본문 바로가기

연구실 공부

[논문] Imaginary Voice: Face-Styled Diffusion Model for Text-to-Speech https://arxiv.org/abs/2302.13700 Imaginary Voice: Face-styled Diffusion Model for Text-to-Speech The goal of this work is zero-shot text-to-speech synthesis, with speaking styles and voices learnt from facial characteristics. Inspired by the natural fact that people can imagine the voice of someone when they look at his or her face, we introduce a fac arxiv.org 해당 논문을 보고 작성했습니다. Abstract 이 논문에서는.. 연구실 공부 2024. 4. 22.
[논문] Improving Medical Speech-to-Text Accuracy with Vision-Language Pre-training Model https://arxiv.org/abs/2303.00091 Improving Medical Speech-to-Text Accuracy with Vision-Language Pre-training Model Automatic Speech Recognition (ASR) is a technology that converts spoken words into text, facilitating interaction between humans and machines. One of the most common applications of ASR is Speech-To-Text (STT) technology, which simplifies user workflows by arxiv.org 해당 논문을 보고 작성했습니다.. 연구실 공부 2024. 4. 16.
[논문] Robust Speech Recognition via Large-Scale Weak Supervision https://arxiv.org/abs/2212.04356 Robust Speech Recognition via Large-Scale Weak Supervision We study the capabilities of speech processing systems trained simply to predict large amounts of transcripts of audio on the internet. When scaled to 680,000 hours of multilingual and multitask supervision, the resulting models generalize well to standard arxiv.org 해당 논문을 보고 작성했습니다. Abstract 저자들은 interne.. 연구실 공부 2024. 4. 14.
[논문] End-to-End Adversarial Text-to-Speech https://arxiv.org/abs/2006.03575 End-to-End Adversarial Text-to-Speech Modern text-to-speech synthesis pipelines typically involve multiple processing stages, each of which is designed or learnt independently from the rest. In this work, we take on the challenging task of learning to synthesise speech from normalised text or arxiv.org 해당 논문을 보고 작성했습니다. Abstract 현대 text-to-speech synthesis piplin.. 연구실 공부 2024. 4. 8.
[논문] FastSpeech: Fast, Robust and Controllable Text to Speech https://arxiv.org/abs/1905.09263 FastSpeech: Fast, Robust and Controllable Text to Speech Neural network based end-to-end text to speech (TTS) has significantly improved the quality of synthesized speech. Prominent methods (e.g., Tacotron 2) usually first generate mel-spectrogram from text, and then synthesize speech from the mel-spectrogram us arxiv.org 해당 논문을 보고 작성했습니다. Abstract Neural network.. 연구실 공부 2024. 4. 5.
[논문] Char2Wav: End-to-End Speech Synthesis https://openreview.net/forum?id=B1VWyySKx Char2Wav: End-to-End Speech Synthesis Unlike traditional models for speech synthesis, Char2Wav learns to produce audio directly from text. openreview.net 해당 논문을 보고 작성했습니다. Abstract 저자들은 end-to-end speech synthesis model인 Char2Wav을 제안합니다. Char2Wav는 2가지 component로 이루어집니다: 'reader' & 'neural vocoder'. reader는 encoder-decoder model with attention입니다. encoder.. 연구실 공부 2024. 4. 4.
[논문] TACOTRON: Towards End-to-End Speech Synthesis https://arxiv.org/abs/1703.10135 Tacotron: Towards End-to-End Speech Synthesis A text-to-speech synthesis system typically consists of multiple stages, such as a text analysis frontend, an acoustic model and an audio synthesis module. Building these components often requires extensive domain expertise and may contain brittle design c arxiv.org 해당 논문을 보고 작성했습니다. Abstract text-to-speech synthesis .. 연구실 공부 2024. 4. 3.
Text-to-Speech (TTS) 정리 STT는 발화된 대화를 text로 변환하는 기능을 제공하는 반면, TTS는 쓰어진 text를 natural-sounding speech로 생성할 수 있습니다. STT와 TTS 인식 기술은 사람들이 computer 및 digital device와 interact하는 방식을 변화시켰습니다. TTS와 STT는 번역 서비스, 가상 비서 등 다양한 domain에서 사용되고 있습니다. STT와 TTS 인식 기술의 발전은 대규모 dataset, deep learning 기술 발전, computational power 향상 덕분에 이루어졌으며, system의 정확성, 자연스러움, 사용성이 크게 증가되었습니다. Text-to-Speech Conversion Text-to-Speech (TTS) 인식, 또는 speech .. 연구실 공부 2024. 4. 1.
728x90

티스토리툴바