{"total":31,"rows":[{"id":"2106.15561","title":"A Survey on Neural Speech Synthesis","created":"2021-06-29","cited_by_count":184,"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":"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":"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":"2110.12612","title":"DelightfulTTS: The Microsoft Speech Synthesis System for Blizzard Challenge 2021","created":"2021-10-25","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":"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":"2111.05095","title":"Speaker Generation","created":"2021-11-07","cited_by_count":14,"area":null},{"id":"2102.00151","title":"Expressive Neural Voice Cloning","created":"2021-01-30","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":"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":"2111.10173","title":"Word-Level Style Control for Expressive, Non-attentive Speech Synthesis","created":"2021-11-19","cited_by_count":5,"area":null},{"id":"2202.06409","title":"Distribution augmentation for low-resource expressive text-to-speech","created":"2022-02-13","cited_by_count":5,"area":null},{"id":"2305.13724","title":"ChatGPT-EDSS: Empathetic Dialogue Speech Synthesis Trained from ChatGPT-derived Context Word Embeddings","created":"2023-05-23","cited_by_count":4,"area":null},{"id":"2312.12181","title":"StyleSpeech: Self-supervised Style Enhancing with VQ-VAE-based Pre-training for Expressive Audiobook Speech Synthesis","created":"2023-12-19","cited_by_count":4,"area":null},{"id":"2405.11413","title":"Exploring speech style spaces with language models: Emotional TTS without emotion labels","created":"2024-05-18","cited_by_count":4,"area":null},{"id":"2107.09477","title":"On Prosody Modeling for ASR+TTS based Voice Conversion","created":"2021-07-20","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":"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":"2205.04952","title":"Read the Room: Adapting a Robot's Voice to Ambient and Social Contexts","created":"2022-05-10","cited_by_count":2,"area":null},{"id":"2110.04451","title":"Using multiple reference audios and style embedding constraints for speech synthesis","created":"2021-10-09","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":"2301.12331","title":"Time out of Mind: Generating Rate of Speech conditioned on emotion and speaker","created":"2023-01-29","cited_by_count":1,"area":null},{"id":"2309.11849","title":"A Discourse-level Multi-scale Prosodic Model for Fine-grained Emotion Analysis","created":"2023-09-21","cited_by_count":1,"area":null},{"id":"2211.01327","title":"Predicting phoneme-level prosody latents using AR and flow-based Prior Networks for expressive speech synthesis","created":"2022-11-02","cited_by_count":0,"area":null},{"id":"2404.02592","title":"Leveraging the Interplay Between Syntactic and Acoustic Cues for Optimizing Korean TTS Pause Formation","created":"2024-04-03","cited_by_count":0,"area":null},{"id":"2505.07202","title":"On the Cost and Benefits of Training Context with Utterance or Full Conversation Training: A Comparative Stud","created":"2025-05-12","cited_by_count":0,"area":null},{"id":"2610.05575","title":"Can Prosodic Style Be Inferred from Text Alone? Evidence from Unsupervised Acoustic Clusters","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}