{"total":33,"rows":[{"id":"2106.15561","title":"A Survey on Neural Speech Synthesis","created":"2021-06-29","cited_by_count":184,"area":null},{"id":"2103.00993","title":"AdaSpeech: Adaptive Text to Speech for Custom Voice","created":"2021-03-01","cited_by_count":98,"area":null},{"id":"2208.05890","title":"Speech Synthesis with Mixed Emotions","created":"2022-08-11","cited_by_count":28,"area":null},{"id":"2205.07211","title":"GenerSpeech: Towards Style Transfer for Generalizable Out-Of-Domain Text-to-Speech","created":"2022-05-15","cited_by_count":21,"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":"2104.07474","title":"EAT: Enhanced ASR-TTS for Self-supervised Speech Recognition","created":"2021-04-13","cited_by_count":13,"area":null},{"id":"2106.15123","title":"FastPitchFormant: Source-filter based Decomposed Modeling for Speech Synthesis","created":"2021-06-29","cited_by_count":12,"area":null},{"id":"2110.02891","title":"Style Equalization: Unsupervised Learning of Controllable Generative Sequence Models","created":"2021-10-06","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":"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":"2202.07200","title":"Unsupervised word-level prosody tagging for controllable speech synthesis","created":"2022-02-15","cited_by_count":7,"area":null},{"id":"2211.13533","title":"Prosody-controllable spontaneous TTS with neural HMMs","created":"2022-11-24","cited_by_count":7,"area":null},{"id":"2212.06397","title":"Style-Label-Free: Cross-Speaker Style Transfer by Quantized VAE and Speaker-wise Normalization in Speech Synthesis","created":"2022-12-13","cited_by_count":7,"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":"2503.08954","title":"An Exhaustive Evaluation of TTS- and VC-based Data Augmentation for ASR","created":"2025-03-11","cited_by_count":5,"area":null},{"id":"2302.12391","title":"PITS: Variational Pitch Inference without Fundamental Frequency for End-to-End Pitch-controllable TTS","created":"2023-02-24","cited_by_count":4,"area":null},{"id":"2411.00588","title":"$\\alpha$-TCVAE: On the relationship between Disentanglement and Diversity","created":"2024-11-01","cited_by_count":4,"area":null},{"id":"2110.12539","title":"Discrete Acoustic Space for an Efficient Sampling in Neural Text-To-Speech","created":"2021-10-24","cited_by_count":3,"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":"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":"2306.15282","title":"Variational latent discrete representation for time series modelling","created":"2023-06-27","cited_by_count":2,"area":null},{"id":"2406.03117","title":"VQUNet: Vector Quantization U-Net for Defending Adversarial Atacks by Regularizing Unwanted Noise","created":"2024-06-05","cited_by_count":2,"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":"2309.04156","title":"Cross-Utterance Conditioned VAE for Speech Generation","created":"2023-09-08","cited_by_count":1,"area":null},{"id":"2409.08664","title":"Investigating Disentanglement in a Phoneme-level Speech Codec for Prosody Modeling","created":"2024-09-13","cited_by_count":1,"area":null},{"id":"2106.13479","title":"Preliminary study on using vector quantization latent spaces for TTS/VC systems with consistent performance","created":"2021-06-25","cited_by_count":0,"area":null},{"id":"2106.15649","title":"Multi-Scale Spectrogram Modelling for Neural Text-to-Speech","created":"2021-06-29","cited_by_count":0,"area":null},{"id":"2211.00523","title":"Learning utterance-level representations through token-level acoustic latents prediction for Expressive Speech Synthesis","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":"2302.03498","title":"MAC: A unified framework boosting low resource automatic speech recognition","created":"2023-02-05","cited_by_count":0,"area":null},{"id":"2310.05374","title":"Improving End-to-End Speech Processing by Efficient Text Data Utilization with Latent Synthesis","created":"2023-10-09","cited_by_count":0,"area":null}],"next_cursor":null}