相关论文: Speech Recognition: Keyword Spotting Through Image…

Human action recognition in videos is a critical task with significant implications for numerous applications, including surveillance, sports analytics, and healthcare. The challenge lies in creating models that are both precise in their…

We introduce a method to identify speakers by computing with high-dimensional random vectors. Its strengths are simplicity and speed. With only 1.02k active parameters and a 128-minute pass through the training data we achieve Top-1 and…

This technical report describes the methods and results of a three-week sprint to produce deployable speech recognition models for 31 under-served languages of the Common Voice project. We outline the preprocessing steps, hyperparameter…

This paper proposes a Sub-band Convolutional Neural Network for spoken term classification. Convolutional neural networks (CNNs) have proven to be very effective in acoustic applications such as spoken term classification, keyword spotting,…

We show that a recurrent neural network is able to learn a model to represent sequences of communications between computers on a network and can be used to identify outlier network traffic. Defending computer networks is a challenging…

Language Identification (LID) systems are used to classify the spoken language from a given audio sample and are typically the first step for many spoken language processing tasks, such as Automatic Speech Recognition (ASR) systems. Without…

The task of estimating the maximum number of concurrent speakers from single channel mixtures is important for various audio-based applications, such as blind source separation, speaker diarisation, audio surveillance or auditory scene…

We study self-supervised video representation learning, which is a challenging task due to 1) lack of labels for explicit supervision; 2) unstructured and noisy visual information. Existing methods mainly use contrastive loss with video…

Improving speech system performance in noisy environments remains a challenging task, and speech enhancement (SE) is one of the effective techniques to solve the problem. Motivated by the promising results of generative adversarial networks…

The problem of multi-speaker localization is formulated as a multi-class multi-label classification problem, which is solved using a convolutional neural network (CNN) based source localization method. Utilizing the common assumption of…

Mismatching problem between the source and target noisy corpora severely hinder the practical use of the machine-learning-based voice activity detection (VAD). In this paper, we try to address this problem in the transfer learning…

Speech emotion recognition (SER) has been a challenging problem in spoken language processing research, because it is unclear how human emotions are connected to various components of sounds such as pitch, loudness, and energy. This paper…

In computer vision pixelwise dense prediction is the task of predicting a label for each pixel in the image. Convolutional neural networks achieve good performance on this task, while being computationally efficient. In this paper we carry…

Visual keyword spotting (KWS) is the problem of estimating whether a text query occurs in a given recording using only video information. This paper focuses on visual KWS for words unseen during training, a real-world, practical setting…

At the present time, computers are employed to solve complex tasks and problems ranging from simple calculations to intensive digital image processing and intricate algorithmic optimization problems to computationally-demanding weather…

In the last few years, steganography has attracted increasing attention from a large number of researchers since its applications are expanding further than just the field of information security. The most traditional method is based on…

Acoustic emotion recognition aims to categorize the affective state of the speaker and is still a difficult task for machine learning models. The difficulties come from the scarcity of training data, general subjectivity in emotion…

The goal of this paper is to learn strong lip reading models that can recognise speech in silent videos. Most prior works deal with the open-set visual speech recognition problem by adapting existing automatic speech recognition techniques…

Automatically generating a natural language sentence to describe the content of an input video is a very challenging problem. It is an essential multimodal task in which auditory and visual contents are equally important. Although audio…

One of the most challenging scenarios for smart speakers is multi-talker, when target speech from the desired speaker is mixed with interfering speech from one or more speakers. A smart assistant needs to determine which voice to recognize…