Abstract
Speaker identification is a classification task which aims to identify a subject from a given time-series sequential data. Since the speech signal is a continuous one-dimensional time series, most of the current research methods are based on convolutional neural network (CNN) or recurrent neural network (RNN). Indeed, these methods perform well in many tasks, but there is no attempt to combine these two network models to study the speaker identification task. Due to the spectrogram that a speech signal contains, the spatial features of voiceprint (which corresponds to the voice spectrum) and CNN are effective for spatial feature extraction (which corresponds to modeling spectral correlations in acoustic features). At the same time, the speech signal is in a time series, and deep RNN can better represent long utterances than shallow networks. Considering the advantage of gated recurrent unit (GRU) (compared with traditional RNN) in the segmentation of sequence data, we decide to use stacked GRU layers in our model for frame-level feature extraction. In this paper, we propose a deep neural network (DNN) model based on a two-dimensional convolutional neural network (2-D CNN) and gated recurrent unit (GRU) for speaker identification. In the network model design, the convolutional layer is used for voiceprint feature extraction and reduces dimensionality in both the time and frequency domains, allowing for faster GRU layer computation. In addition, the stacked GRU recurrent network layers can learn a speaker’s acoustic features. During this research, we tried to use various neural network structures, including 2-D CNN, deep RNN, and deep LSTM. The above network models were evaluated on the Aishell-1 speech dataset. The experimental results showed that our proposed DNN model, which we call deep GRU, achieved a high recognition accuracy of 98.96%. At the same time, the results also demonstrate the effectiveness of the proposed deep GRU network model versus other models for speaker identification. Through further optimization, this method could be applied to other research similar to the study of speaker identification.
Highlights
Speaker recognition [1] is an important bio-feature recognition method
In order to speed up the training procedure, our proposed network schemes are implemented using TensorFlow deep learning library written in Python, which can be executed on a graphics processing unit (GPU)
To visualize the learning efficiency of the models, one training progress of the proposed deep gated recurrent unit (GRU) network model with the Aishell-1 dataset is shown in Figure 8, where the left block presents loss vs. training epochs and the right part represents the accuracy vs. training epochs
Summary
Speaker recognition [1] is an important bio-feature recognition method. It is the task of recognizing the identity of someone based on the speaker’s speech signal. Due to the unique characteristics of speech signal, speaker recognition has drawn increasing attention from researchers in broad fields of information security for many years. Speaker recognition study can be considered as the use of employing statistical methods to identify the individuals based on their unique acoustic properties, which are encoded in a sequence of successive samples in time. Speaker recognition can be divided into two modes: Speaker verification and speaker identification [2,3,4]. We mainly conduct research on speaker identification
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
