paper-with-me

Papers

Attention-based conditioning methods using variable frame rate for style-robust speaker verification

2022-06-28 · Amber Afshan, Abeer Alwan

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.

📄 PDF Abstract BibTeX arXiv:2206.13680

Code (0)

등록된 구현이 없습니다.

Tasks

Speaker VerificationText-Independent Speaker Verification

Similar Papers 제목 키워드 기반

Attention Beats Concatenation for Conditioning Neural Fields

2022-09-21 · Daniel Rebain, Mark J. Matthews, Kwang Moo Yi, Gopal Sharma 외

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 …

Memorization

Conditioning and Processing: Techniques to Improve Information-Theoretic Generalization Bounds

2020-12-01 · NeurIPS 2020 12 · Hassan Hafez-Kolahi, Zeinab Golgooni, Shohreh Kasaei, Mahdieh Soleymani

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 Bounds

Conditional Variable Flow Matching: Transforming Conditional Densities with Amortized Conditional Optimal Transport

2024-11-13 · Adam P. Generale, Andreas E. Robertson, Surya R. Kalidindi

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

2026-05-07 · Panos Tsimpos, Edoardo Calvello, Ayoub Belhadji, Nicholas H. Nelsen arxiv

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 Inference

Causal Inference with Conditional Instruments using Deep Generative Models

2022-11-29 · Debo Cheng, Ziqi Xu, Jiuyong Li, Lin Liu 외

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