paper-with-me

Papers

Training Speaker Embedding Extractors Using Multi-Speaker Audio with Unknown Speaker Boundaries

2022-03-29 · Themos Stafylakis, Ladislav Mošner, Oldřich Plchot, Johan Rohdin, Anna Silnova, Lukáš Burget, Jan "Honza'' Černocký

In this paper, we demonstrate a method for training speaker embedding extractors using weak annotation. More specifically, we are using the full VoxCeleb recordings and the name of the celebrities appearing on each video without knowledge of the time intervals the celebrities appear in the video. We show that by combining a baseline speaker diarization algorithm that requires no training or parameter tuning, a modified loss with aggregation over segments, and a two-stage training approach, we are able to train a competitive ResNet-based embedding extractor. Finally, we experiment with two different aggregation functions and analyze their behaviour in terms of their gradients.

📄 PDF Abstract BibTeX arXiv:2203.15436

Code (0)

등록된 구현이 없습니다.

Tasks

speaker-diarizationSpeaker Diarization

Similar Papers 제목 키워드 기반

In search of strong embedding extractors for speaker diarisation

2022-10-26 · Jee-weon Jung, Hee-Soo Heo, Bong-Jin Lee, Jaesung Huh 외

Speaker embedding extractors (EEs), which map input audio to a speaker discriminant latent space, are of paramount importance in speaker diarisation. However, there are several challenges when adopting EEs for diarisatio…

Data AugmentationSpeaker Verification

State-of-the-art Embeddings with Video-free Segmentation of the Source VoxCeleb Data

2024-10-03 · Sara Barahona, Ladislav Mošner, Themos Stafylakis, Oldřich Plchot 외

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 celebr…

Speaker Verification

Challenging margin-based speaker embedding extractors by using the variational information bottleneck

2024-06-18 · Themos Stafylakis, Anna Silnova, Johan Rohdin, Oldrich Plchot 외

Speaker embedding extractors are typically trained using a classification loss over the training speakers. During the last few years, the standard softmax/cross-entropy loss has been replaced by the margin-based losses, …

Speaker Recognition

Self-supervised speaker embeddings

2019-04-06 · Themos Stafylakis, Johan Rohdin, Oldrich Plchot, Petr Mizera 외

Contrary to i-vectors, speaker embeddings such as x-vectors are incapable of leveraging unlabelled utterances, due to the classification loss over training speakers. In this paper, we explore an alternative training stra…

DecoderGeneral Classification

Mitigating Non-Target Speaker Bias in Guided Speaker Embedding

2025-06-14 · Shota Horiguchi, Takanori Ashihara, Marc Delcroix, Atsushi Ando 외

Obtaining high-quality speaker embeddings in multi-speaker conditions is crucial for many applications. A recently proposed guided speaker embedding framework, which utilizes speech activities of target and non-target sp…

Speaker Verification