Related papers: Invertible DNN-based nonlinear time-frequency tran…
Enhancing noisy speech is an important task to restore its quality and to improve its intelligibility. In traditional non-machine-learning (ML) based approaches the parameters required for noise reduction are estimated blindly from the…
For the purpose of effective suppression of the cycle-skipping phenomenon in full waveform inversion (FWI), we developed a Deep Neural Network (DNN) approach to predict the absent low-frequency components by exploiting the implicit relation…
This paper studies the Speech Enhancement based on Deep Neural Networks. The proposed architecture gradually follows the signal transformation during enhancement by means of a visualization probe at each network block. Alongside the…
This paper proposes a framework for modeling sound change that combines deep learning and iterative learning. Acquisition and transmission of speech is modeled by training generations of Generative Adversarial Networks (GANs) on unannotated…
We report on aggressive quantization strategies that greatly accelerate inference of Recurrent Neural Network Transducers (RNN-T). We use a 4 bit integer representation for both weights and activations and apply Quantization Aware Training…
Text-to-speech (TTS) synthesis is the process of producing synthesized speech from text or phoneme input. Traditional TTS models contain multiple processing steps and require external aligners, which provide attention alignments of…
This paper describes the practical response- and performance-aware development of online speech enhancement for an augmented reality (AR) headset that helps a user understand conversations made in real noisy echoic environments (e.g.,…
Deep neural networks (DNNs) and more precisely recurrent neural networks (RNNs) are at the core of modern automatic speech recognition systems, due to their efficiency to process input sequences. Recently, it has been shown that different…
Speech enhancement model is used to map a noisy speech to a clean speech. In the training stage, an objective function is often adopted to optimize the model parameters. However, in most studies, there is an inconsistency between the model…
We propose an end-to-end model based on convolutional and recurrent neural networks for speech enhancement. Our model is purely data-driven and does not make any assumptions about the type or the stationarity of the noise. In contrast to…
Deep neural networks (DNNs) exhibit vulnerability to adversarial examples that can transfer across different DNN models. A particularly challenging problem is developing transferable targeted attacks that can mislead DNN models into…
To address the monaural speech enhancement problem, numerous research studies have been conducted to enhance speech via operations either in time-domain on the inner-domain learned from the speech mixture or in time--frequency domain on the…
Speech enhancement in multichannel settings has been realized by utilizing the spatial information embedded in multiple microphone signals. Moreover, deep neural networks (DNNs) have been recently advanced in this field; however, studies on…
Speaker-independent speech separation has achieved remarkable performance in recent years with the development of deep neural network (DNN). Various network architectures, from traditional convolutional neural network (CNN) and recurrent…
Speech separation models are used for isolating individual speakers in many speech processing applications. Deep learning models have been shown to lead to state-of-the-art (SOTA) results on a number of speech separation benchmarks. One…
In this paper, a time delay neural network (TDNN) based acoustic model is proposed to implement a fast-converged acoustic modeling for Korean speech recognition. The TDNN has an advantage in fast-convergence where the amount of training…
Recent studies have shown that deep neural networks (DNNs) perform significantly better than shallow networks and Gaussian mixture models (GMMs) on large vocabulary speech recognition tasks. In this paper, we argue that the improved…
Adaption of end-to-end speech recognition systems to new tasks is known to be challenging. A number of solutions have been proposed which apply external language models with various fusion methods, possibly with a combination of two-pass…
In recent years, supervised approaches using deep neural networks (DNNs) have become the mainstream for speech enhancement. It has been established that DNNs generalize well to untrained noises and speakers if trained using a large number…
In this work, we propose a deep beamforming framework for speech enhancement in dynamic acoustic environments. The framework learns time-varying beamformer weights from noisy multichannel signals via a deep neural network, guided by a…