{"total":31,"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":"2306.15687","title":"Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale","created":"2023-06-23","cited_by_count":379,"area":null},{"id":"2403.16973","title":"VoiceCraft: Zero-Shot Speech Editing and Text-to-Speech in the Wild","created":"2024-03-25","cited_by_count":120,"area":null},{"id":"2401.17264","title":"Proactive Detection of Voice Cloning with Localized Watermarking","created":"2024-01-30","cited_by_count":78,"area":null},{"id":"2205.03983","title":"Building Machine Translation Systems for the Next Thousand Languages","created":"2022-05-09","cited_by_count":69,"area":null},{"id":"2308.06873","title":"SpeechX: Neural Codec Language Model as a Versatile Speech Transformer","created":"2023-08-14","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":"2210.15447","title":"Virtuoso: Massive Multilingual Speech-Text Joint Semi-Supervised Learning for Text-To-Speech","created":"2022-10-27","cited_by_count":15,"area":null},{"id":"2409.06029","title":"SongCreator: Lyrics-based Universal Song Generation","created":"2024-09-09","cited_by_count":12,"area":null},{"id":"2402.07383","title":"Making Flow-Matching-Based Zero-Shot Text-to-Speech Laugh as You Like","created":"2024-02-12","cited_by_count":11,"area":null},{"id":"2407.15835","title":"dMel: Speech Tokenization made Simple","created":"2024-07-22","cited_by_count":11,"area":null},{"id":"2505.19206","title":"SpeakStream: Streaming Text-to-Speech with Interleaved Data","created":"2025-05-25","cited_by_count":8,"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},{"id":"2505.00579","title":"Voice Cloning: Comprehensive Survey","created":"2025-05-01","cited_by_count":4,"area":null},{"id":"2212.10191","title":"Emotion Selectable End-to-End Text-based Speech Editing","created":"2022-12-20","cited_by_count":3,"area":null},{"id":"2409.12992","title":"DiffEditor: Enhancing Speech Editing with Semantic Enrichment and Acoustic Consistency","created":"2024-09-19","cited_by_count":3,"area":null},{"id":"2503.16578","title":"SeniorTalk: A Chinese Conversation Dataset with Rich Annotations for Super-Aged Seniors","created":"2025-03-20","cited_by_count":3,"area":null},{"id":"2306.08588","title":"Improving Code-Switching and Named Entity Recognition in ASR with Speech Editing based Data Augmentation","created":"2023-06-14","cited_by_count":2,"area":null},{"id":"2411.17690","title":"Mechanisms of Multimodal Synchronization: Insights from Decoder-Based Video-Text-to-Speech Synthesis","created":"2024-11-26","cited_by_count":2,"area":null},{"id":"2504.00750","title":"$C^2$AV-TSE: Context and Confidence-aware Audio Visual Target Speaker Extraction","created":"2025-04-01","cited_by_count":2,"area":null},{"id":"2212.10901","title":"ALCAP: Alignment-Augmented Music Captioner","created":"2022-12-21","cited_by_count":1,"area":null},{"id":"2302.13678","title":"A Comparative Analysis Of Latent Regressor Losses For Singing Voice Conversion","created":"2023-02-27","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":"2403.04804","title":"AttentionStitch: How Attention Solves the Speech Editing Problem","created":"2024-03-05","cited_by_count":1,"area":null},{"id":"2407.17172","title":"Speech Editing -- a Summary","created":"2024-07-24","cited_by_count":1,"area":null},{"id":"2410.03719","title":"FluentEditor2: Text-based Speech Editing by Modeling Multi-Scale Acoustic and Prosody Consistency","created":"2024-09-28","cited_by_count":1,"area":null},{"id":"2601.21463","title":"Unifying Speech Editing Detection and Content Localization via Prior-Enhanced Audio LLMs","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2603.06444","title":"Prosodic Boundary-Aware Streaming Generation for LLM-Based TTS with Streaming Text Input","created":"2026-03-06","cited_by_count":1,"area":null},{"id":"2211.03545","title":"ERNIE-SAT: Speech and Text Joint Pretraining for Cross-Lingual Multi-Speaker Text-to-Speech","created":"2022-11-07","cited_by_count":0,"area":null},{"id":"2505.20341","title":"Towards Emotionally Consistent Text-Based Speech Editing: Introducing EmoCorrector and The ECD-TSE Dataset","created":"2025-05-24","cited_by_count":0,"area":null},{"id":"2608.02673","title":"dots.tts.edit: Precisely Controlled Speech Editing with a Continuous Autoregressive Model","created":"2026-08-02","cited_by_count":0,"area":null}],"next_cursor":null}