Search Results for author: Siddique Latif

Found 18 papers, 2 papers with code

Controlling Prosody in End-to-End TTS: A Case Study on Contrastive Focus Generation

no code implementations CoNLL (EMNLP) 2021 Siddique Latif, Inyoung Kim, Ioan Calapodescu, Laurent Besacier

In this paper, we investigate whether we can control prosody directly from the input text, in order to code information related to contrastive focus which emphasizes a specific word that is contrary to the presuppositions of the interlocutor.

MESAHA-Net: Multi-Encoders based Self-Adaptive Hard Attention Network with Maximum Intensity Projections for Lung Nodule Segmentation in CT Scan

no code implementations4 Apr 2023 Muhammad Usman, Azka Rehman, Abdullah Shahid, Siddique Latif, Shi Sub Byon, Sung Hyun Kim, Tariq Mahmood Khan, Yeong Gil Shin

By employing a novel adaptive hard attention mechanism, MESAHA-Net iteratively performs slice-by-slice 2D segmentation of lung nodules, focusing on the nodule region in each slice to generate 3D volumetric segmentation of lung nodules.

Computed Tomography (CT) Decoder +4

Transformers in Speech Processing: A Survey

no code implementations21 Mar 2023 Siddique Latif, Aun Zaidi, Heriberto Cuayahuitl, Fahad Shamshad, Moazzam Shoukat, Junaid Qadir

The remarkable success of transformers in the field of natural language processing has sparked the interest of the speech-processing community, leading to an exploration of their potential for modeling long-range dependencies within speech sequences.

Automatic Speech Recognition Speech Enhancement +4

MEDS-Net: Self-Distilled Multi-Encoders Network with Bi-Direction Maximum Intensity projections for Lung Nodule Detection

no code implementations30 Oct 2022 Muhammad Usman, Azka Rehman, Abdullah Shahid, Siddique Latif, Shi Sub Byon, Byoung Dai Lee, Sung Hyun Kim, Byung il Lee, Yeong Gil Shin

Particularly, we exploit Bi-Directional Maximum intensity projection (MIP) images of various thicknesses (i. e., 3, 5 and 10mm) along with a 3D patch of CT scan, consisting of 10 adjacent slices to feed into self-distillation-based Multi-Encoders Network (MEDS-Net).

Lung Nodule Detection

A Survey on Deep Reinforcement Learning for Audio-Based Applications

no code implementations1 Jan 2021 Siddique Latif, Heriberto Cuayáhuitl, Farrukh Pervez, Fahad Shamshad, Hafiz Shehbaz Ali, Erik Cambria

We begin with an introduction to the general field of DL and reinforcement learning (RL), then progress to the main DRL methods and their applications in the audio domain.

Audio Signal Processing reinforcement-learning +1

Deep Representation Learning in Speech Processing: Challenges, Recent Advances, and Future Trends

no code implementations2 Jan 2020 Siddique Latif, Rajib Rana, Sara Khalifa, Raja Jurdak, Junaid Qadir, Björn W. Schuller

Research on speech processing has traditionally considered the task of designing hand-engineered acoustic features (feature engineering) as a separate distinct problem from the task of designing efficient machine learning (ML) models to make prediction and classification decisions.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +6

Pre-training in Deep Reinforcement Learning for Automatic Speech Recognition

no code implementations24 Oct 2019 Thejan Rajapakshe, Rajib Rana, Siddique Latif, Sara Khalifa, Björn W. Schuller

Deep reinforcement learning (deep RL) is a combination of deep learning with reinforcement learning principles to create efficient methods that can learn by interacting with its environment.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

Motion Corrected Multishot MRI Reconstruction Using Generative Networks with Sensitivity Encoding

no code implementations20 Feb 2019 Muhammad Usman, Muhammad Umar Farooq, Siddique Latif, Muhammad Asim, Junaid Qadir

The downside of multishot MRI is that it is very sensitive to subject motion and even small amounts of motion during the scan can produce artifacts in the final MR image that may cause misdiagnosis.

Generative Adversarial Network Motion Correction In Multishot Mri +1

Adversarial Machine Learning And Speech Emotion Recognition: Utilizing Generative Adversarial Networks For Robustness

no code implementations28 Nov 2018 Siddique Latif, Rajib Rana, Junaid Qadir

Deep learning has undoubtedly offered tremendous improvements in the performance of state-of-the-art speech emotion recognition (SER) systems.

Adversarial Attack BIG-bench Machine Learning +2

Automating Motion Correction in Multishot MRI Using Generative Adversarial Networks

no code implementations24 Nov 2018 Siddique Latif, Muhammad Asim, Muhammad Usman, Junaid Qadir, Rajib Rana

Multishot Magnetic Resonance Imaging (MRI) has recently gained popularity as it accelerates the MRI data acquisition process without compromising the quality of final MR image.

Generative Adversarial Network Image Reconstruction +1

Soft Computing Techniques for Dependable Cyber-Physical Systems

no code implementations25 Jan 2018 Muhammad Atif, Siddique Latif, Rizwan Ahmad, Adnan Khalid Kiani, Junaid Qadir, Adeel Baig, Hisao Ishibuchi, Waseem Abbas

Cyber-Physical Systems (CPS) allow us to manipulate objects in the physical world by providing a communication bridge between computation and actuation elements.

Using Deep Autoencoders for Facial Expression Recognition

no code implementations25 Jan 2018 Muhammad Usman, Siddique Latif, Junaid Qadir

Feature descriptors involved in image processing are generally manually chosen and high dimensional in nature.

Dimensionality Reduction Facial Expression Recognition +2

Phonocardiographic Sensing using Deep Learning for Abnormal Heartbeat Detection

no code implementations25 Jan 2018 Siddique Latif, Muhammad Usman, Rajib Rana, Junaid Qadir

Our choice of RNNs is motivated by the great success of deep learning in medical applications and by the observation that RNNs represent the deep learning configuration most suitable for dealing with sequential or temporal data even in the presence of noise.

Heartbeat Classification

Transfer Learning for Improving Speech Emotion Classification Accuracy

1 code implementation19 Jan 2018 Siddique Latif, Rajib Rana, Shahzad Younis, Junaid Qadir, Julien Epps

The majority of existing speech emotion recognition research focuses on automatic emotion detection using training and testing data from same corpus collected under the same conditions.

Classification Cross-corpus +4

Variational Autoencoders for Learning Latent Representations of Speech Emotion: A Preliminary Study

no code implementations23 Dec 2017 Siddique Latif, Rajib Rana, Junaid Qadir, Julien Epps

Inspired by this, we propose VAEs for deriving the latent representation of speech signals and use this representation to classify emotions.

Emotion Classification General Classification +1

Cannot find the paper you are looking for? You can Submit a new open access paper.