MAVFlow: Preserving Paralinguistic Elements with Conditional Flow Matching for Zero-Shot AV2AV Multilingual Translation

• URL: http://arxiv.org/abs/2503.11026v1
• Date: Fri, 14 Mar 2025 02:48:43 GMT
• Title: MAVFlow: Preserving Paralinguistic Elements with Conditional Flow Matching for Zero-Shot AV2AV Multilingual Translation
• Authors: Sungwoo Cho, Jeongsoo Choi, Sungnyun Kim, Se-Young Yun,
• Abstract summary: We propose a conditional flow matching (CFM) model for zero-shot audio-visual translation.<n>By leveraging multi-modal guidance with CFM, our model robustly preserves speaker-specific characteristics.<n>We empirically demonstrate the inclusion of high-quality mel-spectrograms conditioned on facial information.
• Score: 23.892686638994043
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite recent advances in text-to-speech (TTS) models, audio-visual to audio-visual (AV2AV) translation still faces a critical challenge: maintaining speaker consistency between the original and translated vocal and facial features. To address this issue, we propose a conditional flow matching (CFM) zero-shot audio-visual renderer that utilizes strong dual guidance from both audio and visual modalities. By leveraging multi-modal guidance with CFM, our model robustly preserves speaker-specific characteristics and significantly enhances zero-shot AV2AV translation abilities. For the audio modality, we enhance the CFM process by integrating robust speaker embeddings with x-vectors, which serve to bolster speaker consistency. Additionally, we convey emotional nuances to the face rendering module. The guidance provided by both audio and visual cues remains independent of semantic or linguistic content, allowing our renderer to effectively handle zero-shot translation tasks for monolingual speakers in different languages. We empirically demonstrate that the inclusion of high-quality mel-spectrograms conditioned on facial information not only enhances the quality of the synthesized speech but also positively influences facial generation, leading to overall performance improvements.

Related papers

• CTEFM-VC: Zero-Shot Voice Conversion Based on Content-Aware Timbre Ensemble Modeling and Flow Matching [7.144608815694702]
  CTEFM-VC is a framework that disentangles utterances into linguistic content and timbre representations. To enhance its timbre modeling capability and the naturalness of generated speech, we propose a context-aware timbre ensemble modeling approach.
  arXiv  Detail & Related papers  (2024-11-04T12:23:17Z)
• Seeing Your Speech Style: A Novel Zero-Shot Identity-Disentanglement Face-based Voice Conversion [5.483488375189695]
  Face-based Voice Conversion (FVC) is a novel task that leverages facial images to generate the target speaker's voice style. Previous work has two shortcomings: (1) suffering from obtaining facial embeddings that are well-aligned with the speaker's voice identity information, and (2) inadequacy in decoupling content and speaker identity information from the audio input. We present a novel FVC method, Identity-Disentanglement Face-based Voice Conversion (ID-FaceVC), which overcomes the above two limitations.
  arXiv  Detail & Related papers  (2024-09-01T11:51:18Z)
• TransVIP: Speech to Speech Translation System with Voice and Isochrony Preservation [97.54885207518946]
  We introduce a novel model framework TransVIP that leverages diverse datasets in a cascade fashion. We propose two separated encoders to preserve the speaker's voice characteristics and isochrony from the source speech during the translation process. Our experiments on the French-English language pair demonstrate that our model outperforms the current state-of-the-art speech-to-speech translation model.
  arXiv  Detail & Related papers  (2024-05-28T04:11:37Z)
• Multilingual Audio-Visual Speech Recognition with Hybrid CTC/RNN-T Fast Conformer [59.57249127943914]
  We present a multilingual Audio-Visual Speech Recognition model incorporating several enhancements to improve performance and audio noise robustness. We increase the amount of audio-visual training data for six distinct languages, generating automatic transcriptions of unlabelled multilingual datasets. Our proposed model achieves new state-of-the-art performance on the LRS3 dataset, reaching WER of 0.8%.
  arXiv  Detail & Related papers  (2024-03-14T01:16:32Z)
• AV2AV: Direct Audio-Visual Speech to Audio-Visual Speech Translation with Unified Audio-Visual Speech Representation [58.72068260933836]
  The input and output of the system are multimodal (i.e., audio and visual speech) We can perform real-like conversations with individuals worldwide in a virtual meeting by utilizing our own primary languages. In contrast to Speech-to-Speech Translation (A2A), which solely translates between audio modalities, the proposed AV2AV directly translates between audio-visual speech.
  arXiv  Detail & Related papers  (2023-12-05T05:36:44Z)
• Cooperative Dual Attention for Audio-Visual Speech Enhancement with Facial Cues [80.53407593586411]
  We focus on leveraging facial cues beyond the lip region for robust Audio-Visual Speech Enhancement (AVSE) We propose a Dual Attention Cooperative Framework, DualAVSE, to ignore speech-unrelated information, capture speech-related information with facial cues, and dynamically integrate it with the audio signal for AVSE.
  arXiv  Detail & Related papers  (2023-11-24T04:30:31Z)
• Speech-to-Speech Translation with Discrete-Unit-Based Style Transfer [53.72998363956454]
  Direct speech-to-speech translation (S2ST) with discrete self-supervised representations has achieved remarkable accuracy. The scarcity of high-quality speaker-parallel data poses a challenge for learning style transfer during translation. We design an S2ST pipeline with style-transfer capability on the basis of discrete self-supervised speech representations and timbre units.
  arXiv  Detail & Related papers  (2023-09-14T09:52:08Z)
• LipSound2: Self-Supervised Pre-Training for Lip-to-Speech Reconstruction and Lip Reading [24.744371143092614]
  The aim of this work is to investigate the impact of crossmodal self-supervised pre-training for speech reconstruction (video-to-audio) by leveraging the natural co-occurrence of audio and visual streams in videos. We propose LipSound2, which consists of an encoder-decoder architecture and location-aware attention mechanism to map face image sequences to mel-scale spectrograms.
  arXiv  Detail & Related papers  (2021-12-09T08:11:35Z)
• VQMIVC: Vector Quantization and Mutual Information-Based Unsupervised Speech Representation Disentanglement for One-shot Voice Conversion [54.29557210925752]
  One-shot voice conversion can be effectively achieved by speech representation disentanglement. We employ vector quantization (VQ) for content encoding and introduce mutual information (MI) as the correlation metric during training. Experimental results reflect the superiority of the proposed method in learning effective disentangled speech representations.
  arXiv  Detail & Related papers  (2021-06-18T13:50:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.