Attention-based conditioning methods using variable frame rate for style-robust speaker verification
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 with gating, provided statistically significant improvements over the x-vector baseline in 12/23 tasks and was the same as the baseline in 11/23 tasks when using the UCLA speaker variability database. It also significantly outperformed self-attention without conditioning in 9/23 tasks and was worse in 1/23. The method also showed significant improvements in multi-speaker scenarios of SITW.
Code (0)
등록된 구현이 없습니다.
Tasks
Speaker VerificationText-Independent Speaker VerificationSimilar Papers 제목 키워드 기반
Attention Beats Concatenation for Conditioning Neural Fields
Neural fields model signals by mapping coordinate inputs to sampled values. They are becoming an increasingly important backbone architecture across many fields from vision and graphics to biology and astronomy. In this …
MemorizationConditioning and Processing: Techniques to Improve Information-Theoretic Generalization Bounds
Obtaining generalization bounds for learning algorithms is one of the main subjects studied in theoretical machine learning. In recent years, information-theoretic bounds on generalization have gained the attention of re…
Generalization BoundsConditional Variable Flow Matching: Transforming Conditional Densities with Amortized Conditional Optimal Transport
Forecasting conditional stochastic nonlinear dynamical systems is a fundamental challenge repeatedly encountered across the biological and physical sciences. While flow-based models can impressively predict the temporal …
One Operator for Many Densities: Amortized Approximation of Conditioning by Neural Operators
Probabilistic conditioning is concerned with the identification of a distribution of a random variable $X$ given a random variable $Y$. It is a cornerstone of scientific and engineering applications where modeling uncert…
Bayesian InferenceCausal Inference with Conditional Instruments using Deep Generative Models
The instrumental variable (IV) approach is a widely used way to estimate the causal effects of a treatment on an outcome of interest from observational data with latent confounders. A standard IV is expected to be relate…
Causal Inference