{"total":16,"rows":[{"id":"2204.03040","title":"SOMOS: The Samsung Open MOS Dataset for the Evaluation of Neural Text-to-Speech Synthesis","created":"2022-04-06","cited_by_count":18,"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":"2111.10173","title":"Word-Level Style Control for Expressive, Non-attentive Speech Synthesis","created":"2021-11-19","cited_by_count":5,"area":null},{"id":"2111.10168","title":"Improved Prosodic Clustering for Multispeaker and Speaker-independent Phoneme-level Prosody Control","created":"2021-11-19","cited_by_count":3,"area":null},{"id":"2210.17264","title":"Cross-lingual Text-To-Speech with Flow-based Voice Conversion for Improved Pronunciation","created":"2022-10-31","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":"2204.01271","title":"Into-TTS : Intonation Template Based Prosody Control System","created":"2022-04-04","cited_by_count":2,"area":null},{"id":"2204.03421","title":"Self-supervised learning for robust voice cloning","created":"2022-04-07","cited_by_count":2,"area":null},{"id":"2204.05070","title":"Fine-grained Noise Control for Multispeaker Speech Synthesis","created":"2022-04-11","cited_by_count":2,"area":null},{"id":"2211.00342","title":"Investigating Content-Aware Neural Text-To-Speech MOS Prediction Using Prosodic and Linguistic Features","created":"2022-11-01","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":"2211.13939","title":"Efficient Incremental Text-to-Speech on GPUs","created":"2022-11-25","cited_by_count":1,"area":null},{"id":"2203.14416","title":"Bunched LPCNet2: Efficient Neural Vocoders Covering Devices from Cloud to Edge","created":"2022-03-27","cited_by_count":0,"area":null},{"id":"2211.00375","title":"Generating Multilingual Gender-Ambiguous Text-to-Speech Voices","created":"2022-11-01","cited_by_count":0,"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":"2610.00063","title":"Pushing CPU Speech Synthesis to the Wall: Extreme Inference Tuning under Serverless Architecture and Billing","created":"2026-09-04","cited_by_count":0,"area":null}],"next_cursor":null}