","created":"2022-03-21","cited_by_count":0,"area":null},{"id":"2206.02147","title":"Dict-TTS: Learning to Pronounce with Prior Dictionary Knowledge for Text-to-Speech","created":"2022-06-05","cited_by_count":0,"area":null},{"id":"2206.12132","title":"SANE-TTS: Stable And Natural End-to-End Multilingual Text-to-Speech","created":"2022-06-24","cited_by_count":0,"area":null},{"id":"2305.11926","title":"MParrotTTS: Multilingual Multi-speaker Text to Speech Synthesis in Low Resource Setting","created":"2023-05-19","cited_by_count":0,"area":null},{"id":"2601.10315","title":"ADVOSYNTH: A Synthetic Multi-Advocate Dataset for Speaker Identification in Courtroom Scenarios","created":"2026-01-15","cited_by_count":0,"area":null},{"id":"2604.09111","title":"PS-TTS: Phonetic Synchronization in Text-to-Speech for Achieving Natural Automated Dubbing","created":"2026-04-10","cited_by_count":0,"area":null}],"next_cursor":null}