A Robust Hybrid Neural Network Architecture for Blind Source Separation of Speech Signals Exploiting Deep Learning

Abstract

In the contemporary era, blind source separation has emerged as a highly appealing and significant research topic within the field of signal processing. The imperative for the integration of blind source separation techniques within the context of beyond fifth-generation and sixth-generation networks arises from the increasing demand for reliable and efficient communication systems that can effectively handle the challenges posed by high-density networks, dynamic interference environments, and the coexistence of diverse signal sources, thereby enabling enhanced signal extraction and separation for improved system performance. Particularly, audio processing presents a critical domain where the challenge lies in effectively handling files containing a mixture of human speech, silence, and music. Addressing this challenge, speech separation systems can be regarded as a specialized form of human speech recognition or audio signal classification systems that are leveraged to separate, identify, or delineate segments of audio signals encompassing human speech. In various applications such as volume reduction, quality enhancement, detection, and identification, the need arises to separate human speech by eliminating silence, music, or environmental noise from the audio signals. Consequently, the development of robust methods for accurate and efficient speech separation holds paramount importance in optimizing audio signal processing tasks. This study proposes a novel three-way neural network architecture that incorporates transfer learning, a pre-trained dual-path recurrent neural network, and a transformer. In addition to learning the time series associated with audio signals, this network possesses the unique capability of direct context-awareness for modeling the speech sequence within the transformer framework. A comprehensive array of simulations is meticulously conducted to evaluate the performance of the proposed model, which is benchmarked with seven prominent state-of-the-art deep learning-based architectures. The results obtained from these evaluations demonstrate notable advancements in multiple objective metrics. Specifically, our proposed solution showcases an average improvement of 4.60% in terms of short-time objective intelligibility, 14.84% in source-to-distortion ratio, and 9.87% in scale-invariant signal-to-noise ratio. These extraordinary advancements surpass those achieved by the nearest rival, namely the dual-path recurrent neural network time-domain audio separation network, firmly establishing the superiority of our proposed model's performance.

Enhancing Emergency Vehicle Detection: A Deep Learning Approach with Multimodal Fusion

“…In our investigative analysis, we seamlessly integrated the HPSS (Harmonic-Percussive Source Separation) algorithm [29] for input Log-Mel spectrogram processing. This method enabled us to efficiently divide the spectrograms into two fundamental constituents: harmonic spectrograms and percussive spectrograms.…”

Advances in Time-Frequency Analysis for Blind Source Separation: Challenges, Contributions, and Emerging Trends

“…N t , x ( ) M t represents the source signal and observation signal, respectively, n ( ) M t represents the interference signal in the transmission channel, ŝ ( ) N t represents the estimated source signal, N is the number of source signals, and M is the number of mixing channels. Variations in mixing modes, the number of mixing channels, and the relationships between the number of sources lead to different blind source systems, each requiring distinct research approaches [12]. Below, we will introduce them separately:…”

“…To analyze the impact of different TFA methods on the accuracy of mixed matrix estimation, this paper employs the Normalized Mean Square Error (NMSE) to evaluate the estimation accuracy of the mixed matrix. The mathematical expression for NMSE is provided as follows [12]:…”

“…and ̂ represent the values of the true source mixing matrix and the estimated mixing matrix, respectively. Equation (12) illustrates that NMSE changes with the deviation of the estimated mixing matrix values. The greater the deviation, the higher the NMSE, indicating better estimation accuracy of the measurement mixing matrix, resulting in a smaller NMSE value.…”

Underwater Acoustic Nonlinear Blind Ship Noise Separation Using Recurrent Attention Neural Networks

“…In particular, the Transformer is widely used in BSS for mixing signals. For example, [44] proposes a three-way architecture that incorporates a pre-trained dual-path recurrent neural network and Transformer. A Transformer network-based planewave domain masking approach is utilized to retrieve the reverberant ambisonic signals from a multichannel recording in [45].…”