End-to-End Video-To-Speech Synthesis using Generative Adversarial Networks
원문 초록
Video-to-speech is the process of reconstructing the audio speech from a video of a spoken utterance. Previous approaches to this task have relied on a two-step process where an intermediate representation is inferred from the video, and is then decoded into waveform audio using a vocoder or a waveform reconstruction algorithm. In this work, we propose a new end-to-end video-to-speech model based on Generative Adversarial Networks (GANs) which translates spoken video to waveform end-to-end without using any intermediate representation or separate waveform synthesis algorithm. Our model consists of an encoder-decoder architecture that receives raw video as input and generates speech, which is then fed to a waveform critic and a power critic. The use of an adversarial loss based on these two critics enables the direct synthesis of raw audio waveform and ensures its realism. In addition, the use of our three comparative losses helps establish direct correspondence between the generated audio and the input video. We show that this model is able to reconstruct speech with remarkable realism for constrained datasets such as GRID, and that it is the first end-to-end model to produce intelligible speech for LRW (Lip Reading in the Wild), featuring hundreds of speakers recorded entirely `in the wild'. We evaluate the generated samples in two different scenarios -- seen and unseen speakers -- using four objective metrics which measure the quality and intelligibility of artificial speech. We demonstrate that the proposed approach outperforms all previous works in most metrics on GRID and LRW.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Quantitative Analysis of Audio-Visual Tasks: An Information-Theoretic Perspective
생성 AI 시대의 딥페이크 미디어 생성 및 탐지: 서베이와 전망
Deepfake Media Generation and Detection in the Generative AI Era: A Survey and Outlook
딥페이크 생성 및 탐지 기법을 조사하며, 이미지, 동영상, 오디오, 멀티모달 콘텐츠 등 모든 딥페이크 미디어 유형을 다룬다. 다양한 종류의 딥페이크를 식별하고 딥페이크 생성 및 탐지 방법의 분류 체계를 구축하여 주요 방법군을 설명한다. 다음으로, 딥페이크 탐지에 사용되는 데이터셋을 수집하고 가장 널리 사용되는 데이터셋에서 최고 성능의 탐지기에 대한 최신 순위를 제공한다. 또한 분포 외(out-of-distribution) 콘텐츠에 대해 딥페이크 탐지기를 평가하기 위한 새로운 멀티모달 벤치마크를 개발한다. 결과는 최신(state-of-the-art) 탐지기가 이전에 보지 못한 생성기가 만든 딥페이크에 일반화하지 못함을 보여준다. 프로젝트 페이지와 새 벤치마크는 https://github.com/CroitoruAlin/biodeep 에서 확인할 수 있다.
DeepGesture: A conversational gesture synthesis system based on emotions and semantics
RapFlow-TTS: Rapid and High-Fidelity Text-to-Speech with Improved Consistency Flow Matching
InstructTTSEval: Benchmarking Complex Natural-Language Instruction Following in Text-to-Speech Systems
Pushing the Performance of Synthetic Speech Detection with Kolmogorov-Arnold Networks and Self-Supervised Learning Models
토론
이 논문과 연결된 포럼 글이 아직 없습니다.