相关论文: Speaker Reinforcement Using Target Source Extracti…

Automatic recognition of disordered speech remains a highly challenging task to date due to data scarcity. This paper presents a reinforcement learning (RL) based on-the-fly data augmentation approach for training state-of-the-art PyChain…

In the past few years, it has been shown that deep learning systems are highly vulnerable under attacks with adversarial examples. Neural-network-based automatic speech recognition (ASR) systems are no exception. Targeted and untargeted…

We propose a novel approach to semi-supervised automatic speech recognition (ASR). We first exploit a large amount of unlabeled audio data via representation learning, where we reconstruct a temporal slice of filterbank features from past…

In this paper we investigate speech denoising as a defense against adversarial attacks on automatic speech recognition (ASR) systems. Adversarial attacks attempt to force misclassification by adding small perturbations to the original…

Building an accurate automatic speech recognition (ASR) system requires a large dataset that contains many hours of labeled speech samples produced by a diverse set of speakers. The lack of such open free datasets is one of the main issues…

Recent advancement in deep learning encouraged developing large automatic speech recognition (ASR) models that achieve promising results while ignoring computational and memory constraints. However, deploying such models on low resource…

We present a training scheme for streaming automatic speech recognition (ASR) based on recurrent neural network transducers (RNN-T) which allows the encoder network to learn to exploit context audio from a stream, using segmented or…

Punctuation restoration is an important task in automatic speech recognition (ASR) which aim to restore the syntactic structure of generated ASR texts to improve readability. While punctuated texts are abundant from written documents, the…

Noise robustness is essential for deploying automatic speech recognition (ASR) systems in real-world environments. One way to reduce the effect of noise interference is to employ a preprocessing module that conducts speech enhancement, and…

Data augmentation is vital to the generalization ability and robustness of deep neural networks (DNNs) models. Existing augmentation methods for speaker verification manipulate the raw signal, which are time-consuming and the augmented…

Accented automatic speech recognition (ASR) often degrades due to the limited availability of accented training data. Prior work has explored accent modeling in low-resource settings, but existing approaches typically require minutes to…

Self-supervised learning (SSL) methods which learn representations of data without explicit supervision have gained popularity in speech-processing tasks, particularly for single-talker applications. However, these models often have…

Training personalized speech enhancement models is innately a no-shot learning problem due to privacy constraints and limited access to noise-free speech from the target user. If there is an abundance of unlabeled noisy speech from the…

Speaker recognition is a well known and studied task in the speech processing domain. It has many applications, either for security or speaker adaptation of personal devices. In this paper, we present a new paradigm for automatic speaker…

Recent studies have highlighted adversarial examples as ubiquitous threats to the deep neural network (DNN) based speech recognition systems. In this work, we present a U-Net based attention model, U-Net$_{At}$, to enhance adversarial…

It has been shown that the intelligibility of noisy speech can be improved by speech enhancement (SE) algorithms. However, monaural SE has not been established as an effective frontend for automatic speech recognition (ASR) in noisy…

Deep biasing improves automatic speech recognition (ASR) performance by incorporating contextual phrases. However, most existing methods enhance subwords in a contextual phrase as independent units, potentially compromising contextual…

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…

This paper describes multichannel speech enhancement for improving automatic speech recognition (ASR) in noisy environments. Recently, the minimum variance distortionless response (MVDR) beamforming has widely been used because it works…

We propose automatic speech recognition (ASR) models inspired by echo state network (ESN), in which a subset of recurrent neural networks (RNN) layers in the models are randomly initialized and untrained. Our study focuses on RNN-T and…