Related papers: Effects of language mismatch in automatic forensic…

Acoustic word embeddings are fixed-dimensional representations of variable-length speech segments. In settings where unlabelled speech is the only available resource, such embeddings can be used in "zero-resource" speech search, indexing…

This chapter describes a number of signal-processing and statistical-modeling techniques that are commonly used to calculate likelihood ratios in human-supervised automatic approaches to forensic voice comparison. Techniques described…

Despite the significant improvements in speaker recognition enabled by deep neural networks, unsatisfactory performance persists under noisy environments. In this paper, we train the speaker embedding network to learn the "clean" embedding…

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,…

When speaking in presence of background noise, humans reflexively change their way of speaking in order to improve the intelligibility of their speech. This reflex is known as Lombard effect. Collecting speech in Lombard conditions is…

Recent progress in generative AI has made it increasingly easy to create natural-sounding deepfake speech from just a few seconds of audio. While these tools support helpful applications, they also raise serious concerns by making it…

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 presents an improved deep embedding learning method based on convolutional neural network (CNN) for text-independent speaker verification. Two improvements are proposed for x-vector embedding learning: (1) Multi-scale convolution…

Distributed language representation has become the most widely used technique for language representation in various natural language processing tasks. Most of the natural language processing models that are based on deep learning…

End-to-end acoustic-to-word speech recognition models have recently gained popularity because they are easy to train, scale well to large amounts of training data, and do not require a lexicon. In addition, word models may also be easier to…

Investigating linguistic relationships on a global scale requires analyzing diverse features such as syntax, phonology and prosody, which evolve at varying rates influenced by internal diversification, language contact, and sociolinguistic…

Deep speaker embeddings have been shown effective for assessing cognitive impairments aside from their original purpose of speaker verification. However, the research found that speaker embeddings encode speaker identity and an array of…

Word alignment over parallel corpora has a wide variety of applications, including learning translation lexicons, cross-lingual transfer of language processing tools, and automatic evaluation or analysis of translation outputs. The great…

While speaker adaptation for end-to-end speech synthesis using speaker embeddings can produce good speaker similarity for speakers seen during training, there remains a gap for zero-shot adaptation to unseen speakers. We investigate…

Multilingual automatic speech recognition (ASR) systems mostly benefit low resource languages but suffer degradation in performance across several languages relative to their monolingual counterparts. Limited studies have focused on…

This paper proposes novel algorithms for speaker embedding using subjective inter-speaker similarity based on deep neural networks (DNNs). Although conventional DNN-based speaker embedding such as a $d$-vector can be applied to…

Pre-trained models (PTMs) have shown great promise in the speech and audio domain. Embeddings leveraged from these models serve as inputs for learning algorithms with applications in various downstream tasks. One such crucial task is Speech…

Recent research has shown that word embedding spaces learned from text corpora of different languages can be aligned without any parallel data supervision. Inspired by the success in unsupervised cross-lingual word embeddings, in this paper…

While Vision-Language Models (VLMs) and Multimodal Large Language Models (MLLMs) have shown strong generalisation in detecting image and video deepfakes, their use for audio deepfake detection remains largely unexplored. In this work, we…

Verifying the identity of a speaker is crucial in modern human-machine interfaces, e.g., to ensure privacy protection or to enable biometric authentication. Classical speaker verification (SV) approaches estimate a fixed-dimensional…