{"total":15,"rows":[{"id":"2305.13516","title":"Scaling Speech Technology to 1,000+ Languages","created":"2023-05-22","cited_by_count":411,"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":"2407.18879","title":"Utilizing TTS Synthesized Data for Efficient Development of Keyword Spotting Model","created":"2024-07-26","cited_by_count":4,"area":null},{"id":"2406.00022","title":"Multilingual Prosody Transfer: Comparing Supervised & Transfer Learning","created":"2024-05-23","cited_by_count":2,"area":null},{"id":"2406.06664","title":"ASTRA: Aligning Speech and Text Representations for Asr without Sampling","created":"2024-06-10","cited_by_count":2,"area":null},{"id":"2407.16840","title":"Synth4Kws: Synthesized Speech for User Defined Keyword Spotting in Low Resource Environments","created":"2024-07-23","cited_by_count":2,"area":null},{"id":"2502.06180","title":"RideKE: Leveraging Low-Resource, User-Generated Twitter Content for Sentiment and Emotion Detection in Kenyan Code-Switched Dataset","created":"2025-02-10","cited_by_count":2,"area":null},{"id":"2310.05919","title":"Few-Shot Spoken Language Understanding via Joint Speech-Text Models","created":"2023-10-09","cited_by_count":1,"area":null},{"id":"2408.04174","title":"wav2graph: A Framework for Supervised Learning Knowledge Graph from Speech","created":"2024-08-08","cited_by_count":1,"area":null},{"id":"2408.10463","title":"Adversarial training of Keyword Spotting to Minimize TTS Data Overfitting","created":"2024-08-20","cited_by_count":1,"area":null},{"id":"2409.13507","title":"Sketching With Your Voice: \"Non-Phonorealistic\" Rendering of Sounds via Vocal Imitation","created":"2024-09-20","cited_by_count":1,"area":null},{"id":"2410.06572","title":"Can DeepFake Speech be Reliably Detected?","created":"2024-10-09","cited_by_count":1,"area":null},{"id":"2602.03108","title":"ChemPro: A Progressive Chemistry Benchmark for Large Language Models","created":"2026-02-03","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}