State-of-the-art Embeddings With Video-free Segmentation Of The Source Voxceleb Data

Abstract

In this paper, we refine and validate our method for training speaker embedding extractors using weak annotations. More specifically, we use only the audio stream of the source VoxCeleb videos and the names of the celebrities without knowing the time intervals in which they appear in the recording. We experiment with hyperparameters and embedding extractors based on ResNet and WavLM. We show that the method achieves state-of-the-art results in speaker verification, comparable with training the extractors in a standard supervised way on the VoxCeleb dataset. We also extend it by considering segments belonging to unknown speakers appearing alongside the celebrities, which are typically discarded. Removing the need for speaker timestamps and multimodal alignment, our method unlocks the use of large-scale weakly labeled speech data, enabling direct training of state-of-the-art embedding extractors and offering a visual-free alternative to VoxCeleb-style dataset creation.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keybarahona2024state

Related papers

• Training Speaker Embedding Extractors Using Multi-speaker Audio With Unknown Speaker Boundaries (2022)3.58
• Delving Into Voxceleb: Environment Invariant Speaker Recognition (2019)10.35
• Voxceleb: A Large-scale Speaker Identification Dataset (2017)23.55
• Unified Hypersphere Embedding For Speaker Recognition (2018)0.00
• The Ins And Outs Of Speaker Recognition: Lessons From Voxsrc 2020 (2020)11.85
• Voxceleb2: Deep Speaker Recognition (2018)23.96
• Voxceleb-esp: Preliminary Experiments Detecting Spanish Celebrities From Their Voices (2023)0.00
• A Comparative Re-assessment Of Feature Extractors For Deep Speaker Embeddings (2020)8.09