Related papers: Exploring Gaussian mixture model framework for spe…

Dysarthric speech recognition has posed major challenges due to lack of training data and heavy mismatch in speaker characteristics. Recent ASR systems have benefited from readily available pretrained models such as wav2vec2 to improve the…

Recurrent Neural Network Transducer (RNN-T), like most end-to-end speech recognition model architectures, has an implicit neural network language model (NNLM) and cannot easily leverage unpaired text data during training. Previous work has…

Spectral mapping uses a deep neural network (DNN) to map directly from noisy speech to clean speech. Our previous study found that the performance of spectral mapping improves greatly when using helpful cues from an acoustic model trained…

Multimodal dialogue emotion recognition captures emotional cues by fusing text, visual, and audio modalities. However, existing approaches still suffer from notable limitations in modeling emotional dependencies and learning multimodal…

Deep learning models are widely used for speaker recognition and spoofing speech detection. We propose the GMM-ResNet2 for synthesis speech detection. Compared with the previous GMM-ResNet model, GMM-ResNet2 has four improvements. Firstly,…

Data augmentation has proven to be a promising prospect in improving the performance of deep learning models by adding variability to training data. In previous work with developing a noise robust acoustic-to-articulatory speech inversion…

We present the Deep Convolutional Gaussian Mixture Model (DCGMM), a new probabilistic approach for image modeling capable of density estimation, sampling and tractable inference. DCGMM instances exhibit a CNN-like layered structure, in…

When only limited target domain data is available, domain adaptation could be used to promote performance of deep neural network (DNN) acoustic model by leveraging well-trained source model and target domain data. However, suffering from…

Deep feedforward neural networks (DFNNs) are a powerful tool for functional approximation. We describe flexible versions of generalized linear and generalized linear mixed models incorporating basis functions formed by a DFNN. The…

While machine learning techniques are traditionally resource intensive, we are currently witnessing an increased interest in hardware and energy efficient approaches. This need for resource-efficient machine learning is primarily driven by…

For monaural speech enhancement, contextual information is important for accurate speech estimation. However, commonly used convolution neural networks (CNNs) are weak in capturing temporal contexts since they only build blocks that process…

In this paper, we first present a new variant of Gaussian restricted Boltzmann machine (GRBM) called multivariate Gaussian restricted Boltzmann machine (MGRBM), with its definition and learning algorithm. Then we propose using a learned…

Multi-frame algorithms for single-microphone speech enhancement, e.g., the multi-frame minimum variance distortionless response (MFMVDR) filter, are able to exploit speech correlation across adjacent time frames in the short-time Fourier…

Multi-scale deep neural networks (MscaleDNNs) with downing-scaling mapping have demonstrated superiority over traditional DNNs in approximating target functions characterized by high frequency features. However, the performance of…

This work builds on a previous work on unsupervised speech enhancement using a dynamical variational autoencoder (DVAE) as the clean speech model and non-negative matrix factorization (NMF) as the noise model. We propose to replace the NMF…

We propose an Gaussian Mixture Model (GMM) learning algorithm, based on our previous work of GMM expansion idea. The new algorithm brings more robustness and simplicity than classic Expectation Maximization (EM) algorithm. It also improves…

Training acoustic models with sequentially incoming data -- while both leveraging new data and avoiding the forgetting effect-- is an essential obstacle to achieving human intelligence level in speech recognition. An obvious approach to…

Geometry-aware optimization algorithms, such as Muon, have achieved remarkable success in training deep neural networks (DNNs). These methods leverage the underlying geometry of DNNs by selecting appropriate norms for different layers and…

Deep neural networks (DNNs) for supervised learning can be viewed as a pipeline of a feature extractor (i.e. last hidden layer) and a linear classifier (i.e. output layer) that is trained jointly with stochastic gradient descent (SGD). In…

Recently, a versatile limited feedback scheme based on a Gaussian mixture model (GMM) was proposed for frequency division duplex (FDD) systems. This scheme provides high flexibility regarding various system parameters and is applicable to…