본문 바로가기

연구실 공부

[논문] An Image is Worth 16x16 Words: Transformer for Image Recognition at Scale https://arxiv.org/abs/2010.11929 An Image is Worth 16x16 Words: Transformers for Image Recognition at ScaleWhile the Transformer architecture has become the de-facto standard for natural language processing tasks, its applications to computer vision remain limited. In vision, attention is either applied in conjunction with convolutional networks, or used to reparxiv.org해당 논문을 보고 작성했습니다. Abstract.. 연구실 공부 2024. 7. 25.
[논문] Big Transfer (BiT): General Visual Representation Learning https://arxiv.org/abs/1912.11370 Big Transfer (BiT): General Visual Representation LearningTransfer of pre-trained representations improves sample efficiency and simplifies hyperparameter tuning when training deep neural networks for vision. We revisit the paradigm of pre-training on large supervised datasets and fine-tuning the model on a targearxiv.org해당 논문을 보고 작성했습니다.  Abstractpre-trained rep.. 연구실 공부 2024. 7. 24.
[논문] Face-Driven Zero-Shot Voice Conversion with Memory-based Face-Voice Alignment https://arxiv.org/abs/2309.09470 Face-Driven Zero-Shot Voice Conversion with Memory-based Face-Voice AlignmentThis paper presents a novel task, zero-shot voice conversion based on face images (zero-shot FaceVC), which aims at converting the voice characteristics of an utterance from any source speaker to a newly coming target speaker, solely relying on a single faarxiv.org해당 논문을 보고 작성했습니다. Abstr.. 연구실 공부 2024. 7. 23.
[논문] FastPitch: Parallel Text-to-Speech with Pitch Prediction https://arxiv.org/abs/2006.06873 FastPitch: Parallel Text-to-speech with Pitch PredictionWe present FastPitch, a fully-parallel text-to-speech model based on FastSpeech, conditioned on fundamental frequency contours. The model predicts pitch contours during inference. By altering these predictions, the generated speech can be more expressive,arxiv.org해당 논문을 보고 작성했습니다. AbstractFastSpeech 기반 fully.. 연구실 공부 2024. 7. 19.
[논문] Conformer: Convolution-augmented Transformer for Speech Recognition https://arxiv.org/abs/2005.08100 Conformer: Convolution-augmented Transformer for Speech RecognitionRecently Transformer and Convolution neural network (CNN) based models have shown promising results in Automatic Speech Recognition (ASR), outperforming Recurrent neural networks (RNNs). Transformer models are good at capturing content-based global interacarxiv.org해당 논문을 보고 작성했습니다. Abstract최근에 Tra.. 연구실 공부 2024. 7. 18.
[논문] VisualTTS: TTS with Accurate Lip-Speech Synchronization for Automatic Voice Over https://arxiv.org/abs/2110.03342 VisualTTS: TTS with Accurate Lip-Speech Synchronization for Automatic Voice OverIn this paper, we formulate a novel task to synthesize speech in sync with a silent pre-recorded video, denoted as automatic voice over (AVO). Unlike traditional speech synthesis, AVO seeks to generate not only human-sounding speech, but also perfect lip-sarxiv.org해당 논문을 보고 작성했습니다. Ab.. 연구실 공부 2024. 7. 16.
[논문] DRSpeech: Degradation-Robust Text-to-Speech Synthesis with Frame-Level and Utterance-Level Acoustic Representation Learning https://arxiv.org/abs/2203.15683 DRSpeech: Degradation-Robust Text-to-Speech Synthesis with Frame-Level and Utterance-Level Acoustic Representation LearningMost text-to-speech (TTS) methods use high-quality speech corpora recorded in a well-designed environment, incurring a high cost for data collection. To solve this problem, existing noise-robust TTS methods are intended to use noisy speech co.. 연구실 공부 2024. 7. 2.
[논문] CLAPSpeech: Learning Prosody from Text Context with Contrastive Language-Audio Pre-training https://arxiv.org/abs/2305.10763 CLAPSpeech: Learning Prosody from Text Context with Contrastive Language-Audio Pre-trainingImproving text representation has attracted much attention to achieve expressive text-to-speech (TTS). However, existing works only implicitly learn the prosody with masked token reconstruction tasks, which leads to low training efficiency and difficulty iarxiv.org해당 논문을 보고.. 연구실 공부 2024. 7. 1.
728x90

티스토리툴바