A cross-talk robust multichannel VAD model for multiparty agent interactions trained using synthetic re-recordings

In this work, we propose a novel cross-talk rejection framework for a multi-channel multi-talker setup for a live multiparty interactive show. Our far-field audio setup is required to be hands-free during live interaction and comprises four adjacent talkers with directional microphones in the same space. Such setups often introduce heavy cross-talk between channels, resulting in reduced automatic speech recognition (ASR) and natural language understanding (NLU) performance. To address this problem, we propose voice activity detection (VAD) model for all talkers using multichannel information, which is then used to filter audio for downstream tasks. We adopt a synthetic training data generation approach through playback and re-recording for such scenarios, simulating challenging speech overlap conditions. We train our models on this synthetic data and demonstrate that our approach outperforms single-channel VAD models and energy-based multi-channel VAD algorithm in various acoustic environments. In addition to VAD results, we also present multiparty ASR evaluation results to highlight the impact of using our VAD model for filtering audio in downstream tasks by significantly reducing the insertion error.

Biomarker Gene Identification for Breast Cancer Classification

BACKGROUND: Breast cancer has emerged as one of the most prevalent cancers among women leading to a high mortality rate. Due to the heterogeneous nature of breast cancer, there is a need to identify differentially expressed genes associated with breast cancer subtypes for its timely diagnosis and treatment. OBJECTIVE: To identify a small gene set for each of the four breast cancer subtypes that could act as its signature, the paper proposes a novel algorithm for gene signature identification. METHODS: The present work uses interpretable AI methods to investigate the predictions made by the deep neural network employed for subtype classification to identify biomarkers using the TCGA breast cancer RNA Sequence data. RESULTS: The proposed algorithm led to the discovery of a set of 43 differentially expressed gene signatures. We achieved a competitive average 10-fold accuracy of 0.91, using neural network classifier. Further, gene set analysis revealed several relevant pathways, such as GRB7 events in ERBB2 and p53 signaling pathway. Using the Pearson correlation matrix, we noted that the subtype-specific genes are correlated within each subtype. CONCLUSIONS: The proposed technique enables us to find a concise and clinically relevant gene signature set.

Deep Learning Based Model for Breast Cancer Subtype Classification

Breast cancer has long been a prominent cause of mortality among women. Diagnosis, therapy, and prognosis are now possible, thanks to the availability of RNA sequencing tools capable of recording gene expression data. Molecular subtyping being closely related to devising clinical strategy and prognosis, this paper focuses on the use of gene expression data for the classification of breast cancer into four subtypes, namely, Basal, Her2, LumA, and LumB. In stage 1, we suggested a deep learning-based model that uses an autoencoder to reduce dimensionality. The size of the feature set is reduced from 20,530 gene expression values to 500 by using an autoencoder. This encoded representation is passed to the deep neural network of the second stage for the classification of patients into four molecular subtypes of breast cancer. By deploying the combined network of stages 1 and 2, we have been able to attain a mean 10-fold test accuracy of 0.907 on the TCGA breast cancer dataset. The proposed framework is fairly robust throughout 10 different runs, as shown by the boxplot for classification accuracy. Compared to related work reported in the literature, we have achieved a competitive outcome. In conclusion, the proposed two-stage deep learning-based model is able to accurately classify four breast cancer subtypes, highlighting the autoencoder's capacity to deduce the compact representation and the neural network classifier's ability to correctly label breast cancer patients.

Exploring the limits of Concurrency in ML Training on Google TPUs

Recent results in language understanding using neural networks have required training hardware of unprecedentedscale, with thousands of chips cooperating on a single training run. This paper presents techniques to scaleML models on the Google TPU Multipod, a mesh with 4096 TPU-v3 chips. We discuss model parallelism toovercome scaling limitations from the fixed batch size in data parallelism, communication/collective optimizations,distributed evaluation of training metrics, and host input processing scaling optimizations. These techniques aredemonstrated in both the TensorFlow and JAX programming frameworks. We also present performance resultsfrom the recent Google submission to the MLPerf-v0.7 benchmark contest, achieving record training times from16 to 28 seconds in four MLPerf models on the Google TPU-v3 Multipod machine.

COV-ELM classifier: An Extreme Learning Machine based identification of COVID-19 using Chest X-Ray Images

Coronaviruses constitute a family of virus that gives rise to respiratory diseases. Coronavirus disease 2019 (COVID-19) is an infectious disease caused by a newly discovered coronavirus also termed as Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Due to its rapid spread, WHO has declared COVID-19 outbreak a pandemic on 11th March 2020. Reverse transcription-polymerase chain reaction (RT-PCR) test is popularly used worldwide for the detection of COVID-19. However, due to the high false-negative rate of RT-PCR test, chest X-ray (CXR) imaging is emerging as a feasible alternative for the detection of COVID-19. In this work, we propose a multiclass classification model COV-ELM, based on the extreme learning machine which classifies the CXR images into one of the three classes, namely COVID-19, normal, and pneumonia. The choice of ELM in this work has been motivated by its significantly short training time as compared to conventional gradient-based learning algorithms. After some preprocessing, we extract a pool of features based on texture and frequency. This pool of features serves as an input to the ELM and a 10-fold cross-validation method is employed to evaluate the proposed model. For experimentation, we use chest X-ray (CXR) images from three publicly available sources. The results of applying COV-ELM on test data are quite promising. The COV-ELM achieved a macro average F1-score of 0.95 and the overall sensitivity of ${0.94 \pm 0.02}$ at 95% confidence interval. When compared to state-of-the-art machine learning algorithms, the COV-ELM is found to outperform in a three-class classification scenario. The main advantage of COV-ELM is that its training time being quite low, as bigger and diverse datasets become available, it can be quickly retrained as compared to its gradient-based competitor models.

COV-ELM classifier: An Extreme Learning Machine based identification of COVID-19 using Chest-Ray Images

Background and Objective: COVID-19 outbreak was declared as a pandemic on 11th March 2020. The rapid spread of this highly infectious virus has distinguished it from other classes of viral and respiratory diseases. The reverse transcription-polymerase chain reaction (RT-PCR) test is most commonly used for the qualitative assessment of the presence of SARS-CoV-2. Due to the high false-negative rate of RT-PCR tests reported worldwide, chest x-ray imaging has proved to be a feasible alternative for the detection of COVID-19. The COV-ELM classifier aims to classify COVID-19 cases from the chest x-ray images using extreme learning machine (ELM). The choice of ELM in this work is based on the fact that ELM significantly shortens the training time with the least interventions required to tune the networks as compared to other neural networks. Methods: The proposed work is experimented on the COVID-19 chest x-ray (CXR) image data collected from three publicly available sources. The image data is preprocessed and local patterns are extracted by exploiting the frequency and texture regions to generate a feature pool. This pool of features is provided as an input to the ELM and a 10-fold cross-validation method is employed to evaluate the proposed model. Results: The proposed method achieved a macro average of f1-score is 0.95 in a three-class classification scenario. The overall sensitivity of the COV-ELM classifier is ${0.94 \pm 0.03}$ at 95% confidence interval. Conclusions: The COV-ELM outperforms other competitive machine learning algorithms in a multi-class classification scenario. The results of COV-ELM are quite promising which increases its suitability to be applied to bigger and more diverse datasets.