Sum-Product Networks for Robust Automatic Speaker Recognition

10/26/2019
by   Aaron Nicolson, et al.
0

The performance of a speaker recognition system degrades considerably in the presence of noise. One approach to significantly increase robustness is to use the marginal probability density function of the spectral features that reliably represent speech. Current state-of-the-art speaker recognition systems employ non-probabilistic models, such as convolutional neural networks (CNNs), which cannot use marginalisation. As an alternative, we propose the use of sum-product networks (SPNs), a deep probabilistic graphical model which is compatible with marginalisation. SPN speaker models are evaluated here on real-world non-stationary and coloured noise sources at multiple SNR levels. In terms of speaker recognition accuracy, SPN speaker models employing marginalisation are more robust than recent CNN-based speaker recognition systems that pre-process the noisy speech. Additionally, the SPN speaker models consist of significantly fewer parameters than that of the CNN-based speaker recognition systems. The results presented in this work show that SPN speaker models are a robust, parameter-efficient alternative for speaker recognition. Availability: The SPN speaker recognition system is available at: https://github.com/anicolson/SPN-Spk-Rec

READ FULL TEXT
research
02/24/2023

Multi-task learning of speech and speaker recognition

We study multi-task learning for two orthogonal speech technology tasks:...
research
04/05/2022

What can predictive speech coders learn from speaker recognizers?

This paper compares the speech coder and speaker recognizer applications...
research
04/08/2022

Reliable Visualization for Deep Speaker Recognition

In spite of the impressive success of convolutional neural networks (CNN...
research
02/23/2022

State-of-the-art in speaker recognition

Recent advances in speech technologies have produced new tools that can ...
research
03/28/2022

Training speaker recognition systems with limited data

This work considers training neural networks for speaker recognition wit...
research
05/07/2020

AutoSpeech: Neural Architecture Search for Speaker Recognition

Speaker recognition systems based on Convolutional Neural Networks (CNNs...
research
06/29/2020

Data augmentation versus noise compensation for x- vector speaker recognition systems in noisy environments

The explosion of available speech data and new speaker modeling methods ...

Please sign up or login with your details

Forgot password? Click here to reset