paper-with-me

Papers

Audio-Visual Speech Codecs: Rethinking Audio-Visual Speech Enhancement by Re-Synthesis

2022-03-31 · CVPR 2022 1 · Karren Yang, Dejan Markovic, Steven Krenn, Vasu Agrawal, Alexander Richard

Since facial actions such as lip movements contain significant information about speech content, it is not surprising that audio-visual speech enhancement methods are more accurate than their audio-only counterparts. Yet, state-of-the-art approaches still struggle to generate clean, realistic speech without noise artifacts and unnatural distortions in challenging acoustic environments. In this paper, we propose a novel audio-visual speech enhancement framework for high-fidelity telecommunications in AR/VR. Our approach leverages audio-visual speech cues to generate the codes of a neural speech codec, enabling efficient synthesis of clean, realistic speech from noisy signals. Given the importance of speaker-specific cues in speech, we focus on developing personalized models that work well for individual speakers. We demonstrate the efficacy of our approach on a new audio-visual speech dataset collected in an unconstrained, large vocabulary setting, as well as existing audio-visual datasets, outperforming speech enhancement baselines on both quantitative metrics and human evaluation studies. Please see the supplemental video for qualitative results at https://github.com/facebookresearch/facestar/releases/download/paper_materials/video.mp4.

📄 PDF Abstract BibTeX arXiv:2203.17263

Code (1)

facebookresearch/facestar 공식 구현

Tasks

Speech Enhancement

Similar Papers 제목 키워드 기반

Spectral Codecs: Improving Non-Autoregressive Speech Synthesis with Spectrogram-Based Audio Codecs

2024-06-07 · Ryan Langman, Ante Jukić, Kunal Dhawan, Nithin Rao Koluguri 외

Historically, most speech models in machine-learning have used the mel-spectrogram as a speech representation. Recently, discrete audio tokens produced by neural audio codecs have become a popular alternate speech repres…

QuantizationSpeech Synthesistext-to-speechText to Speech

LILAC: An Idempotent Neural Speech Codec

2026-08-06 · June Young Yi, Dongwook Lee, Jiheum Yeom, Sungroh Yoon arxiv

Neural Audio Codecs are widely adopted in speech generation and editing. However, existing neural audio codecs are not idempotent: across the paper's twelve baseline systems, every configuration tested rewrites, on avera…

Audio Codec Augmentation for Robust Collaborative Watermarking of Speech Synthesis

2024-09-20 · Lauri Juvela, Xin Wang

Automatic detection of synthetic speech is becoming increasingly important as current synthesis methods are both near indistinguishable from human speech and widely accessible to the public. Audio watermarking and other …

Face SwappingSpeech Synthesis

How to Label Resynthesized Audio: The Dual Role of Neural Audio Codecs in Audio Deepfake Detection

2026-02-18 · Yixuan Xiao, Florian Lux, Alejandro Pérez-González-de-Martos, Ngoc Thang Vu arxiv

Since Text-to-Speech systems typically don't produce waveforms directly, recent spoof detection studies use resynthesized waveforms from vocoders and neural audio codecs to simulate an attacker. Unlike vocoders, which ar…

Audio Deepfake DetectionSpeech SynthesisSpoof Detection

Bringing Interpretability to Neural Audio Codecs

2025-06-04 · Samir Sadok, Julien Hauret, Éric Bavu

The advent of neural audio codecs has increased in popularity due to their potential for efficiently modeling audio with transformers. Such advanced codecs represent audio from a highly continuous waveform to low-sampled…