No abstract

Automatic Speech Recognition, (ASR) has achieved the best results for English, with end-to-end neural network based supervised models. These supervised models need huge amounts of labeled speech data for good generalization, which can be quite a challenge to obtain for low-resource languages like Urdu. Most models proposed for Urdu ASR are based on Hidden Markov Models (HMMs). This paper proposes an end-to-end neural network model, for Urdu ASR, regularized with dropout, ensemble averaging and Maxout units. Dropout and ensembles are averaging techniques over multiple neural network models while Maxout are units in a neural network which adapt their activation functions. Due to limited labeled data, Semi Supervised Learning (SSL) techniques are also incorporated to improve model generalization. Speech features are transformed into a lower dimensional manifold using an unsupervised dimensionality-reduction technique called Locally Linear Embedding (LLE). Transformed data along with higher dimensional features is used to train neural networks. The proposed model also utilizes label propagation-based self-training of initially trained models and achieves a Word Error Rate (WER) of 4% less than that reported as the benchmark on the same Urdu corpus using HMM. The decrease in WER after incorporating SSL is more significant with an increased validation data size.

Laser-induced breakdown spectroscopy (LIBS) was used for the quantitative analysis of elements present in textile dyes at ambient pressure via the fundamental mode (1064 nm) of a Nd:YAG pulsed laser. Three samples were collected for this purpose. Spectra of textile dyes were acquired using an HR spectrometer (LIBS2000+, Ocean Optics, Inc.) having an optical resolution of 0.06 nm in the spectral range of 200 to 720 nm. Toxic metals like Cr, Cu, Fe, Ni, and Zn along with other elements like Al, Mg, Ca, and Na were revealed to exist in the samples. The %-age concentrations of the detected elements were measured by means of standard calibration curve method, intensities of every emission from every species, and calibration-free (CF) LIBS approach. Only Sample 3 was found to contain heavy metals like Cr, Cu, and Ni above the prescribed limit. The results using LIBS were found to be in good agreement when compared to outcomes of inductively coupled plasma/atomic emission spectroscopy (ICP/AES).

No abstract

No abstract