Hybrid and end-to-end models compare in syllable recognition.
problem Comparing hybrid and end-to-end models for syllable recognition.
method Traditional hybrid system (kaldi) vs. end-to-end (TensorFlow) models.
result Hybrid models with explicit syllable knowledge outperform end-to-end models.
End-to-end transformer model improves lexical stress detection accuracy.
problem Inaccurate phoneme boundaries and limited features for stress classification.
method End-to-end sequence to sequence model using transformer trained on feature sequences and phoneme sequences with stress marks.
result End-to-end model achieves better performance and lower phoneme error rate (6.36%) compared to syllable segmentation methods.
As the technology is advancing, audio recognition in machine learning is improved as well. Research in audio recognition has traditionally focused on speech. Living creatures (especially the small ones) are part of the whole ecosystem, monitoring as well as maintaining them are important tasks. Species such as animals …
System identifies language of transliterated text.
problem Users struggle to understand non-native language transliterated text.
method Feature extraction of phonetic syllables using LSTM network.
result System accurately identifies language of transliterated text.
Syllabification does not seem to improve word-level RNN language modeling quality when compared to character-based segmentation. However, our best syllable-aware language model, achieving performance comparable to the competitive character-aware model, has 18%-33% fewer parameters and is trained 1.2-2.2 times faster.
We define families of aperiodic words associated to Lorenz knots that arise naturally as syllable permutations of symbolic words corresponding to torus knots. An algorithm to construct symbolic words of satellite Lorenz knots is defined. We prove, subject to the validity of a previous conjecture, that Lorenz knots code…
Study on finiteness property of right-angled Artin groups actions on extension graphs.
problem Finiteness property of hyperbolic simplicial actions on right-angled Artin groups.
method Analysis of right-angled Artin group actions on extension graphs, using asymptotic translation lengths and syllable lengths.
result Asymptotic translation lengths of elements in right-angled Artin groups are rational and have a common denominator under certain conditions.
We propose several ways of reusing subword embeddings and other weights in subword-aware neural language models. The proposed techniques do not benefit a competitive character-aware model, but some of them improve the performance of syllable- and morpheme-aware models while showing significant reductions in model sizes…
We define invariants of braids rather than invariants of conjugacy classes of braids. For any pure three-braid we give effective upper and lower bounds for these invariants. This is done in terms of a natural syllable decomposition of the word representing the image of the braid in the braid group modulo its center. Th…
Recent studies have introduced end-to-end TTS, which integrates the production of context and acoustic features in statistical parametric speech synthesis. As a result, a single neural network replaced laborious feature engineering with automated feature learning. However, little is known about what types of context in…
Paper introduces regularization for multi-head attention to spot keywords.
problem Redundancy in multi-head attention leads to lack of rich information.
method Regularization technique to enforce orthogonality between attention heads.
result Significant improvement in keyword spotting performance.
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.
Study shows emotion affects speaker recognition and vice versa.
problem Dependencies between emotion and speaker recognition.
method Transfer learning and fine-tuning for emotion classification.
result Fine-tuning improves emotion recognition performance by 30.40% on IEMOCAP, 7.99% on MSP-Podcast, and 8.61% on Crema-D.
With the recent renaissance of deep convolution neural networks, encouraging breakthroughs have been achieved on the supervised recognition tasks, where each class has sufficient training data and fully annotated training data. However, to scale the recognition to a large number of classes with few or now training samp…
New proof for sphere recognition algorithm.
problem Sphere recognition algorithm proof.
method New proof of a lemma in Abigail Thompson's algorithm.
result New proof of a lemma in Abigail Thompson's proof of the Recognition Algorithm for 3-spheres.
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.
VoxCeleb 2019 challenge assesses speaker recognition in uncontrolled settings.
problem Evaluate speaker recognition technology in unconstrained data.
method Public dataset, challenge, and workshop at Interspeech 2019.
result Baseline results and discussions provided.
Paper proposes Roweisposes for 3D action recognition using generalized eigenvalue problem.
problem Need for basic methods in 3D action recognition.
method Roweisposes uses Roweis discriminant analysis for generalized subspace learning.
result Roweisposes is effective for 3D action recognition.
This is a survey article on recognition problem of frontal singularities. We specify geometrically several frontal singularities and then we solve the recognition problem of such singularities, giving explicit normal forms. We combine the recognition results by K. Saji and several arguments on openings, which was perfo…
Paper tackles zero-shot activity recognition using video features and text embeddings.
problem Zero-shot activity recognition with videos.
method Auto-encoder model for multimodal joint embedding, 3D convolutional action recognition for visual features, GloVe word embeddings for textual features.
result Improved zero-shot recognition results with top-n accuracy and mean Nearest Neighbor Overlap.
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.
EmbraceNet fusion model for multi-sensor activity recognition.
problem Human activity recognition using multiple sensors is challenging.
method Independent processing of each sensor, feature fusion with EmbraceNet, post-processing, and additional processes.
result Improved performance in SHL recognition challenge.
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.
In this paper we demonstrate end-to-end continuous speech recognition (CSR) using electroencephalography (EEG) signals with no speech signal as input. An attention model based automatic speech recognition (ASR) and connectionist temporal classification (CTC) based ASR systems were implemented for performing recognition…
TransFall uses transfer learning to improve activity recognition from mobile sensors.
problem Performance degradation due to platform and user movement differences.
method Two-tier data transformation, label estimation, and model generation layers.
result TransFall enhances activity recognition accuracy for new scenarios.
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.
Neural network framework for language recognition considers sequence information and improves accuracy.
problem Challenging task of automatic language identification in noisy conditions.
method Proposes a neural network framework with bidirectional LSTM and attention modeling for relevance weighting.
result Significant improvements over conventional methods in noisy conditions and multi-speaker speech.
Fawkes protects images from unauthorized facial recognition models.
problem Unauthorized training of facial recognition models poses privacy risks.
method Fawkes adds imperceptible pixel-level changes (cloaks) to images before release.
result Fawkes can protect images from misidentification by 95% and 80% even when clean images are leaked.
Paper proposes a framework to protect user anonymity in emotion recognition.
problem Preserving user anonymity in face-based emotion recognition systems.
method Adversarial learning framework using CNN architecture.
result The proposed approach minimizes identity-specific information and maximizes emotion-dependent information.
Learned feature representations and sub-phoneme posteriors from Deep Neural Networks (DNNs) have been used separately to produce significant performance gains for speaker and language recognition tasks. In this work we show how these gains are possible using a single DNN for both speaker and language recognition. The u…
Study develops sign recognition system for DHH users.
problem Accessibility of voice-controlled devices for Deaf and Hard-of-Hearing users.
method Multimodal data (RGB video and skeletal data) for sign language recognition using deep learning.
result Validation on GMUASL51 dataset of 12 users and 13107 samples across 51 signs.
Random forest can be adapted for open-set recognition with improved performance.
problem Handling unknown classes in real-world classification tasks.
method Incorporating distance metric learning and distance-based open-set recognition into random forest.
result The proposed method outperforms state-of-the-art open-set recognition methods.
This paper presents a novel method for structural data recognition using a large number of graph models. In general, prevalent methods for structural data recognition have two shortcomings: 1) Only a single model is used to capture structural variation. 2) Naive recognition methods are used, such as the nearest neighbo…
Enhances 2D face recognition with 3D features using active illumination.
problem Improving robustness of 2D face recognition to spoofing attacks and low-light conditions.
method Projecting a high spatial frequency pattern onto the face to recover 3D information and a 2D image simultaneously.
result Significantly boosts face recognition performance and dramatically improves robustness to spoofing attacks.
We build CSI-Net, a unified Deep Neural Network~(DNN), to learn the representation of WiFi signals. Using CSI-Net, we jointly solved two body characterization problems: biometrics estimation (including body fat, muscle, water, and bone rates) and person recognition. We also demonstrated the application of CSI-Net on tw…
Improved speech emotion recognition using pre-trained language models.
problem Challenging task of speech emotion recognition for natural human-machine interaction.
method Fine-tuning pre-trained language models for text emotion recognition, combining with speech emotion recognition.
result 73.5% accuracy in speech emotion recognition on a subset of IEMOCAP dataset.
Proves NP and co-NP status for knot core recognition in solid torus.
problem Determining if a knot is the core of a solid torus.
method Alternate proof and corollary of Hopf link recognition problem.
result Proves NP and co-NP status for solid torus core recognition problem.
Todays interactive devices such as smart-phone assistants and smart speakers often deal with short-duration speech segments. As a result, speaker recognition systems integrated into such devices will be much better suited with models capable of performing the recognition task with short-duration utterances. In this pap…
The performance of automatic speech recognition systems(ASR) degrades in the presence of noisy speech. This paper demonstrates that using electroencephalography (EEG) can help automatic speech recognition systems overcome performance loss in the presence of noise. The paper also shows that distillation training of auto…
Deep learning improves speaker recognition verification and identification.
problem Limited progress in speaker recognition for 5-6 years.
method Applied deep learning techniques in speaker verification and identification.
result Deep learning becomes the state-of-the-art solution for speaker recognition.
NIST CTS Superset offers a large dataset for telephony speaker recognition.
problem Lack of a large-scale, uniform dataset for telephony speaker recognition.
method Compilation of speech segments from multiple corpora, including Greybeard, Switchboard, and Mixer series.
result Results on the NIST 2020 CTS Speaker Recognition Challenge serve as a reference baseline.
Study proposes a decision tree for more accurate depression recognition in speech.
problem Subjective bias in traditional depression diagnosis methods.
method A novel speech segment fusion method based on decision tree.
result The proposed decision tree model improves depression classification performance.
FineHand learns hand shapes for better ASL recognition.
problem Difficult ASL recognition due to fast, articulate gestures.
method Combines manual and deep learning for hand shape embeddings, uses RNN for sequential gestures.
result Improved video gesture recognition accuracy on GMU-ASL51 benchmark.
A new approach to unsupervised learning using recognition-parametrised models.
problem Discovering meaningful latent structure in observational data.
method Recognition-Parametrised Model (RPM) combining parametric and non-parametric components.
result Effective learning of latent structure without explicit generative models.
Project extends emotion recognition database and trains neural networks for categorical and dimensional emotions.
problem Understanding and recognizing emotions for human-computer interaction, safety, and medical research.
method Training CNN + RNN models with emotion category and valence/arousal representations, comparing three model types.
result Categorical emotion recognition performance improves with combined model training.
Long Short-Term Memory (LSTM) is a recurrent neural network (RNN) architecture that has been designed to address the vanishing and exploding gradient problems of conventional RNNs. Unlike feedforward neural networks, RNNs have cyclic connections making them powerful for modeling sequences. They have been successfully u…
Personalized activity recognition improves performance for diverse users.
problem Poor performance of impersonal algorithms for individual users.
method Personalized activity recognition using deep embeddings from a fully convolutional neural network with triplet loss.
result Novel subject triplet loss provides the best performance overall.
Current UAV-recorded datasets are mostly limited to action recognition and object tracking, whereas the gesture signals datasets were mostly recorded in indoor spaces. Currently, there is no outdoor recorded public video dataset for UAV commanding signals. Gesture signals can be effectively used with UAVs by leveraging…