Slovakia

This presentation evaluates results of an ongoing research employing novel offline end-to-end speech recognition models for Slovak language. Transition to ESPnet&#39;s Transformer neural network architecture is introduced along with a brief theoretical introduction to end-to-end based speech recognition.

IWSSIP 2021

Transition from hybrid to end-to-end speech recognition in Slovak utilizing Transformer neural network architecture

slovak language

attention

speech recognition

end-to-end

transformer

**Welcome to ACL-IJCNLP 2021!**

The great event is jointly organized by the Association for Computational Linguistics (ACL) and Asian Federation of Natural Language Processing (AFNLP). 

As in previous years, the program of the conference includes a poster session, tutorials, workshops and demonstrations in addition to the main conference.


We were able to keep the registration fees similar to those charged for the virtual ACL 2020. The one fee allows attendance at the main conference and any/all tutorials and workshops. These fees would be $125 Regular Early and $175 Regular Late; $50 Student Early and $75 Student Late. Early registration closes at midnight July 11, 2021 (Eastern Daylight Time).

**Reminder:** It is ACL’s policy that at least one author of each accepted paper (including ACL Finding papers) must register for the conference.

**Reminder2:** Underline site will open closer to the event. If you already registered you will receive access detail

Registration is now open

ACL-IJCNLP 2021

The great event is jointly organized by the Association for Computational Linguistics (ACL) and Asian Federation of Natural Language Processing (AFNLP).

This presentation evaluates results of an ongoing research employing novel offline end-to-end speech recognition models for Slovak language. Transition to ESPnet's Transformer neural network architecture is introduced along with a brief theoretical introduction to end-to-end based speech recognition.

technical paper


IWSSIP is an international conference that brings together researchers and developers from both academia and industry reporting the latest scientific and theoretical advances to discuss and debate major issues and state-of-the-art aspects on systems, signals and image processing.

###### For the session discussion, each author will be seated at individual breakout tables.  Please find which table they will be at here:
###### [QA table assignments in Gather.town](https://drive.google.com/file/d/1hBHOD_KF7NSsaTcpYcHCZslXJvQVxJQe/view?usp=sharing)

The aim of this paper is to present a method for source detection within unknown mixtures using several measurement modalities. Contrary to the well studied case of single source detection, this approach enables simultaneous detection of multiple sources by exploiting the mixing coefficients resulting from supervised linear unmixing and thresholded non-negative least squares. The first contribution of this work is to propose an automated procedure to compute an optimized binary classifier rule for each source independently using a database of known mixtures. The second contribution is to propose a global decision rule based on the fusion of the multimodal decisions using weighting schemes such as those used in multiple classifier systems (MCS). A real database of Ion Mobiliy Mass Spectrometry (IMMS) data is used to evaluate the detection performance. An increase of the detection accuracy is reached using the multiple thresholds within the independent classifiers approach as compared to single modality detection.

Supervised Mixture Analysis and Source Detection from Multimodal Measurements

"In this work, we present a viewpoint selection method specif-
ically designed for fibrous structures in a pre-operative context. A view
quality metric based on entropy was developed, which integrates the typ-
ical requirements of surgery planning. We applied our approach in the
case of cranial nerves surrounding skull base tumors. The relevance of the
viewpoints selected by our method was assessed qualitatively by a neu-
rosurgeon and quantitatively based on statistical tests. These viewpoints
were proven to have a high informative content, and therefore to enable a
good understanding and mental representation the 3D anatomical scene
in a pre-operative context."

Viewpoint selection for fibrous structures in a pre-operative context: application to cranial nerves surrounding skull base tumors

In this work we perform a detailed study in which we dissect whether or not the use of a dataset with only a single sample taken from some writers may skew the results. In this sense, we propose here what we call "Document Filter".

Document Filter for Writer Identification

"We create a compact 3D model-based gait feature out of
2D images using DensePose. We also design a CNN to show that the
obtained gait feature can be used to improve recognition. Results are
based on the publicly available CASIA-B dataset."

Gait Recognition with DensePose Energy Images

Monitoring plant growth with computer vision is an important topic in plant science. This monitoring can be challenging when plants are located in outdoor conditions due to light variations and other noises. On other hand, there is a lack of annotated datasets available for such outdoor environments to train machine learning algorithms while indoor similar datasets may be more easily available. In this communication, we investigate, for the first time to the best of our knowledge in plant imaging, how to take benefit from model trained in fully controlled environment to build model for an outdoor environment. This is illustrated with the prediction of seedling development from top view RGB images.  

Deep learning-based detection of seedling development from indoor to outdoor

"Due to the omnipresence of computers today, the need for forensic experts has increased. Much of the knowledge associated with digital forensics has become common and has found its way to universities through courses or study programs.
As with many other domains related to computer engineering, computer forensics is based on theoretical concepts which must become integrated into skills and those skills serve as foundations of competence. For example, computer forensics experts must be able to recover data from a deleted file or reconstruct the sequence of actions in a cyberattack. Assessment is, therefore, a necessary precondition of effective computer forensics training and outcomes evaluation. Skills related to computer forensics should be acquired through practice and assessed in an authentic environment, yet that is difficult to achieve since the development of a large number of custom problems for assessing them is timeconsuming. This paper describes an approach to addressing this issue with a system for automatic generation and scoring of individualized and authentic computer forensics problems. Problem types and system implementation details are described in the paper."

Computer forensics problem generator for competence assessment

"This work presents the computer vision and machine learn-
ing techniques used in an implementation of a prototype system to aid
on understanding DICOM exams. In such a way, all aspects included
from the image prepossessing to identification and final classification of
bone anomalies by the digital bone scintigraphy images are commended
in details. It is possible to state that these used techniques are very
promising, because although, there are few patients already included for
leaning, the results obtained in the tested phase achieved more than
seventy percent of correction when used with Decision Tree (DT) and
k-Nearest Neighbors (K-NN) classification algorithms."

Presenting a system to aid on the scintigraphy bone metastasis analysis using DICOM files

Sparse representation and compressive sensing theory is wide used in image processing with the core idea that given a transformation that describes a signal in sparse domain can be achieved a moore compact and thus compressed form of the signal through optimization. In this research discrete orthogonal moments transforms are applied in sparse representation and compressive sensing theory under the implementation of transformed-based compressive sensing. Finally a comparison take place between image moments transforms and DCT in compression and denoising. 

Moment transform-based Compressive Sensing in Image Processing

Particle colliders are machines built to probe fundamental questions in physics. The properties of the produced particles are measured by complex experiments which use a wide variety of devices, such as the calorimeter system. In the ATLAS experiment at LHC, the Tile Calorimeter (TileCal) comprises about 10,000 readout channels that amplify, shape, and sample each signal every 25 ns. Since LHC collisions occur every 25 ns, and due to the increase of the luminosity level, signals from adjacent collisions may be read out within the same TileCal readout window, deforming the expected signal, and degrading the energy estimation efficiency. Therefore, this work compares the performance of the currently available methods for TileCal energy estimation using LHC collision data. Different pile-up conditions are considered. The results show that the performance in terms of the uncertainty of the energy estimation can be improved up to 35% in high occupancy readout channels.

Energy Reconstruction Techniques in TileCal under High Pile-up Conditions

Automatic cardiac MRI segmentation, including left and rightventricular endocardium and epicardium, has an essential role in clinical  diagnosis  by  providing  crucial  information  about  cardiac  function. Determining heart chamber properties, such as volume or ejection fraction,  directly  relies  on  their  accurate  segmentation.  In  this  work,  we propose a new automatic method for the segmentation of myocardium, left, and right ventricles from MRI images. We introduce a new archi-tecture that incorporates SERes blocks into 3D U-net architecture (3DSERes-U-Net). The SERes blocks incorporate squeeze-and-excitation operations into residual learning. The adaptive feature recalibration ability of squeeze-and-excitation operations boosts the network’s representational power while feature reuse utilizes effective learning of the features,which  improves  segmentation  performance.  We  evaluate  the  proposedmethod on the testing dataset of the MICCAI Automated Cardiac Diag-nosis Challenge (ACDC) dataset and obtain highly comparable resultsto the state-of-the-art methods

Premium content

Transition from hybrid to end-to-end speech recognition in Slovak utilizing Transformer neural network architecture

Downloads

Next from IWSSIP 2021

Supervised Mixture Analysis and Source Detection from Multimodal Measurements

Similar lecture

AdaST: Dynamically Adapting Encoder States in the Decoder for End-to-End Speech-to-Text Translation