Attention-based Conditioning Methods Using Variable Frame Rate For Style-robust Speaker Verification

Abstract

We propose an approach to extract speaker embeddings that are robust to speaking style variations in text-independent speaker verification. Typically, speaker embedding extraction includes training a DNN for speaker classification and using the bottleneck features as speaker representations. Such a network has a pooling layer to transform frame-level to utterance-level features by calculating statistics over all utterance frames, with equal weighting. However, self-attentive embeddings perform weighted pooling such that the weights correspond to the importance of the frames in a speaker classification task. Entropy can capture acoustic variability due to speaking style variations. Hence, an entropy-based variable frame rate vector is proposed as an external conditioning vector for the self-attention layer to provide the network with information that can address style effects. This work explores five different approaches to conditioning. The best conditioning approach, concatenation wit

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keyafshan2022attention

Related papers

• Variable Frame Rate-based Data Augmentation To Handle Speaking-style Variability For Automatic Speaker Verification (2020)3.58
• End-to-end Attention Based Text-dependent Speaker Verification (2017)14.87
• Attentive Statistics Pooling For Deep Speaker Embedding (2018)18.88
• Rethinking Session Variability: Leveraging Session Embeddings For Session Robustness In Speaker Verification (2023)5.24
• Disentangled Speaker And Nuisance Attribute Embedding For Robust Speaker Verification (2020)8.60
• Deep Representation Decomposition For Rate-invariant Speaker Verification (2022)2.26
• Deep Segment Attentive Embedding For Duration Robust Speaker Verification (2018)2.26
• Self Multi-head Attention For Speaker Recognition (2019)13.84