Enhances activity recognition in wearable computing with context awareness and uncertainty quantification.
problem Context-dependent activity recognition and unknown contexts in wearable computing.
method Developed the α-{eta} network coupled with uncertainty quantification (UQ) based on maximum entropy.
result Improved accuracy and F-score by 10% through high-level context identification.
End-to-end ASR system uses context n-grams for better speech recognition.
problem Contextual information impacts speech recognition accuracy.
method Jointly optimizes ASR components with context embeddings during inference.
result Proposed CLAS system outperforms traditional methods by 68% relative WER.
Modeling long-range context for multi-function utterances in dialogues.
problem Complex dependencies across dialogue turns in long utterances.
method Adapted Convolutional Recurrent Neural Network (CRNN) to model interactions between utterances.
result Significantly outperforms existing work on CDA recognition on a tech forum dataset.
Context-aware ZSL improves object recognition by considering object context.
problem Previous ZSL approaches ignore object context, limiting their effectiveness.
method Proposes a new approach that models the conditional likelihood of objects appearing in specific contexts.
result Contextual information significantly improves ZSL performance and is robust to class imbalance.
A deep network learns diverse contexts from multi-modal sensor data.
problem Recognizing diverse contexts and activities from multi-modal sensor data.
method Multi-stream temporal convolutional network with contextualization module.
result Deep network achieves optimal recognition rate.
Paper proposes neural approach for Chinese named entity recognition.
problem Challenges in Chinese named entity recognition due to context-dependency and lack of word delimiters.
method Introduces a CNN-LSTM-CRF neural architecture and a unified framework for joint training with word segmentation.
result Improves Chinese named entity recognition performance, especially with limited training data.
Hybrid ASR systems can model graphemes effectively using chenones, outperforming traditional methods.
problem Traditional hybrid ASR systems struggle with English's poor grapheme-phoneme correspondence.
method Leveraging tied context-dependent graphemes (chenones) to model graphemes directly.
result Chenone-based systems significantly outperform senone baselines by 4.5% to 11.1% on English datasets.
SVM with local features improves human action recognition.
problem Improving human action recognition in videos.
method Local appearance and motion features extracted using CNNs, concatenated, and used with SVM for classification.
result SVM with local features outperforms previous methods on benchmark datasets.
AV-ASR system improves speech recognition with visual context.
problem Improving speech recognition accuracy with visual information.
method Transformer-based architecture with multiresolution and multimodal training.
result Multiresolution training speeds up convergence and improves WER by 18%.
New metric and method for sEMG-based gesture recognition under domain shifts.
problem Measuring and adapting to domain divergence in sEMG-based gesture recognition.
method Probability distribution-based metric, 2-stage autoregressive RNN architecture.
result Improved autoregressive, RNN-based architecture enhances performance.
Bayesian method improves neural net convergence for character recognition.
problem Improving convergence rate of neural network training algorithms.
method Customization of Kalman filter into Bayesian statistics for initialization of weights.
result Improved convergence rate for backpropagation training algorithm.
This paper improves speech recognition by distilling knowledge from acoustic models.
problem Improving speech recognition accuracy using ensemble models.
method Proposes multi-teacher distillation strategies for joint CTC-attention end-to-end ASR systems, integrating error rate metric for optimization.
result Reports state-of-the-art error rates on various datasets and languages.
Paper proposes a dataset quality process for ML systems.
problem Inadequate standards for ML datasets in safety-critical systems.
method Proposes a dataset specification and verification process.
result Demonstrates the process on a railway signal recognition system.
Convolutional Neural Networks (CNNs) are effective models for reducing spectral variations and modeling spectral correlations in acoustic features for automatic speech recognition (ASR). Hybrid speech recognition systems incorporating CNNs with Hidden Markov Models/Gaussian Mixture Models (HMMs/GMMs) have achieved the …
Enhances speech emotion recognition by adapting to varying time scales.
problem Robust emotion recognition from speech audio with temporal variations.
method Introduces multi-time-scale (MTS) convolutional layers to CNNs.
result MTS layers improve generalization, especially on smaller datasets.
We have recently shown that deep Long Short-Term Memory (LSTM) recurrent neural networks (RNNs) outperform feed forward deep neural networks (DNNs) as acoustic models for speech recognition. More recently, we have shown that the performance of sequence trained context dependent (CD) hidden Markov model (HMM) acoustic m…
Novel CNN array for sign language recognition using wearable IMUs.
problem Efficiently recognizing sign language from wearable IMU signals.
method Two-dimensional Convolutional Neural Network array architecture for Indian sign language recognition.
result Peak classification accuracies of 94.20% for general sentences and 95.00% for interrogative sentences achieved.
Smart city surveillance benefits from sound event recognition.
problem Improving monitoring capabilities in smart cities.
method Exploration of several classifiers on the SESA dataset.
result SGD achieved 72.13% accuracy in sound event recognition.
Gaussian Process upsampling boosts OCR accuracy from low-res images.
problem Low-quality and downsampled image data hinders OCR accuracy.
method Gaussian Process upsampling model for improving OCR on low-resolution documents.
result Upsampling improves OCR accuracy on low-resolution images.
The paper studies conditions for exact posterior modeling in Bayesian networks.
problem Exact modeling of posterior distributions in Bayesian networks.
method Derives conditions for a recognition network to model the true posterior distribution exactly.
result Perfectness of the recognition network is crucial for local conditions to hold.
Multi-output Gaussian processes (MOGP) are probability distributions over vector-valued functions, and have been previously used for multi-output regression and for multi-class classification. A less explored facet of the multi-output Gaussian process is that it can be used as a generative model for vector-valued rando…
TACAM improves argument mining by integrating topic and external context.
problem Mining arguments from text without topic information leads to confusion.
method Proposes models that consider topic information and integrate external context.
result Performance boost for argument mining when topic and external context are considered.
The problem of human activity recognition is central for understanding and predicting the human behavior, in particular in a prospective of assistive services to humans, such as health monitoring, well being, security, etc. There is therefore a growing need to build accurate models which can take into account the varia…
Improved 3D scene understanding from partial point sets using multiview fusion.
problem Challenging task of 3D scene semantic understanding from partial point clouds.
method Multiview representation of 360° point clouds and fusion with original data.
result Overall increase of 31.9% and 4.3% in segmentation accuracy for partial and complete scenes.
Study evaluates feature selection methods for emotion recognition in resource-constrained settings.
problem Reducing memory and computational requirements for emotion recognition in low-resource settings.
method Evaluation of three feature selection methods: ILFS, ReliefF, Fisher, and AFS.
result Smaller feature sets can achieve similar or better accuracy, reducing resource usage.
Self-attention model improves HAR from wearable sensors.
problem Capturing spatio-temporal context from sensor data.
method Proposes a self-attention based neural network model.
result Significant performance improvement over state-of-the-art models.
We replace the Hidden Markov Model (HMM) which is traditionally used in in continuous speech recognition with a bi-directional recurrent neural network encoder coupled to a recurrent neural network decoder that directly emits a stream of phonemes. The alignment between the input and output sequences is established usin…
This research tackles backdoor attacks on audio data using a stochastic investment approach.
problem The threat of backdoor attacks on audio data, especially in voice-activated systems.
method A Stochastic investment-based backdoor attack (MarketBack) approach.
result MarketBack can achieve an average attack success rate close to 100% with less than 1% of poisoned data.
The study compares adversarial and multi-task learning for speech recognition, finding invariant representations are key.
problem Improving speech recognition performance with speaker information.
method Investigated multi-task learning and adversarial learning for speech recognition, comparing their effects on error rates.
result Deep models already develop speaker-invariant representations, and adversarial learning has a minor impact.
Long short-term memory (LSTM) is normally used in recurrent neural network (RNN) as basic recurrent unit. However,conventional LSTM assumes that the state at current time step depends on previous time step. This assumption constraints the time dependency modeling capability. In this study, we propose a new variation of…
Quaternion neural networks improve speech recognition efficiency.
problem Improving speech recognition systems with fewer parameters.
method Investigating quaternion-valued convolutional and recurrent neural networks.
result Quaternion neural networks outperform real-valued models with fewer parameters.
We propose a simple neural network model to deal with the domain adaptation problem in object recognition. Our model incorporates the Maximum Mean Discrepancy (MMD) measure as a regularization in the supervised learning to reduce the distribution mismatch between the source and target domains in the latent space. From …
Study shows semi-supervised learning improves human activity recognition with minimal user input.
problem Improving human activity recognition models using incremental learning.
method Three approaches: non-supervised, semi-supervised, and supervised learning were compared.
result Semi-supervised learning achieves similar accuracy to supervised learning with minimal user input.
Self-attentive network improves emotion recognition in conversations.
problem Emotion recognition in dyadic conversations using deep learning.
method Introduces a novel self-attention mechanism for capturing temporal dynamics without a decoder.
result Outperforms state-of-the-art alternatives on the IEMOCAP benchmark.
Paper uses SSD to detect miners' activities in a mining environment.
problem Tracking miners' activities in a mining environment with little obstruction.
method Used SSD trained on COCO dataset to detect miners' activities. Implemented machine learning algorithms using Tensorflow and C++.
result Improved accuracy of detecting miners' activities through data fusion.
Non-autoregressive transformer improves speech recognition speed and accuracy.
problem Reducing inference computation cost in speech recognition.
method Two non-autoregressive transformer structures (A-CMLM and A-FMLM) trained with masked tokens and iterative prediction during inference.
result Non-autoregressive transformer can match autoregressive transformer performance with 7x speedup.
Photo-identification technique improved for new dolphin individuals.
problem Traditional photo-identification of dolphins is laborious and manual.
method Metric embedding learning using triplet loss function in Euclidean space.
result Compact representation of fin images generalizes well to new identities.
High-dimensional ConvNets detect patterns in 32+ dimensions for geometric registration.
problem Detecting geometric patterns in high-dimensional spaces.
method High-dimensional convolutional networks applied to geometric registration problems.
result High-dimensional ConvNets outperform global pooling approaches in 3D registration and image correspondence.
DACNN improves skeleton-based action recognition and segmentation.
problem Lack of spatial relationships and non-uniform temporal scalings in skeleton-based data.
method Introduces deep-aligned convolutional neural network (DACNN) with new filters trained on local subsequences.
result DACNN achieves competitive performance compared to state-of-the-art models.
VFDS selects dynamic features for efficient HAR tasks, optimizing performance-cost trade-offs.
problem Optimizing feature selection for varying costs and dynamic contexts in machine learning tasks.
method Bayesian learning framework with variational dynamic selection policy.
result VFDS selects different features under changing contexts, saving sensory costs while maintaining HAR accuracy.
With a simple architecture and the ability to learn meaningful word embeddings efficiently from texts containing billions of words, word2vec remains one of the most popular neural language models used today. However, as only a single embedding is learned for every word in the vocabulary, the model fails to optimally re…
New online few-shot learning model for context-aware recognition.
problem Few-shot learning in online, continuous settings with spatiotemporal context.
method Proposed new dataset and online versions of existing few-shot learning approaches.
result Contextual prototypical memory model improves performance.
We generate transformation-invariant CNNs using context-aware filters.
problem Creating transformation-invariant neural networks for image recognition.
method Input-conditioned convolution filters combined with max-pooling and multi-instance learning.
result Significantly improved error rates on MNIST variations (1.13% on MNIST-rot-12k, 1.12% on Half-rotated MNIST, 0.68% on Scaling MNIST).
Riemannian batchnorm improves SPD matrix networks.
problem Learning SPD matrices in deep networks.
method Introduces a novel Riemannian batchnorm algorithm.
result Riemannian batchnorm outperforms existing methods.
We consider object recognition in the context of lifelong learning, where a robotic agent learns to discriminate between a growing number of object classes as it accumulates experience about the environment. We propose an incremental variant of the Regularized Least Squares for Classification (RLSC) algorithm, and expl…
Deep convolutional neural networks have recently achieved state-of-the-art performance on a number of image recognition benchmarks, including the ImageNet Large-Scale Visual Recognition Challenge (ILSVRC-2012). The winning model on the localization sub-task was a network that predicts a single bounding box and a confid…
Streaming ASR with transformer achieves low WER.
problem Real-time ASR with speech recognition.
method Time-restricted self-attention and triggered attention mechanisms.
result 2.8% and 7.2% WER for LibriSpeech test data.
ADDoG improves cross-dataset speech emotion recognition.
problem Cross-dataset speech emotion recognition failure.
method ADDoG uses an iterative approach to move representations closer together across datasets.
result ADDoG and MADDoG improve cross-dataset speech emotion recognition.