Training Speaker Embedding Extractors Using Multi-Speaker Audio with Unknown Speaker Boundaries
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.
Code (0)
등록된 구현이 없습니다.
Tasks
speaker-diarizationSpeaker DiarizationSimilar Papers 제목 키워드 기반
In search of strong embedding extractors for speaker diarisation
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 VerificationState-of-the-art Embeddings with Video-free Segmentation of the Source VoxCeleb Data
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 VerificationChallenging margin-based speaker embedding extractors by using the variational information bottleneck
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 During the last few years, the standard softmax/cross-entropy loss has been replaced by the margin-based losses, …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 RecognitionSelf-supervised speaker embeddings
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 ClassificationMitigating Non-Target Speaker Bias in Guided Speaker Embedding
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