A Facial Feature and Lip Movement Enhanced Audio-Visual Speech Separation Model

The cocktail party problem can be more effectively addressed by leveraging the speaker's visual and audio information. This paper proposes a method to improve the audio's separation using two visual cues: facial features and lip movement. Firstly, residual connections are introduced in the audio separation module to extract detailed features. Secondly, considering the video stream contains information other than the face, which has a minimal correlation with the audio, an attention mechanism is employed in the face module to focus on crucial information. Then, the loss function considers the audio-visual similarity to take advantage of the relationship between audio and visual completely. Experimental results on the public VoxCeleb2 dataset show that the proposed model significantly enhanced SDR, PSEQ, and STOI, especially 4 dB improvements in SDR.

Improved Swarm Intelligent Blind Source Separation Based on Signal Cross-Correlation

In recent years, separating effective target signals from mixed signals has become a hot and challenging topic in signal research. The SI-BSS (Blind source separation (BSS) based on swarm intelligence (SI) algorithm) has become an effective method for the linear mixture BSS. However, the SI-BSS has the problem of incomplete separation, as not all the signal sources can be separated. An improved algorithm for BSS with SI based on signal cross-correlation (SI-XBSS) is proposed in this paper. Our method created a candidate separation pool that contains more separated signals than the traditional SI-BSS does; it identified the final separated signals by the value of the minimum cross-correlation in the pool. Compared with the traditional SI-BSS, the SI-XBSS was applied in six SI algorithms (Particle Swarm Optimization (PSO), Genetic Algorithm (GA), Differential Evolution (DE), Sine Cosine Algorithm (SCA), Butterfly Optimization Algorithm (BOA), and Crow Search Algorithm (CSA)). The results showed that the SI-XBSS could effectively achieve a higher separation success rate, which was over 35% higher than traditional SI-BSS on average. Moreover, SI-SDR increased by 14.72 on average.

Extracting the Auditory Attention in a Dual-Speaker Scenario From EEG Using a Joint CNN-LSTM Model

Human brain performs remarkably well in segregating a particular speaker from interfering ones in a multispeaker scenario. We can quantitatively evaluate the segregation capability by modeling a relationship between the speech signals present in an auditory scene, and the listener's cortical signals measured using electroencephalography (EEG). This has opened up avenues to integrate neuro-feedback into hearing aids where the device can infer user's attention and enhance the attended speaker. Commonly used algorithms to infer the auditory attention are based on linear systems theory where cues such as speech envelopes are mapped on to the EEG signals. Here, we present a joint convolutional neural network (CNN)—long short-term memory (LSTM) model to infer the auditory attention. Our joint CNN-LSTM model takes the EEG signals and the spectrogram of the multiple speakers as inputs and classifies the attention to one of the speakers. We evaluated the reliability of our network using three different datasets comprising of 61 subjects, where each subject undertook a dual-speaker experiment. The three datasets analyzed corresponded to speech stimuli presented in three different languages namely German, Danish, and Dutch. Using the proposed joint CNN-LSTM model, we obtained a median decoding accuracy of 77.2% at a trial duration of 3 s. Furthermore, we evaluated the amount of sparsity that the model can tolerate by means of magnitude pruning and found a tolerance of up to 50% sparsity without substantial loss of decoding accuracy.

Time-Frequency Masking in the Complex Domain for Speech Dereverberation and Denoising

In real-world situations, speech is masked by both background noise and reverberation, which negatively affect perceptual quality and intelligibility. In this paper, we address monaural speech separation in reverberant and noisy environments. We perform dereverberation and denoising using supervised learning with a deep neural network. Specifically, we enhance the magnitude and phase by performing separation with an estimate of the complex ideal ratio mask. We define the complex ideal ratio mask so that direct speech results after the mask is applied to reverberant and noisy speech. Our approach is evaluated using simulated and real room impulse responses, and with background noises. The proposed approach improves objective speech quality and intelligibility significantly. Evaluations and comparisons show that it outperforms related methods in many reverberant and noisy environments.

Complex Ratio Masking for Monaural Speech Separation

Speech separation systems usually operate on the short-time Fourier transform (STFT) of noisy speech, and enhance only the magnitude spectrum while leaving the phase spectrum unchanged. This is done because there was a belief that the phase spectrum is unimportant for speech enhancement. Recent studies, however, suggest that phase is important for perceptual quality, leading some researchers to consider magnitude and phase spectrum enhancements. We present a supervised monaural speech separation approach that simultaneously enhances the magnitude and phase spectra by operating in the complex domain. Our approach uses a deep neural network to estimate the real and imaginary components of the ideal ratio mask defined in the complex domain. We report separation results for the proposed method and compare them to related systems. The proposed approach improves over other methods when evaluated with several objective metrics, including the perceptual evaluation of speech quality (PESQ), and a listening test where subjects prefer the proposed approach with at least a 69% rate.

On Training Targets for Supervised Speech Separation

Formulation of speech separation as a supervised learning problem has shown considerable promise. In its simplest form, a supervised learning algorithm, typically a deep neural network, is trained to learn a mapping from noisy features to a time-frequency representation of the target of interest. Traditionally, the ideal binary mask (IBM) is used as the target because of its simplicity and large speech intelligibility gains. The supervised learning framework, however, is not restricted to the use of binary targets. In this study, we evaluate and compare separation results by using different training targets, including the IBM, the target binary mask, the ideal ratio mask (IRM), the short-time Fourier transform spectral magnitude and its corresponding mask (FFT-MASK), and the Gammatone frequency power spectrum. Our results in various test conditions reveal that the two ratio mask targets, the IRM and the FFT-MASK, outperform the other targets in terms of objective intelligibility and quality metrics. In addition, we find that masking based targets, in general, are significantly better than spectral envelope based targets. We also present comparisons with recent methods in non-negative matrix factorization and speech enhancement, which show clear performance advantages of supervised speech separation.

A NEW MASK-BASED OBJECTIVE MEASURE FOR PREDICTING THE INTELLIGIBILITY OF BINARY MASKED SPEECH

Mask-based objective speech-intelligibility measures have been successfully proposed for evaluating the performance of binary masking algorithms. These objective measures were computed directly by comparing the estimated binary mask against the ground truth ideal binary mask (IdBM). Most of these objective measures, however, assign equal weight to all time-frequency (T-F) units. In this study, we propose to improve the existing mask-based objective measures by weighting each T-F unit according to its target or masker loudness. The proposed objective measure shows significantly better performance than two other existing mask-based objective measures.