Related papers: Exploiting Low-dimensional Structures to Enhance D…
Estimating time-frequency domain masks for speech enhancement using deep learning approaches has recently become a popular field of research. In this paper, we propose a mask-based speech enhancement framework by using concatenated…
Conventional deep neural network (DNN)-based speech enhancement (SE) approaches aim to minimize the mean square error (MSE) between enhanced speech and clean reference. The MSE-optimized model may not directly improve the performance of an…
The current dominant approach for neural speech enhancement is based on supervised learning by using simulated training data. The trained models, however, often exhibit limited generalizability to real-recorded data. To address this, this…
Identifying the structural priors that enable Deep Neural Networks (DNNs) to overcome the curse of dimensionality is a fundamental challenge in machine learning theory. Existing literature suggests that effective high-dimensional learning…
This paper proposes novel algorithms for speaker embedding using subjective inter-speaker similarity based on deep neural networks (DNNs). Although conventional DNN-based speaker embedding such as a $d$-vector can be applied to…
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…
In this work, we investigate the use of embeddings for speaker-adaptive training of DNNs (DNN-SAT) focusing on a small amount of adaptation data per speaker. DNN-SAT can be viewed as learning a mapping from each embedding to transformation…
As for the humanoid robots, the internal noise, which is generated by motors, fans and mechanical components when the robot is moving or shaking its body, severely degrades the performance of the speech recognition accuracy. In this paper,…
Deep neural networks (DNNs) usually contain massive parameters, but there is redundancy such that it is guessed that the DNNs could be trained in low-dimensional subspaces. In this paper, we propose a Dynamic Linear Dimensionality Reduction…
A speaker cluster-based speaker adaptive training (SAT) method under deep neural network-hidden Markov model (DNN-HMM) framework is presented in this paper. During training, speakers that are acoustically adjacent to each other are…
A significant performance reduction is often observed in speech recognition when the rate of speech (ROS) is too low or too high. Most of present approaches to addressing the ROS variation focus on the change of speech signals in dynamic…
Ability of deep networks to extract high level features and of recurrent networks to perform time-series inference have been studied. In view of universality of one hidden layer network at approximating functions under weak constraints, the…
Data hiding is essential for secure communication across digital media, and recent advances in Deep Neural Networks (DNNs) provide enhanced methods for embedding secret information effectively. However, previous audio hiding methods often…
Speakers tend to engage in adaptive behavior, known as entrainment, when they become similar to their interlocutor in various aspects of speaking. We present an unsupervised deep learning framework that derives meaningful representation…
Neural network based approaches for sentence relation modeling automatically generate hidden matching features from raw sentence pairs. However, the quality of matching feature representation may not be satisfied due to complex semantic…
With the development of deep learning, many different network architectures have been explored in speaker verification. However, most network architectures rely on a single deep learning architecture, and hybrid networks combining different…
A deep neural network (DNN)-based speech enhancement (SE) aiming to maximize the performance of an automatic speech recognition (ASR) system is proposed in this paper. In order to optimize the DNN-based SE model in terms of the character…
Trans-dimensional random field language models (TRF LMs) where sentences are modeled as a collection of random fields, have shown close performance with LSTM LMs in speech recognition and are computationally more efficient in inference.…
Overparametrized Deep Neural Networks (DNNs) have demonstrated remarkable success in a wide variety of domains too high-dimensional for classical shallow networks subject to the curse of dimensionality. However, open questions about…
Large neural networks are typically trained for a fixed computational budget, creating a rigid trade-off between performance and efficiency that is ill-suited for deployment in resource-constrained or dynamic environments. Existing…