Analyzing speaker verification embedding extractors and back-ends under language and channel mismatch
In this paper, we analyze the behavior and performance of speaker embeddings and the back-end scoring model under domain and language mismatch. We present our findings regarding ResNet-based speaker embedding architectures and show that reduced temporal stride yields improved performance. We then consider a PLDA back-end and show how a combination of small speaker subspace, language-dependent PLDA mixture, and nuisance-attribute projection can have a drastic impact on the performance of the system. Besides, we present an efficient way of scoring and fusing class posterior logit vectors recently shown to perform well for speaker verification task. The experiments are performed using the NIST SRE 2021 setup.
Code (0)
등록된 구현이 없습니다.
Tasks
AttributeSpeaker VerificationSimilar 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 VerificationGraph Attention Networks for Speaker Verification
This work presents a novel back-end framework for speaker verification using graph attention networks. Segment-wise speaker embeddings extracted from multiple crops within an utterance are interpreted as node representat…
Graph AttentionSpeaker 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 VerificationMemory-Efficient Training for Deep Speaker Embedding Learning in Speaker Verification
Recent speaker verification (SV) systems have shown a trend toward adopting deeper speaker embedding extractors. Although deeper and larger neural networks can significantly improve performance, their substantial memory …
GPUQuantizationSpeaker VerificationA Comparative Re-Assessment of Feature Extractors for Deep Speaker Embeddings
Modern automatic speaker verification relies largely on deep neural networks (DNNs) trained on mel-frequency cepstral coefficient (MFCC) features. While there are alternative feature extraction methods based on phase, pr…
Speaker Verification