1
|
{"id": "8875ae233bc074f5cd6c4ebba447b536a7e847a5", "citations": [{"id": "ff34d1ede03e99fb4694961d458bf0ca51cd4b31", "title": "A Near Real-Time Automatic Speaker Recognition Architecture for Voice-Based User Interface", "year": "2019", "pdf": ["https://pdfs.semanticscholar.org/ff34/d1ede03e99fb4694961d458bf0ca51cd4b31.pdf"], "doi": []}, {"id": "a2344004f0e1409c0c9473d071a5cfd74bff0a5d", "title": "Learnable PINs: Cross-modal Embeddings for Person Identity", "year": "2018", "pdf": ["https://arxiv.org/pdf/1805.00833.pdf"], "doi": []}, {"id": "bececcda7976be8e19abe19baf2e1f19483b5eaa", "title": "Additive Margin SincNet for Speaker Recognition", "year": "2019", "pdf": ["https://arxiv.org/pdf/1901.10826.pdf"], "doi": []}, {"id": "87061b07b04c55d426e5469935f7d679fe111ede", "title": "VoiceID Loss: Speech Enhancement for Speaker Verification", "year": "2019", "pdf": ["https://arxiv.org/pdf/1904.03601.pdf"], "doi": []}, {"id": "7fe117f5bbf91f85a97720eca8be36da87a5f8a8", "title": "Revisiting Cross Modal Retrieval", "year": "2018", "pdf": ["https://arxiv.org/pdf/1807.07364.pdf"], "doi": []}, {"id": "2fa77c103e2e4bb166cefab209a0be24c99914d8", "title": "UPC Multimodal Speaker Diarization System for the 2018 Albayzin Challenge", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/2fa7/7c103e2e4bb166cefab209a0be24c99914d8.pdf"], "doi": []}, {"id": "2bee6a78bbc3222a76cf1da0217567277aa3ed5f", "title": "Noise-tolerant Audio-visual Online Person Verification using an Attention-based Neural Network Fusion", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.10813.pdf"], "doi": []}, {"id": "23a109da0c4ce0314f6f016da679a4e1fd6960ef", "title": "JHU Diarization System Description", "year": "2018", "pdf": ["https://pdfs.semanticscholar.org/23a1/09da0c4ce0314f6f016da679a4e1fd6960ef.pdf"], "doi": []}, {"id": "e89cf011bb543137b961807924e0b765d536aa98", "title": "iQIYI-VID: A Large Dataset for Multi-modal Person Identification", "year": "2018", "pdf": ["https://arxiv.org/pdf/1811.07548.pdf"], "doi": []}]}
|
