본문 바로가기

연구실 공부

[논문] Learning Arousal-Valence Representation From Categorical Emotion Labels of Speech https://ieeexplore.ieee.org/document/10445890 Learning Arousal-Valence Representation from Categorical Emotion Labels of SpeechDimensional representations of speech emotions such as the arousal-valence (AV) representation provide a continuous and fine-grained description and control than their categorical counterparts. They have wide applications in tasks such as dynamic emotion uieeexplore.ieee.. 연구실 공부 2025. 1. 19.
[논문] StethoSpeech: Speech Generation Through a Clinical Stethoscope Attached to the Skin https://dl.acm.org/doi/10.1145/3678515 StethoSpeech: Speech Generation Through a Clinical Stethoscope Attached to the Skin | Proceedings of the ACM on Interactive, MobWe introduce StethoSpeech, a silent speech interface that transforms flesh-conducted vibrations behind the ear into speech. This innovation is designed to improve social interactions for those with voice disorders, and furthermore .. 연구실 공부 2025. 1. 16.
[논문] Speech Resynthesis from Discrete Disentangled Self-Supervised Representations https://arxiv.org/abs/2104.00355 Speech Resynthesis from Discrete Disentangled Self-Supervised RepresentationsWe propose using self-supervised discrete representations for the task of speech resynthesis. To generate disentangled representation, we separately extract low-bitrate representations for speech content, prosodic information, and speaker identity. This alarxiv.org해당 논문을 보고 작성했습니다. Abstr.. 연구실 공부 2025. 1. 15.
[논문] Recovering Implicit Pitch Contours from Formants in Whispered Speech https://arxiv.org/abs/2307.03168 Recovering implicit pitch contours from formants in whispered speechWhispered speech is characterised by a noise-like excitation that results in the lack of fundamental frequency. Considering that prosodic phenomena such as intonation are perceived through f0 variation, the perception of whispered prosody is relatively difarxiv.org해당 논문을 보고 작성했습니다. Abstractwhispe.. 연구실 공부 2025. 1. 8.
[논문] A Fast and Accurate Pitch Estimation Algorithm Based on the Pseudo Wigner-Ville Distribution https://arxiv.org/abs/2210.15272 A Fast and Accurate Pitch Estimation Algorithm Based on the Pseudo Wigner-Ville DistributionEstimation of fundamental frequency (F0) in voiced segments of speech signals, also known as pitch tracking, plays a crucial role in pitch synchronous speech analysis, speech synthesis, and speech manipulation. In this paper, we capitalize on the high timearxiv.org해당 논문을 보.. 연구실 공부 2025. 1. 2.
[논문] CinC-GAN for Effective $F_0$ prediction for Whisper-to-Normal Speech Conversion https://arxiv.org/abs/2008.07788 CinC-GAN for Effective F0 prediction for Whisper-to-Normal Speech ConversionRecently, Generative Adversarial Networks (GAN)-based methods have shown remarkable performance for the Voice Conversion and WHiSPer-to-normal SPeeCH (WHSP2SPCH) conversion. One of the key challenges in WHSP2SPCH conversion is the prediction of fundamentalarxiv.org해당 논문을 보고 작성했습니다. Abstra.. 연구실 공부 2024. 12. 31.
[논문] Analysing Diffusion-based Generative Approaches Versus Discriminative Approaches for Speech Restoration [2211.02397] Analysing Diffusion-based Generative Approaches versus Discriminative Approaches for Speech Restoration Analysing Diffusion-based Generative Approaches versus Discriminative Approaches for Speech RestorationDiffusion-based generative models have had a high impact on the computer vision and speech processing communities these past years. Besides data generation tasks, they have also .. 연구실 공부 2024. 12. 30.
[논문] Self-Supervised Learning for Speech Enhancement Through Synthesis https://arxiv.org/abs/2211.02542 Self-Supervised Learning for Speech Enhancement through SynthesisModern speech enhancement (SE) networks typically implement noise suppression through time-frequency masking, latent representation masking, or discriminative signal prediction. In contrast, some recent works explore SE via generative speech synthesis, whearxiv.org해당 논문을 보고 작성했습니다. Abstract현대 speech.. 연구실 공부 2024. 12. 30.
728x90

티스토리툴바