{"total":29,"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":"2106.15561","title":"A Survey on Neural Speech Synthesis","created":"2021-06-29","cited_by_count":184,"area":null},{"id":"2103.15060","title":"PnG BERT: Augmented BERT on Phonemes and Graphemes for Neural TTS","created":"2021-03-28","cited_by_count":52,"area":null},{"id":"2106.15153","title":"GANSpeech: Adversarial Training for High-Fidelity Multi-Speaker Speech Synthesis","created":"2021-06-29","cited_by_count":18,"area":null},{"id":"2106.12896","title":"Non-Autoregressive TTS with Explicit Duration Modelling for Low-Resource Highly Expressive Speech","created":"2021-06-24","cited_by_count":14,"area":null},{"id":"2207.00688","title":"Building African Voices","created":"2022-07-01","cited_by_count":14,"area":null},{"id":"2103.03541","title":"Multilingual Byte2Speech Models for Scalable Low-resource Speech Synthesis","created":"2021-03-05","cited_by_count":13,"area":null},{"id":"2104.08459","title":"KazakhTTS: An Open-Source Kazakh Text-to-Speech Synthesis Dataset","created":"2021-04-17","cited_by_count":13,"area":null},{"id":"2203.17190","title":"Mixed-Phoneme BERT: Improving BERT with Mixed Phoneme and Sup-Phoneme Representations for Text to Speech","created":"2022-03-31","cited_by_count":13,"area":null},{"id":"2204.02524","title":"Simple and Effective Unsupervised Speech Synthesis","created":"2022-04-06","cited_by_count":12,"area":null},{"id":"2202.08164","title":"Voice Filter: Few-shot text-to-speech speaker adaptation using voice conversion as a post-processing module","created":"2022-02-16","cited_by_count":8,"area":null},{"id":"2204.10020","title":"Cross-Speaker Emotion Transfer for Low-Resource Text-to-Speech Using Non-Parallel Voice Conversion with Pitch-Shift Data Augmentation","created":"2022-04-21","cited_by_count":8,"area":null},{"id":"2207.09889","title":"When Is TTS Augmentation Through a Pivot Language Useful?","created":"2022-07-20","cited_by_count":8,"area":null},{"id":"2102.09914","title":"Alternate Endings: Improving Prosody for Incremental Neural TTS with Predicted Future Text Input","created":"2021-02-19","cited_by_count":7,"area":null},{"id":"2104.09995","title":"Review of end-to-end speech synthesis technology based on deep learning","created":"2021-04-20","cited_by_count":6,"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":"2305.07455","title":"Improving Cascaded Unsupervised Speech Translation with Denoising Back-translation","created":"2023-05-12","cited_by_count":5,"area":null},{"id":"2503.00733","title":"UniWav: Towards Unified Pre-training for Speech Representation Learning and Generation","created":"2025-03-02","cited_by_count":5,"area":null},{"id":"2301.09099","title":"Unsupervised Data Selection for TTS: Using Arabic Broadcast News as a Case Study","created":"2023-01-22","cited_by_count":4,"area":null},{"id":"2212.03232","title":"Learning the joint distribution of two sequences using little or no paired data","created":"2022-12-06","cited_by_count":3,"area":null},{"id":"2409.01217","title":"A multilingual training strategy for low resource Text to Speech","created":"2024-09-02","cited_by_count":3,"area":null},{"id":"2209.10848","title":"MnTTS: An Open-Source Mongolian Text-to-Speech Synthesis Dataset and Accompanied Baseline","created":"2022-09-22","cited_by_count":2,"area":null},{"id":"2210.14723","title":"Semi-Supervised Learning Based on Reference Model for Low-resource TTS","created":"2022-10-25","cited_by_count":2,"area":null},{"id":"2212.08321","title":"Investigation of Japanese PnG BERT language model in text-to-speech synthesis for pitch accent language","created":"2022-12-16","cited_by_count":2,"area":null},{"id":"2110.03857","title":"A study on the efficacy of model pre-training in developing neural text-to-speech system","created":"2021-10-08","cited_by_count":1,"area":null},{"id":"2209.08795","title":"AutoLV: Automatic Lecture Video Generator","created":"2022-09-19","cited_by_count":1,"area":null},{"id":"2303.15669","title":"Unsupervised Pre-Training For Data-Efficient Text-to-Speech On Low Resource Languages","created":"2023-03-28","cited_by_count":1,"area":null},{"id":"2309.00126","title":"QS-TTS: Towards Semi-Supervised Text-to-Speech Synthesis via Vector-Quantized Self-Supervised Speech Representation Learning","created":"2023-08-31","cited_by_count":1,"area":null},{"id":"2402.01692","title":"Maximizing Data Efficiency for Cross-Lingual TTS Adaptation by Self-Supervised Representation Mixing and Embedding Initialization","created":"2024-01-23","cited_by_count":0,"area":null}],"next_cursor":null}