相关论文: A Curriculum Learning Method for Improved Noise Ro…

We study the problem of learning robust acoustic models in adverse environments, characterized by a significant mismatch between training and test conditions. This problem is of paramount importance for the deployment of speech recognition…

We address the problem of speech enhancement generalisation to unseen environments by performing two manipulations. First, we embed an additional recording from the environment alone, and use this embedding to alter activations in the main…

Batch normalization (BN) is an effective method to accelerate model training and improve the generalization performance of neural networks. In this paper, we propose an improved batch normalization technique called attentive batch…

To improve device robustness, a highly desirable key feature of a competitive data-driven acoustic scene classification (ASC) system, a novel two-stage system based on fully convolutional neural networks (CNNs) is proposed. Our two-stage…

In this paper, we introduce a novel training framework designed to comprehensively address the acoustic howling issue by examining its fundamental formation process. This framework integrates a neural network (NN) module into the…

Eliminating the negative effect of non-stationary environmental noise is a long-standing research topic for automatic speech recognition that stills remains an important challenge. Data-driven supervised approaches, including ones based on…

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…

This research presents a novel approach to enhancing automatic speech recognition systems by integrating noise detection capabilities directly into the recognition architecture. Building upon the wav2vec2 framework, the proposed method…

Robustness to environmental noise is important to creating automatic speech emotion recognition systems that are deployable in the real world. Prior work on noise robustness has assumed that systems would not make use of sample-by-sample…

Humans have the ability to utilize visual cues, such as lip movements and visual scenes, to enhance auditory perception, particularly in noisy environments. However, current Automatic Speech Recognition (ASR) or Audio-Visual Speech…

Neural sequence-to-sequence systems deliver state-of-the-art performance for automatic speech recognition. When using appropriate modeling units, e.g., byte-pair encoding, these systems are in principle open vocabulary systems. In practice,…

With the surge of online meetings, it has become more critical than ever to provide high-quality speech audio and live captioning under various noise conditions. However, most monaural speech enhancement (SE) models introduce processing…

In this paper, we present a method for jointly-learning a microphone selection mechanism and a speech enhancement network for multi-channel speech enhancement with an ad-hoc microphone array. The attention-based microphone selection…

Automatic speech recognition (ASR) systems play a key role in many commercial products including voice assistants. Typically, they require large amounts of clean speech data for training which gives an undue advantage to large organizations…

Despite recent advances, standard sequence labeling systems often fail when processing noisy user-generated text or consuming the output of an Optical Character Recognition (OCR) process. In this paper, we improve the noise-aware training…

We propose a novel multi-task pre-training method for Speech Emotion Recognition (SER). We pre-train SER model simultaneously on Automatic Speech Recognition (ASR) and sentiment classification tasks to make the acoustic ASR model more…

Acoustic Event Classification (AEC) has become a significant task for machines to perceive the surrounding auditory scene. However, extracting effective representations that capture the underlying characteristics of the acoustic events is…

This paper presents some recent algorithms developed by the authors for real-time adaptive active noise (AANC) control systems. These algorithms address some of the common challenges faced by AANC systems, such as speaker saturation, system…

Automatic speaker verification systems are vulnerable to a variety of access threats, prompting research into the formulation of effective spoofing detection systems to act as a gate to filter out such spoofing attacks. This study…

Consistency training regularizes a model by enforcing predictions of original and perturbed inputs to be similar. Previous studies have proposed various augmentation methods for the perturbation but are limited in that they are agnostic to…