Related papers: Modular Deep Learning Framework for Assistive Perc…

Recent advances in deep neural networks have been developed via architecture search for stronger representational power. In this work, we focus on the effect of attention in general deep neural networks. We propose a simple and effective…

This paper describes the extension and optimization of our previous work on very deep convolutional neural networks (CNNs) for effective recognition of noisy speech in the Aurora 4 task. The appropriate number of convolutional layers, the…

Motivated by the desire to exploit patterns shared across classes, we present a simple yet effective class-specific memory module for fine-grained feature learning. The memory module stores the prototypical feature representation for each…

Speech emotion recognition is a challenging task and heavily depends on hand-engineered acoustic features, which are typically crafted to echo human perception of speech signals. However, a filter bank that is designed from perceptual…

Convolutional Neural Networks (CNNs) have proven very effective in image classification and show promise for audio. We use various CNN architectures to classify the soundtracks of a dataset of 70M training videos (5.24 million hours) with…

This paper aims to improve the widely used deep speaker embedding x-vector model. We propose the following improvements: (1) a hybrid neural network structure using both time delay neural network (TDNN) and long short-term memory neural…

Speaker identification refers to the task of localizing the face of a person who has the same identity as the ongoing voice in a video. This task not only requires collective perception over both visual and auditory signals, the robustness…

Deep neural networks, albeit their great success on feature learning in various computer vision tasks, are usually considered as impractical for online visual tracking because they require very long training time and a large number of…

The capability of the self-attention mechanism to model the long-range dependencies has catapulted its deployment in vision models. Unlike convolution operators, self-attention offers infinite receptive field and enables compute-efficient…

In recent times, various modules such as squeeze-and-excitation, and others have been proposed to improve the quality of features learned from wearable sensor signals. However, these modules often cause the number of parameters to be large,…

The recent advances in deep learning are mostly driven by availability of large amount of training data. However, availability of such data is not always possible for specific tasks such as speaker recognition where collection of large…

The increasing global aging population has intensified the demand for reliable health monitoring systems, particularly those capable of detecting critical events such as falls among elderly individuals. Traditional fall detection approaches…

Speech perception is key to verbal communication. For people with hearing loss, the capability to recognize speech is restricted, particularly in a noisy environment or the situations without visual cues, such as lip-reading unavailable via…

In this paper, a novel architecture for speaker recognition is proposed by cascading speech enhancement and speaker processing. Its aim is to improve speaker recognition performance when speech signals are corrupted by noise. Instead of…

Object detection and segmentation are two core modules of an autonomous vehicle perception system. They should have high efficiency and low latency while reducing computational complexity. Currently, the most commonly used algorithms are…

Semantic segmentation has made significant strides in pixel-level image understanding, yet it remains limited in capturing contextual and semantic relationships between objects. Current models, such as CNN and Transformer-based…

In this paper, we summarize recent progresses made in deep learning based acoustic models and the motivation and insights behind the surveyed techniques. We first discuss acoustic models that can effectively exploit variable-length…

This paper addresses the problem of dense depth predictions from sparse distance sensor data and a single camera image on challenging weather conditions. This work explores the significance of different sensor modalities such as camera,…

Recurrent neural networks (RNNs), especially long short-term memory (LSTM) RNNs, are effective network for sequential task like speech recognition. Deeper LSTM models perform well on large vocabulary continuous speech recognition, because…

This paper proposes a serialized multi-layer multi-head attention for neural speaker embedding in text-independent speaker verification. In prior works, frame-level features from one layer are aggregated to form an utterance-level…