{"total":16,"rows":[{"id":"2106.15561","title":"A Survey on Neural Speech Synthesis","created":"2021-06-29","cited_by_count":184,"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":"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":"2211.01751","title":"Iterative autoregression: a novel trick to improve your low-latency speech enhancement model","created":"2022-11-03","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":"2211.16307","title":"Controllable speech synthesis by learning discrete phoneme-level prosodic representations","created":"2022-11-29","cited_by_count":3,"area":null},{"id":"2106.15021","title":"How to Reach Real-Time AI on Consumer Devices? Solutions for Programmable and Custom Architectures","created":"2021-06-21","cited_by_count":2,"area":null},{"id":"2111.09146","title":"Rapping-Singing Voice Synthesis based on Phoneme-level Prosody Control","created":"2021-11-17","cited_by_count":2,"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":"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":"2212.04532","title":"Framewise WaveGAN: High Speed Adversarial Vocoder in Time Domain with Very Low Computational Complexity","created":"2022-12-08","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":"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":"2202.11169","title":"Neural Speech Synthesis on a Shoestring: Improving the Efficiency of LPCNet","created":"2022-02-22","cited_by_count":0,"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}],"next_cursor":null}