Study On The Temporal Pooling Used In Deep Neural Networks For Speaker Verification

Abstract

The x-vector architecture has recently achieved state-of-the-art results on the speaker verification task. This architecture incorporates a central layer, referred to as temporal pooling, which stacks statistical parameters of the acoustic frame distribution. This work proposes to highlight the significant effect of the temporal pooling content on the training dynamics and task performance. An evaluation with different pooling layers is conducted, that is, including different statistical measures of central tendency. Notably, 3rd and 4th moment-based statistics (skewness and kurtosis) are also tested to complete the usual mean and standard-deviation parameters. Our experiments show the influence of the pooling layer content in terms of speaker verification performance, but also for several classification tasks (speaker, channel or text related), and allow to better reveal the presence of external information to the speaker identity depending on the layer content.

Stats

• citations5
• S2 citations—
• github stars0
• HF likes0
• heat score5.84
• arxiv keyrouvier2021study

Related papers

• Exploring A Unified Attention-based Pooling Framework For Speaker Verification (2018)6.77
• Deep Speaker Embedding Learning With Multi-level Pooling For Text-independent Speaker Verification (2019)0.00
• An Improved Deep Neural Network For Modeling Speaker Characteristics At Different Temporal Scales (2020)6.34
• Speechnas: Towards Better Trade-off Between Latency And Accuracy For Large-scale Speaker Verification (2021)9.76
• Attentive Statistics Pooling For Deep Speaker Embedding (2018)18.88
• Deep Neural Network Embeddings With Gating Mechanisms For Text-independent Speaker Verification (2019)8.82
• Double Multi-head Attention For Speaker Verification (2020)8.09
• ECAPA-TDNN: Emphasized Channel Attention, Propagation And Aggregation In TDNN Based Speaker Verification (2020)23.07