{"total":52,"rows":[{"id":"2106.15561","title":"A Survey on Neural Speech Synthesis","created":"2021-06-29","cited_by_count":184,"area":null},{"id":"2112.08352","title":"Textless Speech-to-Speech Translation on Real Data","created":"2021-12-15","cited_by_count":121,"area":null},{"id":"2110.14513","title":"Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representations","created":"2021-10-27","cited_by_count":81,"area":null},{"id":"2212.08055","title":"UnitY: Two-pass Direct Speech-to-speech Translation with Discrete Units","created":"2022-12-15","cited_by_count":60,"area":null},{"id":"2211.04508","title":"SpeechMatrix: A Large-Scale Mined Corpus of Multilingual Speech-to-Speech Translations","created":"2022-11-08","cited_by_count":35,"area":null},{"id":"2103.11401","title":"SwissDial: Parallel Multidialectal Corpus of Spoken Swiss German","created":"2021-03-21","cited_by_count":26,"area":null},{"id":"2203.03191","title":"Language-Agnostic Meta-Learning for Low-Resource Text-to-Speech with Articulatory Features","created":"2022-03-07","cited_by_count":20,"area":null},{"id":"2206.04523","title":"Face-Dubbing++: Lip-Synchronous, Voice Preserving Translation of Videos","created":"2022-06-09","cited_by_count":18,"area":null},{"id":"2212.08486","title":"BLASER: A Text-Free Speech-to-Speech Translation Evaluation Metric","created":"2022-12-16","cited_by_count":16,"area":null},{"id":"2106.06309","title":"HUI-Audio-Corpus-German: A high quality TTS dataset","created":"2021-06-11","cited_by_count":15,"area":null},{"id":"2210.12223","title":"Low-Resource Multilingual and Zero-Shot Multispeaker TTS","created":"2022-10-21","cited_by_count":15,"area":null},{"id":"2203.15796","title":"Unsupervised Text-to-Speech Synthesis by Unsupervised Automatic Speech Recognition","created":"2022-03-29","cited_by_count":14,"area":null},{"id":"2410.01036","title":"MOSEL: 950,000 Hours of Speech Data for Open-Source Speech Foundation Model Training on EU Languages","created":"2024-10-01","cited_by_count":14,"area":null},{"id":"2206.12229","title":"Exact Prosody Cloning in Zero-Shot Multispeaker Text-to-Speech","created":"2022-06-24","cited_by_count":13,"area":null},{"id":"2308.01831","title":"Textless Unit-to-Unit training for Many-to-Many Multilingual Speech-to-Speech Translation","created":"2023-08-03","cited_by_count":11,"area":null},{"id":"2110.13877","title":"Assessing Evaluation Metrics for Speech-to-Speech Translation","created":"2021-10-26","cited_by_count":10,"area":null},{"id":"2204.00618","title":"ASR data augmentation in low-resource settings using cross-lingual multi-speaker TTS and cross-lingual voice conversion","created":"2022-03-29","cited_by_count":10,"area":null},{"id":"2301.12596","title":"Learning to Speak from Text: Zero-Shot Multilingual Text-to-Speech with Unsupervised Text Pretraining","created":"2023-01-30","cited_by_count":10,"area":null},{"id":"2406.06403","title":"Meta Learning Text-to-Speech Synthesis in over 7000 Languages","created":"2024-06-10","cited_by_count":9,"area":null},{"id":"2111.03800","title":"Finnish Dialect Identification: The Effect of Audio and Text","created":"2021-11-06","cited_by_count":8,"area":null},{"id":"2110.07982","title":"Scribosermo: Fast Speech-to-Text models for German and other Languages","created":"2021-10-15","cited_by_count":7,"area":null},{"id":"2305.13137","title":"EMNS /Imz/ Corpus: An emotive single-speaker dataset for narrative storytelling in games, television and graphic novels","created":"2023-05-22","cited_by_count":7,"area":null},{"id":"2409.08346","title":"Towards Quantifying and Reducing Language Mismatch Effects in Cross-Lingual Speech Anti-Spoofing","created":"2024-09-12","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":"2103.14512","title":"Continual Speaker Adaptation for Text-to-Speech Synthesis","created":"2021-03-26","cited_by_count":5,"area":null},{"id":"2104.04896","title":"A Toolbox for Construction and Analysis of Speech Datasets","created":"2021-04-11","cited_by_count":5,"area":null},{"id":"2207.05549","title":"PoeticTTS -- Controllable Poetry Reading for Literary Studies","created":"2022-07-11","cited_by_count":5,"area":null},{"id":"2307.08655","title":"Multilingual Speech-to-Speech Translation into Multiple Target Languages","created":"2023-07-17","cited_by_count":5,"area":null},{"id":"2310.09653","title":"SelfVC: Voice Conversion With Iterative Refinement using Self Transformations","created":"2023-10-14","cited_by_count":5,"area":null},{"id":"2406.15284","title":"The Greek podcast corpus: Competitive speech models for low-resourced languages with weakly supervised data","created":"2024-06-21","cited_by_count":4,"area":null},{"id":"2107.09477","title":"On Prosody Modeling for ASR+TTS based Voice Conversion","created":"2021-07-20","cited_by_count":3,"area":null},{"id":"2110.08214","title":"From Start to Finish: Latency Reduction Strategies for Incremental Speech Synthesis in Simultaneous Speech-to-Speech Translation","created":"2021-10-15","cited_by_count":3,"area":null},{"id":"2206.08039","title":"Acoustic Modeling for End-to-End Empathetic Dialogue Speech Synthesis Using Linguistic and Prosodic Contexts of Dialogue History","created":"2022-06-16","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":"2110.04482","title":"Towards Lifelong Learning of Multilingual Text-To-Speech Synthesis","created":"2021-10-09","cited_by_count":2,"area":null},{"id":"2306.12040","title":"Strategies in Transfer Learning for Low-Resource Speech Synthesis: Phone Mapping, Features Input, and Source Language Selection","created":"2023-06-21","cited_by_count":2,"area":null},{"id":"2407.11370","title":"A Pilot Study of GSLM-based Simulation of Foreign Accentuation Only Using Native Speech Corpora","created":"2024-07-16","cited_by_count":2,"area":null},{"id":"2509.01390","title":"Analysing the Language of Neural Audio Codecs","created":"2025-09-01","cited_by_count":2,"area":null},{"id":"2206.15427","title":"Few-Shot Cross-Lingual TTS Using Transferable Phoneme Embedding","created":"2022-06-27","cited_by_count":1,"area":null},{"id":"2211.12796","title":"IMaSC -- ICFOSS Malayalam Speech Corpus","created":"2022-11-23","cited_by_count":1,"area":null},{"id":"2310.17502","title":"Controllable Generation of Artificial Speaker Embeddings through Discovery of Principal Directions","created":"2023-10-26","cited_by_count":1,"area":null},{"id":"2405.04128","title":"Fine-grained Speech Sentiment Analysis in Chinese Psychological Support Hotlines Based on Large-scale Pre-trained Model","created":"2024-05-07","cited_by_count":1,"area":null},{"id":"2406.17257","title":"Leveraging Parameter-Efficient Transfer Learning for Multi-Lingual Text-to-Speech Adaptation","created":"2024-06-25","cited_by_count":1,"area":null},{"id":"2601.12205","title":"Do Neural Codecs Generalize? A Controlled Study Across Unseen Languages and Non-Speech Tasks","created":"2026-01-18","cited_by_count":1,"area":null},{"id":"2605.00251","title":"Alethia: A Foundational Encoder for Voice Deepfakes","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2606.09553","title":"OpenBibleTTS: Large-Scale Speech Resources and TTS Models for Low-Resource Languages","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2609.01016","title":"Phrase-Localized Language-Contrastive Guidance: Training-Free Localized Accent Control for Code-Switching Text-to-Speech","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2211.13776","title":"German Phoneme Recognition with Text-to-Phoneme Data Augmentation","created":"2022-11-24","cited_by_count":0,"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},{"id":"2408.06827","title":"PRESENT: Zero-Shot Text-to-Prosody Control","created":"2024-08-13","cited_by_count":0,"area":null},{"id":"2412.20048","title":"CrossSpeech++: Cross-lingual Speech Synthesis with Decoupled Language and Speaker Generation","created":"2024-12-28","cited_by_count":0,"area":null},{"id":"2609.10022","title":"Deterministic Prompting for Speaker-Stable Low-Resource Greek TTS","created":"2026-09-09","cited_by_count":0,"area":null}],"next_cursor":null}