{"total":42,"rows":[{"id":"2106.15561","title":"A Survey on Neural Speech Synthesis","created":"2021-06-29","cited_by_count":184,"area":null},{"id":"2102.12664","title":"MixSpeech: Data Augmentation for Low-resource Automatic Speech Recognition","created":"2021-02-25","cited_by_count":39,"area":null},{"id":"2209.02842","title":"ASR2K: Speech Recognition for Around 2000 Languages without Audio","created":"2022-09-06","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":"2204.11909","title":"How can NLP Help Revitalize Endangered Languages? A Case Study and Roadmap for the Cherokee Language","created":"2022-04-25","cited_by_count":19,"area":null},{"id":"2106.09317","title":"EMOVIE: A Mandarin Emotion Speech Dataset with a Simple Emotional Text-to-Speech Model","created":"2021-06-17","cited_by_count":18,"area":null},{"id":"2108.11436","title":"Integrated Speech and Gesture Synthesis","created":"2021-08-25","cited_by_count":16,"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":"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":"2203.15796","title":"Unsupervised Text-to-Speech Synthesis by Unsupervised Automatic Speech Recognition","created":"2022-03-29","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":"2103.07762","title":"OkwuGb\\'e: End-to-End Speech Recognition for Fon and Igbo","created":"2021-03-13","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":"2406.06403","title":"Meta Learning Text-to-Speech Synthesis in over 7000 Languages","created":"2024-06-10","cited_by_count":9,"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":"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":"2201.01209","title":"Speech-to-SQL: Towards Speech-driven SQL Query Generation From Natural Language Question","created":"2022-01-04","cited_by_count":6,"area":null},{"id":"2203.11562","title":"A Text-to-Speech Pipeline, Evaluation Methodology, and Initial Fine-Tuning Results for Child Speech Synthesis","created":"2022-03-22","cited_by_count":5,"area":null},{"id":"2305.19563","title":"Zero-Shot Automatic Pronunciation Assessment","created":"2023-05-31","cited_by_count":5,"area":null},{"id":"2204.04645","title":"Self-Supervised Audio-and-Text Pre-training with Extremely Low-Resource Parallel Data","created":"2022-04-10","cited_by_count":4,"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":"2303.01261","title":"ParrotTTS: Text-to-Speech synthesis by exploiting self-supervised representations","created":"2023-03-01","cited_by_count":4,"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":"2507.17578","title":"Synthetic Voice Data for Automatic Speech Recognition in African Languages","created":"2025-07-23","cited_by_count":3,"area":null},{"id":"2208.13191","title":"Towards Disentangled Speech Representations","created":"2022-08-28","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":"2210.15131","title":"Towards High-Quality Neural TTS for Low-Resource Languages by Learning Compact Speech Representations","created":"2022-10-27","cited_by_count":1,"area":null},{"id":"2303.10727","title":"ERSAM: Neural Architecture Search For Energy-Efficient and Real-Time Social Ambiance Measurement","created":"2023-03-19","cited_by_count":1,"area":null},{"id":"2304.11053","title":"A Comparison of Semi-Supervised Learning Techniques for Streaming ASR at Scale","created":"2023-04-19","cited_by_count":1,"area":null},{"id":"2412.20833","title":"Inclusion 2024 Global Multimedia Deepfake Detection Challenge: Towards Multi-dimensional Face Forgery Detection","created":"2024-12-30","cited_by_count":1,"area":null},{"id":"2510.16497","title":"Edge-Based Speech Transcription and Synthesis for Kinyarwanda and Swahili Languages","created":"2025-10-18","cited_by_count":1,"area":null},{"id":"2301.04327","title":"Dual Learning for Large Vocabulary On-Device ASR","created":"2023-01-11","cited_by_count":0,"area":null},{"id":"2305.11926","title":"MParrotTTS: Multilingual Multi-speaker Text to Speech Synthesis in Low Resource Setting","created":"2023-05-19","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":"2410.14380","title":"Dual-Label Learning With Irregularly Present Labels","created":"2024-10-18","cited_by_count":0,"area":null},{"id":"2412.04717","title":"NoLoR: An ASR-Based Framework for Expedited Endangered Language Documentation with Neo-Aramaic as a Case Study","created":"2024-12-06","cited_by_count":0,"area":null},{"id":"2504.07858","title":"Empowering Global Voices: A Data-Efficient, Phoneme-Tone Adaptive Approach to High-Fidelity Speech Synthesis","created":"2025-04-10","cited_by_count":0,"area":null},{"id":"2505.05056","title":"Teochew-Wild: The First In-the-wild Teochew Dataset with Orthographic Annotations","created":"2025-05-08","cited_by_count":0,"area":null},{"id":"2507.16843","title":"Weak Supervision Techniques towards Enhanced ASR Models in Industry-level CRM Systems","created":"2025-07-20","cited_by_count":0,"area":null},{"id":"2510.04750","title":"A Low-Resource Speech-Driven NLP Pipeline for Sinhala Dyslexia Assistance","created":"2025-10-06","cited_by_count":0,"area":null},{"id":"2602.23388","title":"Task-Lens: Cross-Task Utility Based Speech Dataset Profiling for Low-Resource Indian Languages","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2606.09295","title":"N\\\"ushuVoice: Reviving the Voice of Endangered N\\\"ushu with Pitch-Aware Text-to-Speech","created":"2026-06-08","cited_by_count":0,"area":null}],"next_cursor":null}