Related papers: Zero-Shot to Zero-Lies: Detecting Bengali Deepfake…

Deepfake speech detection presents a growing challenge as generative audio technologies continue to advance. We propose a hybrid training framework that advances detection performance through novel augmentation strategies. First, we…

Although over 300M around the world speak Bangla, scant work has been done in improving Bangla voice-to-text transcription due to Bangla being a low-resource language. However, with the introduction of the Bengali Common Voice 9.0 speech…

Transfer learning (TL) is an increasingly popular approach to training deep learning (DL) models that leverages the knowledge gained by training a foundation model on diverse, large-scale datasets for use on downstream tasks where less…

Although few-shot learning has attracted much attention from the fields of image and audio classification, few efforts have been made on few-shot speaker identification. In the task of few-shot learning, overfitting is a tough problem…

Automatic Speech Recognition (ASR) and speaker diarization in Bangla remain challenging due to long form recordings, diverse acoustic conditions, and significant speaker variability. This work addresses these two core tasks in Bangla spoken…

Generalization is a main issue for current audio deepfake detectors, which struggle to provide reliable results on out-of-distribution data. Given the speed at which more and more accurate synthesis methods are developed, it is very…

Data augmentation is conventionally used to inject robustness in Speaker Verification systems. Several recently organized challenges focus on handling novel acoustic environments. Deep learning based speech enhancement is a modern solution…

Recently, direct modeling of raw waveforms using deep neural networks has been widely studied for a number of tasks in audio domains. In speaker verification, however, utilization of raw waveforms is in its preliminary phase, requiring…

Deepfake videos, produced through advanced artificial intelligence methods now a days, pose a new challenge to the truthfulness of the digital media. As Deepfake becomes more convincing day by day, detecting them requires advanced methods…

Imbalanced datasets can lead to biasedness into the detection of fake news. In this work, we present several strategies for resolving the imbalance issue for fake news detection in Bangla with a comparative assessment of proposed…

Deepfake is content or material that is synthetically generated or manipulated using artificial intelligence (AI) methods, to be passed off as real and can include audio, video, image, and text synthesis. This survey has been conducted with…

Albeit recent progress in speaker verification generates powerful models, malicious attacks in the form of spoofed speech, are generally not coped with. Recent results in ASVSpoof2015 and BTAS2016 challenges indicate that spoof-aware…

Data-driven models achieve successful results in Speech Emotion Recognition (SER). However, these models, which are often based on general acoustic features or end-to-end approaches, show poor performance when the testing set has a…

Recent advances in Deep Learning and Computer Vision have been successfully leveraged to serve marginalized communities in various contexts. One such area is Sign Language - a primary means of communication for the deaf community. However,…

In recent years, neural models trained on large multilingual text and speech datasets have shown great potential for supporting low-resource languages. This study investigates the performances of two state-of-the-art Automatic Speech…

Since the majority of audio DeepFake (DF) detection methods are trained on English-centric datasets, their applicability to non-English languages remains largely unexplored. In this work, we present a benchmark for the multilingual audio DF…

This paper addresses the challenge of developing a robust audio-visual deepfake detection model. In practical use cases, new generation algorithms are continually emerging, and these algorithms are not encountered during the development of…

We present a simple yet effective approach to build multilingual speech-to-text (ST) translation by efficient transfer learning from pretrained speech encoder and text decoder. Our key finding is that a minimalistic LNA (LayerNorm and…

Voice Conversion research in recent times has increasingly focused on improving the zero-shot capabilities of existing methods. Despite remarkable advancements, current architectures still tend to struggle in zero-shot cross-lingual…

This study presents a novel zero-shot user-defined keyword spotting model that utilizes the audio-phoneme relationship of the keyword to improve performance. Unlike the previous approach that estimates at utterance level, we use both…