Improved speech recognition using EEG and video.
problem Enhancing continuous speech recognition systems.
method Implemented a CTC-based ASR model using EEG features.
result EEG features improve continuous visual speech recognition.
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
169,051 papers · 148 categories
Trend · papers per month
48 results for “automatic recognition”
Paper shows EEG can improve ASR in noisy speech.
problem ASR performance drops in noisy conditions.
method Used EEG to train ASR models and improve performance.
result ASR accuracy improved with EEG features and distillation.
New system for automatic music emotion recognition considers multiple emotions simultaneously.
problem Automatic recognition of simultaneous and multiplicity of emotions in music.
method Comparison of multilabel and multiclass machine learning algorithms on the Emotify dataset.
result The Geneva Emotional Music Scale 9 is adopted for multilabel and multiclass classification of music emotions.
Spoken language translation (SLT) has become very important in an increasingly globalized world. Machine translation (MT) for automatic speech recognition (ASR) systems is a major challenge of great interest. This research investigates that automatic sentence segmentation of speech that is important for enriching speec…
Paper explores EEG-based speech recognition using transformers, showing faster training and better performance for smaller vocabularies.
problem Continuous speech recognition using EEG features.
method Transformer-based ASR model compared to RNN-based models.
result Transformer models perform better for smaller vocabularies but RNN models outperform them for larger vocabularies.
Improved speech recognition with audio-visual fusion.
problem Enhance speech recognition accuracy in noisy conditions.
method Proposes an attention-based audio-visual fusion strategy to align and learn from acoustic and lip motion data.
result Significant improvements in recognition accuracy (7-30%) on TCD-TIMIT dataset.
Universal audio perturbations fool ASR systems.
problem Speech recognition systems are vulnerable to adversarial attacks.
method Developed an algorithm to create universal perturbations that fool ASR models.
result Universal perturbations can fool ASR systems across different models.
Joint Unsupervised and Supervised Training for Automatic Speech Recognition via Bilevel Optimizationcs.CL
Novel approach trains ASR models with less supervision using bilevel optimization.
problem Training acoustic models for ASR with minimal supervision.
method Bilevel optimization with unsupervised and supervised losses.
result Achieves superior performance compared to existing methods.
Nontrivial connectivity has allowed the training of very deep networks by addressing the problem of vanishing gradients and offering a more efficient method of reusing parameters. In this paper we make a comparison between residual networks, densely-connected networks and highway networks on an image classification tas…
End-to-end speech recognition using EEG without speech input.
problem Speech recognition without direct speech input.
method Implemented attention model and CTC-based ASR systems for EEG signals; fused EEG with noisy speech features.
result Demonstrated end-to-end speech recognition using EEG signals.
A new weighted FDA method improves face recognition accuracy.
problem Equal treatment of all class pairs in FDA leads to suboptimal performance.
method Cosine-weighted and automatically weighted FDA methods are proposed.
result Improved face recognition accuracy through weighted FDA.
Continuous speech recognition from brain activity without vocalization.
problem Recognizing silent speech from EEG signals.
method Implemented a CTC ASR model using EEG signals.
result Demonstrated feasibility of EEG for continuous silent speech recognition.
Develops STC for sequential data with missing labels.
problem Learning from partially labeled and unsegmented sequential data.
method Introduces Star Temporal Classification (STC) using a star token and GTN framework.
result Recover most of supervised baseline performance with up to 70% missing labels.
Deep Neural Networks for Automatic Speech Processing: A Survey from Large Corpora to Limited Dataeess.AS
Survey on DNNs for speech processing, focusing on limited data challenges.
problem Challenges in training DNNs for speech tasks with limited data.
method Overview of techniques for few-shot speech processing.
result Promising few-shot techniques for speech processing.
Introspects convolutional speech recognition models using Gradient-adjusted Neuron Activation Profiles.
problem Lack of interpretability in deep learning ASR models.
method Gradient-adjusted Neuron Activation Profiles (GradNAPs) for feature and representation visualization.
result Gains insight into how data is processed in convolutional ASR models.
CL methods improve monolingual ASR models across new tasks without forgetting past data.
problem Catastrophic Forgetting in monolingual ASR models when adapting to new domains or accents.
method Implement and compare various Continual Learning methods for monolingual ASR.
result Best CL method reduces performance gap by over 40% with minimal past data.
Paper improves EEG-based speech recognition using CTC and beam search.
problem Improving continuous speech recognition from EEG signals.
method Implemented CTC-based ASR system, initialized weights, used external language model, studied articulatory feature prediction.
result Enhanced performance of EEG-based speech recognition systems.
This work improves ASR noise robustness using parallel data and T/S learning.
problem Noise robustness in automatic speech recognition.
method Teacher-student learning with parallel clean and noisy data, logits selection.
result Best student model yields significant WER reductions in noisy conditions.
Robust ASR model removes fast-changing features to resist attacks.
problem Vulnerability of ASR systems to adversarial attacks.
method Removing fast-changing features using slow feature analysis or low-pass filtering.
result Hybrid ASR models are more than four times more robust against targeted attacks.
A new multi-layer attention mechanism improves speech keyword recognition accuracy.
problem Inaccurate attention weights in LSTM networks for speech keyword recognition.
method Introducing information from layers prior to feature extraction into attention weights calculations.
result The proposed multi-layer attention mechanism leads to more accurate attention weights and improved keyword spotting performance.
Study improves RF sensor robustness for target recognition.
problem Variability in RF target responses makes them vulnerable to attacks.
method Evaluates techniques for building robust classification architectures.
result Improves accuracy in identifying true target characteristics.
Emotion Recognition in Low-Resource Settings: An Evaluation of Automatic Feature Selection Methodscs.LG
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.
ADPSGD enables faster ASR training with larger batch sizes.
problem Efficient distributed deep learning for ASR with large batch sizes.
method Asynchronous Decentralized Parallel Stochastic Gradient Descent (ADPSGD) and Hierarchical-ADPSGD (H-ADPSGD).
result ADPSGD can converge with a 3X larger batch size than SSGD, enabling faster training.
Deep-AER system uses lightweight CNN models for EEG-based emotion recognition.
problem Challenging task of emotion recognition using EEG signals.
method Two-level ensemble of lightweight 1D-CNN models trained on a small dataset.
result Deep-AER achieved high accuracies (98.43% and 97.65%) for emotion detection.
The paper explores distributed deep learning strategies for ASR, achieving faster training times.
problem Improving ASR performance and training speed with distributed deep learning.
method Investigated and implemented various distributed strategies including SYNC, ADPSGD, and HYBRID.
result ADPSGD achieved a 7.6% WER on the Hub5-2000 Switchboard test set in 14 hours with 16 NVIDIA P100 GPUs.
A Review of Deep Learning with Special Emphasis on Architectures, Applications and Recent Trendscs.LG
Deep learning tackles automatic pattern recognition with high accuracy.
problem Automatic recognition of patterns in data.
method Multilayer ANNs and automatic architecture optimization protocols.
result Deep learning surpasses human accuracy in pattern recognition.
In this work we explored building automatic speech recognition models for transcribing doctor patient conversation. We collected a large scale dataset of clinical conversations ( hr), designed the task to represent the real word scenario, and explored several alignment approaches to iteratively improve data qua…
This study provides benchmarks for different implementations of LSTM units between the deep learning frameworks PyTorch, TensorFlow, Lasagne and Keras. The comparison includes cuDNN LSTMs, fused LSTM variants and less optimized, but more flexible LSTM implementations. The benchmarks reflect two typical scenarios for au…
Paper explores deep learning features for complex emotion recognition.
problem Improving emotion recognition accuracy in complex emotions.
method Used pretrained networks (AudioSet Net, VoxCeleb Net, Deep Speech Net) and their deep layer features for emotion recognition.
result Achieved highest F1 score of 0.85 on EmoReact dataset.
ChemGrapher uses deep learning to automatically convert chemical compound images into accurate graphs.
problem Automatically converting chemical compound images into accurate graphs with correct bond multiplicity and stereochemical information.
method Developed a deep neural network model for optical compound recognition, including segmentation and classification models.
result Significant error reductions in bond multiplicity and stereochemical information compared to existing tools.
Study combines speaker verification and voice trigger detection in a single network.
problem Separate training for speaker verification and voice trigger detection.
method Multi-task learning with a single network trained on both tasks.
result Single network achieves comparable accuracy to independent models for each task.
AV-CPL uses continuous pseudo-labels for AVSR combining labeled and unlabeled data.
problem Improving AVSR performance with labeled and unlabeled data.
method Semi-supervised method using continuous pseudo-labels generated by the same AVSR model.
result Significant improvements in VSR performance on LRS3 dataset.
The paper analyzes sports commentary to automatically recognize events and extract insights.
problem Automatically recognizing and categorizing major actions in sports events from commentary.
method Used multiple Natural Language Processing techniques for classification and sentiment analysis.
result Identified insights from analyzing live sport commentaries and classifying major actions.
The performance of automatic speech recognition (ASR) systems can be significantly compromised by previously unseen conditions, which is typically due to a mismatch between training and testing distributions. In this paper, we address robustness by studying domain invariant features, such that domain information become…
Model learns accent patterns from small datasets.
problem Automatic speech recognition struggles with rare accents.
method Automatically retrieves phonological generalizations from a small dataset.
result Model generates a million phonological variations of words.
Deep neural network architectures designed for application domains other than sound, especially image recognition, may not optimally harness the time-frequency representation when adapted to the sound recognition problem. In this work, we explore the ConditionaL Neural Network (CLNN) and the Masked ConditionaL Neural N…
Spatial Diffuseness Features for DNN-Based Speech Recognition in Noisy and Reverberant Environmentscs.CL
We propose a spatial diffuseness feature for deep neural network (DNN)-based automatic speech recognition to improve recognition accuracy in reverberant and noisy environments. The feature is computed in real-time from multiple microphone signals without requiring knowledge or estimation of the direction of arrival, an…
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.
AeGAN improves speech clarity in noisy environments.
problem Improving speech recognition in crowded noisy environments.
method Generative adversarial networks (GAN) with a novel architecture.
result The proposed framework outperforms traditional and learning-based methods.
GP-CNAS uses genetic programming to automatically design CNN architectures.
problem Designing optimal CNN architectures is laborious and error-prone.
method GP-CNAS uses a tree-based representation of CNNs and dynamic crossover operators to search for optimal architectures.
result GP-CNAS finds optimal CNN architectures with balanced depth and width in limited trials.
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.
Dilated CNN improves multivariate time series classification.
problem Multivariate time series classification.
method Transformed multivariate time series into image-like style, applied dilated and strided convolutions.
result Automatic features extracted by dilated CNN are as effective as hand-crafted features.
The paper improves ASR accuracy using semi-supervised learning and dropout.
problem Improving ASR accuracy with limited labeled data.
method Training a seed model on limited labeled data, using dropout for uncertainty, and data selection for diversity.
result The approach significantly reduces ASR errors compared to baseline.
Iterative AutoML improves ASR model compression by 5x without WER degradation.
problem Challenges in achieving high compression levels without degrading ASR performance.
method Iterative AutoML-based Low Rank Factorization (LRF) approach.
result Achieved over 5x compression without WER degradation.
AVEC 2019 challenges AI in detecting depression and cross-cultural emotions.
problem Detecting depression and cross-cultural emotions from audiovisual data.
method Comparison of machine learning methods under standardized conditions.
result Baseline system performance on state-of-mind, depression, and cross-cultural tasks.
Unsupervised beamforming improves ASR in noisy conditions.
problem Improving ASR in unknown noisy environments.
method Multichannel NMF-Informed Beamforming (MVDR) for noise-robust ASR.
result The proposed method outperformed DNN-based beamforming in unknown environments.
Bidirectional Quaternion Long-Short Term Memory Recurrent Neural Networks for Speech Recognitioneess.AS
QLSTM improves speech recognition by considering internal quaternion dependencies.
problem Weak internal dependencies in traditional RNNs for speech recognition.
method Proposes QLSTM, a quaternion-based LSTM that considers both external and internal dependencies.
result QLSTM achieves better performance with up to 2.8 times fewer parameters.
In conventional supervised pattern recognition tasks, model selection is typically accomplished by minimizing the classification error rate on a set of so-called development data, subject to ground-truth labeling by human experts or some other means. In the context of speech processing systems and other large-scale pra…