Related papers: Speaker De-identification System using Autoencoder…

Using our voices to access, and interact with, online services raises concerns about the trade-offs between convenience, privacy, and security. The conflict between maintaining privacy and ensuring input authenticity has often been hindered…

In this article we propose a novel approach for adapting speaker embeddings to new domains based on adversarial training of neural networks. We apply our embeddings to the task of text-independent speaker verification, a challenging,…

A number of studies have successfully developed speaker verification or presentation attack detection systems. However, studies integrating the two tasks remain in the preliminary stages. In this paper, we propose two approaches for…

Data augmentation (DA) has gained widespread popularity in deep speaker models due to its ease of implementation and significant effectiveness. It enriches training data by simulating real-life acoustic variations, enabling deep neural…

Automatic Speech Understanding (ASU) leverages the power of deep learning models for accurate interpretation of human speech, leading to a wide range of speech applications that enrich the human experience. However, training a robust ASU…

The proliferation of speech technologies and rising privacy legislation calls for the development of privacy preservation solutions for speech applications. These are essential since speech signals convey a wealth of rich, personal and…

The audio data is increasing day by day throughout the globe with the increase of telephonic conversations, video conferences and voice messages. This research provides a mechanism for identifying a speaker in an audio file, based on the…

State-of-the-art Deep Learning systems for speaker verification are commonly based on speaker embedding extractors. These architectures are usually composed of a feature extractor front-end together with a pooling layer to encode…

Speaker Verification still suffers from the challenge of generalization to novel adverse environments. We leverage on the recent advancements made by deep learning based speech enhancement and propose a feature-domain supervised denoising…

This paper evaluates the impact of training undergraduate students to improve their audio deepfake discernment ability by listening for expert-defined linguistic features. Such features have been shown to improve performance of AI…

Recent research has delved into speech enhancement (SE) approaches that leverage audio embeddings from pre-trained models, diverging from time-frequency masking or signal prediction techniques. This paper introduces an efficient and…

Speaker embeddings carry valuable emotion-related information, which makes them a promising resource for enhancing speech emotion recognition (SER), especially with limited labeled data. Traditionally, it has been assumed that emotion…

Speaker diarization is a task to label audio or video recordings with classes that correspond to speaker identity, or in short, a task to identify "who spoke when". In the early years, speaker diarization algorithms were developed for…

Self-supervised learning (SSL) has reduced the reliance on expensive labeling in speech technologies by learning meaningful representations from unannotated data. Since most SSL-based downstream tasks prioritize content information in…

Speaker anonymization aims to conceal cues to speaker identity while preserving linguistic content. Current machine learning based approaches require substantial computational resources, hindering real-time streaming applications. To…

Deep learning models, while achieving state-of-the-art performance on many tasks, are susceptible to adversarial attacks that exploit inherent vulnerabilities in their architectures. Adversarial attacks manipulate the input data with…

We present a Lipreading system, i.e. a speech recognition system using only visual features, which uses domain-adversarial training for speaker independence. Domain-adversarial training is integrated into the optimization of a lipreader…

Speaker-independent speech recognition systems trained with data from many users are generally robust against speaker variability and work well for a large population of speakers. However, these systems do not always generalize well for…

The present work is based on the COST Action IC1206 for De-identification in multimedia content. It was performed to test four algorithms of voice modifications on a speech gender recognizer to find the degree of modification of pitch when…

The rapid spread of media content synthesis technology and the potentially damaging impact of audio and video deepfakes on people's lives have raised the need to implement systems able to detect these forgeries automatically. In this work…