{"total":33,"rows":[{"id":"2110.07205","title":"SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing","created":"2021-10-14","cited_by_count":180,"area":null},{"id":"2303.03926","title":"Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling","created":"2023-03-07","cited_by_count":167,"area":null},{"id":"2305.16107","title":"VioLA: Unified Codec Language Models for Speech Recognition, Synthesis, and Translation","created":"2023-05-25","cited_by_count":87,"area":null},{"id":"2208.10441","title":"The GENEA Challenge 2022: A large evaluation of data-driven co-speech gesture generation","created":"2022-08-22","cited_by_count":40,"area":null},{"id":"2303.08737","title":"Evaluating gesture generation in a large-scale open challenge: The GENEA Challenge 2022","created":"2023-03-15","cited_by_count":29,"area":null},{"id":"2110.09103","title":"LDNet: Unified Listener Dependent Modeling in MOS Prediction for Synthetic Speech","created":"2021-10-18","cited_by_count":24,"area":null},{"id":"2411.07111","title":"Building a Taiwanese Mandarin Spoken Language Model: A First Attempt","created":"2024-11-11","cited_by_count":23,"area":null},{"id":"2401.00246","title":"Boosting Large Language Model for Speech Synthesis: An Empirical Study","created":"2023-12-30","cited_by_count":21,"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":"2307.00024","title":"EmoSpeech: Guiding FastSpeech2 Towards Emotional Text to Speech","created":"2023-06-28","cited_by_count":15,"area":null},{"id":"2404.06690","title":"CoVoMix: Advancing Zero-Shot Speech Generation for Human-like Multi-talker Conversations","created":"2024-04-10","cited_by_count":15,"area":null},{"id":"2410.16726","title":"Enhancing Low-Resource ASR through Versatile TTS: Bridging the Data Gap","created":"2024-10-22","cited_by_count":12,"area":null},{"id":"2505.19598","title":"Evaluating Robustness of Large Audio Language Models to Audio Injection: An Empirical Study","created":"2025-05-26","cited_by_count":12,"area":null},{"id":"2405.17809","title":"TransVIP: Speech to Speech Translation System with Voice and Isochrony Preservation","created":"2024-05-28","cited_by_count":10,"area":null},{"id":"2406.11727","title":"1000 African Voices: Advancing inclusive multi-speaker multi-accent speech synthesis","created":"2024-06-17","cited_by_count":9,"area":null},{"id":"2210.11096","title":"Robust One-Shot Singing Voice Conversion","created":"2022-10-20","cited_by_count":6,"area":null},{"id":"2107.09392","title":"SVSNet: An End-to-end Speaker Voice Similarity Assessment Model","created":"2021-07-20","cited_by_count":4,"area":null},{"id":"2107.12003","title":"Facetron: A Multi-speaker Face-to-Speech Model based on Cross-modal Latent Representations","created":"2021-07-26","cited_by_count":4,"area":null},{"id":"2505.14410","title":"Pairwise Evaluation of Accent Similarity in Speech Synthesis","created":"2025-05-20","cited_by_count":4,"area":null},{"id":"2407.21476","title":"On the Problem of Text-To-Speech Model Selection for Synthetic Data Generation in Automatic Speech Recognition","created":"2024-07-31","cited_by_count":3,"area":null},{"id":"2204.07075","title":"Learning and controlling the source-filter representation of speech with a variational autoencoder","created":"2022-04-14","cited_by_count":2,"area":null},{"id":"2206.13272","title":"Wideband Audio Waveform Evaluation Networks: Efficient, Accurate Estimation of Speech Qualities","created":"2022-06-27","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":"2305.15055","title":"Iteratively Improving Speech Recognition and Voice Conversion","created":"2023-05-24","cited_by_count":2,"area":null},{"id":"2504.20447","title":"APG-MOS: Auditory Perception Guided-MOS Predictor for Synthetic Speech","created":"2025-04-29","cited_by_count":2,"area":null},{"id":"2209.11003","title":"Predicting pairwise preferences between TTS audio stimuli using parallel ratings data and anti-symmetric twin neural networks","created":"2022-09-22","cited_by_count":1,"area":null},{"id":"2302.13838","title":"Cross-modal Face- and Voice-style Transfer","created":"2023-02-27","cited_by_count":1,"area":null},{"id":"2404.01339","title":"Humane Speech Synthesis through Zero-Shot Emotion and Disfluency Generation","created":"2024-03-31","cited_by_count":1,"area":null},{"id":"2210.14406","title":"RedPen: Region- and Reason-Annotated Dataset of Unnatural Speech","created":"2022-10-26","cited_by_count":0,"area":null},{"id":"2507.13563","title":"Balalaika: Data-Centric, Prosody-Aware Annotation Pipeline for Russian Speech","created":"2025-07-17","cited_by_count":0,"area":null},{"id":"2606.31947","title":"LuxEmo: Expressive Text-to-Speech Corpus for Luxembourgish","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.02763","title":"LuxSQA: Ask Me in Luxembourgish with TTS-Augmented Spoken Question Answering","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2609.28974","title":"Same Bit Width, Different Outcomes: Post-Training Quantization of Text-to-Speech Across Architectures","created":"2026-09-24","cited_by_count":0,"area":null}],"next_cursor":null}