본문 바로가기

전체 글

[논문] YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone https://arxiv.org/abs/2112.02418 YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyoneYourTTS brings the power of a multilingual approach to the task of zero-shot multi-speaker TTS. Our method builds upon the VITS model and adds several novel modifications for zero-shot multi-speaker and multilingual training. We achieved state-of-the-art (arxiv.org해당 논문을 보고 작성.. 연구실 공부 2024. 10. 15.
[논문] Avocodo: Generative Adversarial Network for Artifact-free Vocoder https://arxiv.org/abs/2206.13404 Avocodo: Generative Adversarial Network for Artifact-free VocoderNeural vocoders based on the generative adversarial neural network (GAN) have been widely used due to their fast inference speed and lightweight networks while generating high-quality speech waveforms. Since the perceptually important speech components arearxiv.org해당 논문을 보고 작성했습니다. Abstract빠른 추론 속도와.. 연구실 공부 2024. 10. 10.
[논문] LUKE: Deep Contextualized Entity Representation with Entity-aware Self-attention https://arxiv.org/abs/2010.01057 LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attentionEntity representations are useful in natural language tasks involving entities. In this paper, we propose new pretrained contextualized representations of words and entities based on the bidirectional transformer. The proposed model treats words and entitiarxiv.org해당 논문을 보고 작성했습니다. A.. 연구실 공부 2024. 9. 13.
[논문] Simple Unsupervised Keyphrase Extraction using Sentence Embeddings https://arxiv.org/abs/1801.04470 Simple Unsupervised Keyphrase Extraction using Sentence EmbeddingsKeyphrase extraction is the task of automatically selecting a small set of phrases that best describe a given free text document. Supervised keyphrase extraction requires large amounts of labeled training data and generalizes very poorly outside the domainarxiv.org해당 논문을 보고 작성했습니다. Abstractkeyphras.. 연구실 공부 2024. 9. 10.
[논문] LoCoNet: Long-Short Context Network for Active Speaker Detection https://arxiv.org/abs/2301.08237 LoCoNet: Long-Short Context Network for Active Speaker DetectionActive Speaker Detection (ASD) aims to identify who is speaking in each frame of a video. ASD reasons from audio and visual information from two contexts: long-term intra-speaker context and short-term inter-speaker context. Long-term intra-speaker contextarxiv.org해당 논문을 보고 작성했습니다. AbstractActive Spe.. 연구실 공부 2024. 9. 6.
[논문] Adding Conditional Control to Text-to-Image Diffusion Models https://arxiv.org/abs/2302.05543 Adding Conditional Control to Text-to-Image Diffusion ModelsWe present ControlNet, a neural network architecture to add spatial conditioning controls to large, pretrained text-to-image diffusion models. ControlNet locks the production-ready large diffusion models, and reuses their deep and robust encoding layers prarxiv.org해당 논문을 보고 작성했습니다. Abstract저자들은 large, pr.. 연구실 공부 2024. 9. 3.
[논문] KoSpeech: Open-Source Toolkit for End-to-End Korean Speech Recognition https://arxiv.org/abs/2009.03092 KoSpeech: Open-Source Toolkit for End-to-End Korean Speech RecognitionWe present KoSpeech, an open-source software, which is modular and extensible end-to-end Korean automatic speech recognition (ASR) toolkit based on the deep learning library PyTorch. Several automatic speech recognition open-source toolkits have been releaarxiv.org해당 논문을 보고 작성했습니다. AbstractKoSp.. 연구실 공부 2024. 9. 2.
[논문] Hear The Flow: Optical Flow-Based Self-Supervised Visual Sound Source Localization https://arxiv.org/abs/2211.03019 Hear The Flow: Optical Flow-Based Self-Supervised Visual Sound Source LocalizationLearning to localize the sound source in videos without explicit annotations is a novel area of audio-visual research. Existing work in this area focuses on creating attention maps to capture the correlation between the two modalities to localize the sourcarxiv.org해당 논문을 보고 작성했습니다. .. 연구실 공부 2024. 8. 30.
728x90

티스토리툴바