Non-local convolutional neural networks (nlcnn) for speaker recognition

TL;DR

This paper introduces Non-local Convolutional Neural Networks (NLCNN) for speaker recognition, enhancing the capture of global dependencies in voice features to outperform existing methods on public datasets.

Contribution

The work proposes integrating non-local blocks into CNNs to better capture long-range dependencies in speaker voice features, improving recognition accuracy.

Findings

NLCNN outperforms state-of-the-art algorithms on Voxceleb dataset.

Time domain non-local operations are most effective for speaker recognition.

Non-local blocks enhance global feature capturing in CNNs.

Abstract

Speaker recognition is the process of identifying a speaker based on the voice. The technology has attracted more attention with the recent increase in popularity of smart voice assistants, such as Amazon Alexa. In the past few years, various convolutional neural network (CNN) based speaker recognition algorithms have been proposed and achieved satisfactory performance. However, convolutional operations are building blocks that typically perform on a local neighborhood at a time and thus miss to capture global, long-range interactions at the feature level which are critical for understanding the pattern in a speaker's voice. In this work, we propose to apply Non-local Convolutional Neural Networks (NLCNN) to improve the capability of capturing long-range dependencies at the feature level, therefore improving speaker recognition performance. Specifically, we introduce non-local blocks where the output response of a position is computed as a weighted sum of the input features at all positions. Combining non-local blocks with pre-defined CNN networks, we investigate the effectiveness of NLCNN models. Without extensive tuning, the proposed NLCNN models outperform state-of-the-art speaker recognition algorithms on the public Voxceleb dataset. What's more, we investigate different types of non-local operations applied to the frequency-time domain, time domain, frequency domain and frame-level respectively. Among them, time domain is the most effective one for speaker recognition applications.