Related papers: Trainable Frontend For Robust and Far-Field Keywor…

Neural network applications generally benefit from larger-sized models, but for current speech enhancement models, larger scale networks often suffer from decreased robustness to the variety of real-world use cases beyond what is…

Recently, deep learning-based beamforming algorithms have shown promising performance in target speech extraction tasks. However, most systems do not fully utilize spatial information. In this paper, we propose a target speech extraction…

Mel-scale spectrum features are used in various recognition and classification tasks on speech signals. There is no reason to expect that these features are optimal for all different tasks, including speaker verification (SV). This paper…

Very deep CNNs achieve state-of-the-art results in both computer vision and speech recognition, but are difficult to train. The most popular way to train very deep CNNs is to use shortcut connections (SC) together with batch normalization…

Noise efficiency factor (NEF) and power efficiency factor (PEF) are widely used as the figure of merit to quantify the performance of biopotential recording front-ends. NEF and PEF are discussed from the noise analysis to the trend survey.…

Despite the significant success of deep learning in computer vision tasks, cross-domain tasks still present a challenge in which the model's performance will degrade when the training set and the test set follow different distributions.…

Noise suppression and echo cancellation are critical in speech enhancement and essential for smart devices and real-time communication. Deployed in voice processing front-ends and edge devices, these algorithms must ensure efficient…

Recent advances in unsupervised speech representation learning discover new approaches and provide new state-of-the-art for diverse types of speech processing tasks. This paper presents an investigation of using wav2vec 2.0 deep speech…

Distributed Mean Estimation (DME) is a central building block in federated learning, where clients send local gradients to a parameter server for averaging and updating the model. Due to communication constraints, clients often use lossy…

As one of the major sources in speech variability, accents have posed a grand challenge to the robustness of speech recognition systems. In this paper, our goal is to build a unified end-to-end speech recognition system that generalizes…

Deep neural networks provide effective solutions to small-footprint keyword spotting (KWS). However, if training data is limited, it remains challenging to achieve robust and highly accurate KWS in real-world scenarios where unseen sounds…

In recent years, pretrained models revolutionized the paradigm of natural language understanding (NLU), where we append a randomly initialized classification head after the pretrained backbone, e.g. BERT, and finetune the whole model. As…

Speech enhancement is a task to improve the intelligibility and perceptual quality of degraded speech signal. Recently, neural networks based methods have been applied to speech enhancement. However, many neural network based methods…

This paper introduces Progressively Diffused Networks (PDNs) for unifying multi-scale context modeling with deep feature learning, by taking semantic image segmentation as an exemplar application. Prior neural networks, such as ResNet, tend…

While originally designed for image generation, diffusion models have recently shown to provide excellent pretrained feature representations for semantic segmentation. Intrigued by this result, we set out to explore how well…

This article introduces a novel and fast method for refining pre-trained static word or, more generally, token embeddings. By incorporating the embeddings of neighboring tokens in text corpora, it continuously updates the representation of…

Most existing keyword spotting research focuses on conditions with slight or moderate noise. In this paper, we try to tackle a more challenging task: detecting keywords buried under strong interfering speech (10 times higher than the…

This paper introduces a novel convolutional neural networks (CNN) framework tailored for end-to-end audio deep learning models, presenting advancements in efficiency and explainability. By benchmarking experiments on three standard speech…

Image-text retrieval is a widely studied topic in the field of computer vision due to the exponential growth of multimedia data, whose core concept is to measure the similarity between images and text. However, most existing retrieval…

Many problems in computer vision require dealing with sparse, unordered data in the form of point clouds. Permutation-equivariant networks have become a popular solution-they operate on individual data points with simple perceptrons and…