본문 바로가기

연구실 공부

[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.
[논문] MaskCycleGAN-VC: Learning Non-parallel Voice Conversion with Filling in Frames https://arxiv.org/abs/2102.12841 Mask CycleGAN: Unpaired Multi-modal Domain Translation with Interpretable Latent VariableWe propose Mask CycleGAN, a novel architecture for unpaired image domain translation built based on CycleGAN, with an aim to address two issues: 1) unimodality in image translation and 2) lack of interpretability of latent variables. Our innovation in thearxiv.org해당 논문을 보고 작성.. 연구실 공부 2024. 12. 27.
[논문] GESPER: A Unified Framework for General Speech Restoration https://ieeexplore.ieee.org/abstract/document/10095557 Gesper: A Unified Framework for General Speech RestorationThis paper describes the legends-tencent team’s real-time General Speech Restoration (Gesper) system submitted to the ICASSP 2023 Speech Signal Improvement (SSI) Challenge. This newly proposed system is a two-stage architecture, in which the speech restoieeexplore.ieee.org해당 논문을 보고 작성.. 연구실 공부 2024. 12. 26.
[논문] SelfRemaster: Self-Supervised Speech Restoration with Analysis-by-Synthesis Approach Using Channel Modeling https://arxiv.org/abs/2203.12937 SelfRemaster: Self-Supervised Speech Restoration with Analysis-by-Synthesis Approach Using Channel ModelingWe present a self-supervised speech restoration method without paired speech corpora. Because the previous general speech restoration method uses artificial paired data created by applying various distortions to high-quality speech corpora, it cannot suffiar.. 연구실 공부 2024. 12. 24.
[논문] Seen and Unseen Emotional Style Transfer for Voice Conversion with a New Emotional Speech Dataset https://arxiv.org/abs/2010.14794 Seen and Unseen emotional style transfer for voice conversion with a new emotional speech datasetEmotional voice conversion aims to transform emotional prosody in speech while preserving the linguistic content and speaker identity. Prior studies show that it is possible to disentangle emotional prosody using an encoder-decoder network conditioned on darxiv.org해당 .. 연구실 공부 2024. 12. 20.
[논문] Converting Anyone's Voice: End-to-End Expressive Voice Conversion with a Conditional Diffusion Model https://arxiv.org/abs/2405.01730 Converting Anyone's Voice: End-to-End Expressive Voice Conversion with a Conditional Diffusion ModelExpressive voice conversion (VC) conducts speaker identity conversion for emotional speakers by jointly converting speaker identity and emotional style. Emotional style modeling for arbitrary speakers in expressive VC has not been extensively explored. Prearxiv.org.. 연구실 공부 2024. 12. 18.
[논문] Towards Realistic Emotional Voice Conversion using Controllable Emotional Intensity https://arxiv.org/abs/2407.14800 Towards Realistic Emotional Voice Conversion using Controllable Emotional IntensityRealistic emotional voice conversion (EVC) aims to enhance emotional diversity of converted audios, making the synthesized voices more authentic and natural. To this end, we propose Emotional Intensity-aware Network (EINet), dynamically adjusting intonatioarxiv.org해당 논문을 보고 작성했습니다... 연구실 공부 2024. 12. 17.
[논문] VoiceMixer: Adversarial Voice Style Mixup https://proceedings.neurips.cc/paper/2021/hash/0266e33d3f546cb5436a10798e657d97-Abstract.html VoiceMixer: Adversarial Voice Style MixupRequests for name changes in the electronic proceedings will be accepted with no questions asked. However name changes may cause bibliographic tracking issues. Authors are asked to consider this carefully and discuss it with their co-authors prior to requeproceed.. 연구실 공부 2024. 12. 16.
728x90

티스토리툴바