Related papers: Tied Probabilistic Linear Discriminant Analysis fo…

In forensic voice comparison the speaker embedding has become widely popular in the last 10 years. Most of the pretrained speaker embeddings are trained on English corpora, because it is easily accessible. Thus, language dependency can be…

Recent research demonstrates the effectiveness of using pretrained language models (PLM) to improve dense retrieval and multilingual dense retrieval. In this work, we present a simple but effective monolingual pretraining task called…

Utilizing language models (LMs) without internal access is becoming an attractive paradigm in the field of NLP as many cutting-edge LMs are released through APIs and boast a massive scale. The de-facto method in this type of black-box…

In this paper, we analyze the behavior and performance of speaker embeddings and the back-end scoring model under domain and language mismatch. We present our findings regarding ResNet-based speaker embedding architectures and show that…

This paper proposes a probabilistic neural network developed on the basis of time-series discriminant component analysis (TSDCA) that can be used to classify high-dimensional time-series patterns. TSDCA involves the compression of…

Numerous examples in the literature proved that deep learning models have the ability to work well with multimodal data. Recently, CLIP has enabled deep learning systems to learn shared latent spaces between images and text descriptions,…

We present MooseNet, a trainable speech metric that predicts the listeners' Mean Opinion Score (MOS). We propose a novel approach where the Probabilistic Linear Discriminative Analysis (PLDA) generative model is used on top of an embedding…

Distributed dense word vectors have been shown to be effective at capturing token-level semantic and syntactic regularities in language, while topic models can form interpretable representations over documents. In this work, we describe…

In this article we propose and validate an unsupervised probabilistic model, Gaussian Latent Dirichlet Allocation (GLDA), for the problem of discrete state discovery from repeated, multivariate psychophysiological samples collected from…

To join the advantages of classical and end-to-end approaches for speech recognition, we present a simple, novel and competitive approach for phoneme-based neural transducer modeling. Different alignment label topologies are compared and…

Although masked language models are highly performant and widely adopted by NLP practitioners, they can not be easily used for autoregressive language modelling (next word prediction and sequence probability estimation). We present an…

Speaker verification system trained on one domain usually suffers performance degradation when applied to another domain. To address this challenge, researchers commonly use feature distribution matching-based methods in unsupervised domain…

Most state-of-the-art spoken language identification models are closed-set; in other words, they can only output a language label from the set of classes they were trained on. Open-set spoken language identification systems, however, gain…

The growing number of generative AI-based dialogue systems has made their evaluation a crucial challenge. This paper presents our contribution to this important problem through the Dialogue System Technology Challenge (DSTC-12, Track 1),…

We propose an approach for continuous prediction of turn-taking and backchanneling locations in spoken dialogue by fusing a neural acoustic model with a large language model (LLM). Experiments on the Switchboard human-human conversation…

The widespread adoption of mobile communication technology has led to a severe shortage of spectrum resources, driving the development of cognitive radio technologies aimed at improving spectrum utilization, with spectrum sensing being the…

We propose an end-to-end joint optimization framework of a multi-channel neural speech extraction and deep acoustic model without mel-filterbank (FBANK) extraction for overlapped speech recognition. First, based on a multi-channel…

A fundamental challenge in neuroscience is to understand what structure in the world is represented in spatially distributed patterns of neural activity from multiple single-trial measurements. This is often accomplished by learning a…

We investigate deep neural network performance in the textindependent speaker recognition task. We demonstrate that using angular softmax activation at the last classification layer of a classification neural network instead of a simple…

Attention-based models have recently shown great performance on a range of tasks, such as speech recognition, machine translation, and image captioning due to their ability to summarize relevant information that expands through the entire…