Related papers: Uncertainty Quantification in Machine Learning for…

Speaker recognition systems based on deep speaker embeddings have achieved significant performance in controlled conditions according to the results obtained for early NIST SRE (Speaker Recognition Evaluation) datasets. From the practical…

Machine learning (ML) systems are increasingly deployed in high-stakes domains where reliability is paramount. This thesis investigates how uncertainty estimation can enhance the safety and trustworthiness of ML, focusing on selective…

The current monaural state of the art tools for speech separation relies on supervised learning. This means that they must deal with permutation problem, they are impacted by the mismatch on the number of speakers used in training and…

Source separation (SS) aims to separate individual sources from an audio recording. Sound event detection (SED) aims to detect sound events from an audio recording. We propose a joint separation-classification (JSC) model trained only on…

Speaker embeddings are promising identity-related features that can enhance the identity assignment performance of a tracking system by leveraging its spatial predictions, i.e, by performing identity reassignment. Common speaker embedding…

Speaker identification systems are deployed in diverse environments, often different from the lab conditions on which they are trained and tested. In this paper, first, we show the problem of generalization using fixed thresholds (computed…

The task of estimating the maximum number of concurrent speakers from single channel mixtures is important for various audio-based applications, such as blind source separation, speaker diarisation, audio surveillance or auditory scene…

Multi-microphone speech enhancement using deep neural networks (DNNs) has significantly progressed in recent years. However, many proposed DNN-based speech enhancement algorithms cannot be implemented on devices with limited hardware…

In recent years, the remarkable advancements in deep neural networks have brought tremendous convenience. However, the training process of a highly effective model necessitates a substantial quantity of samples, which brings huge potential…

In reverberant conditions with multiple concurrent speakers, each microphone acquires a mixture signal of multiple speakers at a different location. In over-determined conditions where the microphones out-number speakers, we can narrow down…

While deep neural networks have shown impressive results in automatic speaker recognition and related tasks, it is dissatisfactory how little is understood about what exactly is responsible for these results. Part of the success has been…

In this paper, we address the problem of multichannel speech enhancement in the short-time Fourier transform (STFT) domain. A long short-time memory (LSTM) network takes as input a sequence of STFT coefficients associated with a frequency…

Determining 'who spoke what and when' remains challenging in real-world applications. In typical scenarios, Speaker Diarization (SD) is employed to address the problem of 'who spoke when,' while Target Speaker Extraction (TSE) or Target…

The diverse perceptual consequences of hearing loss severely impede speech communication, but standard clinical audiometry, which is focused on threshold-based frequency sensitivity, does not adequately capture deficits in frequency and…

Estimating the fundamental frequency, or melody, is a core task in Music Information Retrieval (MIR). Various studies have explored signal processing, machine learning, and deep-learning-based approaches, with a very recent focus on…

Mel-scale spectrum features are used in various recognition and classification tasks on speech signals. There is no reason to expect that these features are optimal for all different tasks, including speaker verification (SV). This paper…

Accurate uncertainty quantification is critical for reliable predictive modeling. Existing methods typically address either aleatoric uncertainty due to measurement noise or epistemic uncertainty resulting from limited data, but not both in…

Attractor-based end-to-end diarization is achieving comparable accuracy to the carefully tuned conventional clustering-based methods on challenging datasets. However, the main drawback is that it cannot deal with the case where the number…

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…

A key task for speech recognition systems is to reduce the mismatch between training and evaluation data that is often attributable to speaker differences. Speaker adaptation techniques play a vital role to reduce the mismatch. Model-based…