Related papers: GCI detection from raw speech using a fully-convol…
Detecting synthetic from real speech is increasingly crucial due to the risks of misinformation and identity impersonation. While various datasets for synthetic speech analysis have been developed, they often focus on specific areas,…
This thesis presents advancements in the detection of gravitational waves from compact binary coalescences, utilising the most sensitive observatories constructed to date. The research focuses on enhancing gravitational-wave signal searches…
Starting with a collection of traces generated by process executions, process discovery is the task of constructing a simple model that describes the process, where simplicity is often measured in terms of model size. The challenge of…
We propose a method to reduce false voice triggers of a speech-enabled personal assistant by post-processing the hypothesis lattice of a server-side large-vocabulary continuous speech recognizer (LVCSR) via a neural network. We first…
3D open-vocabulary scene understanding, crucial for advancing augmented reality and robotic applications, involves interpreting and locating specific regions within a 3D space as directed by natural language instructions. To this end, we…
Intrinsic image decomposition is a challenging, long-standing computer vision problem for which ground truth data is very difficult to acquire. We explore the use of synthetic data for training CNN-based intrinsic image decomposition…
Mask processing in the time-frequency (T-F) domain through the neural network has been one of the mainstreams for single-channel speech enhancement. However, it is hard for most models to handle the situation when harmonics are partially…
Attempts to develop speech enhancement algorithms with improved speech intelligibility for cochlear implant (CI) users have met with limited success. To improve speech enhancement methods for CI users, we propose to perform speech…
Contemporary Human Computer Interaction (HCI) research relies primarily on neural network models for machine vision and speech understanding of a system user. Such models require extensively annotated training datasets for optimal…
We present a novel approach to improve the performance of learning-based speech dereverberation using accurate synthetic datasets. Our approach is designed to recover the reverb-free signal from a reverberant speech signal. We show that…
Automatic emotion recognition for real-life appli-cations is a challenging task. Human emotion expressions aresubtle, and can be conveyed by a combination of several emo-tions. In most existing emotion recognition studies, each…
Brain-Computer Interfaces (BCIs) rely on accurately decoding electroencephalography (EEG) motor imagery (MI) signals for effective device control. Graph Neural Networks (GNNs) outperform Convolutional Neural Networks (CNNs) in this regard,…
Incremental text-to-speech (TTS) synthesis generates utterances in small linguistic units for the sake of real-time and low-latency applications. We previously proposed an incremental TTS method that leverages a large pre-trained language…
The intelligibility of natural speech is seriously degraded when exposed to adverse noisy environments. In this work, we propose a deep learning-based speech modification method to compensate for the intelligibility loss, with the…
The recent developments in technology have re-warded us with amazing audio synthesis models like TACOTRON and WAVENETS. On the other side, it poses greater threats such as speech clones and deep fakes, that may go undetected. To tackle…
To progress in the characterization of noise for current quantum computers, gate set tomography (GST) has emerged as a self-consistent tomographic protocol that can accurately estimate the complete set of noisy quantum gates, state…
Grammatical error correction (GEC) is one of the areas in natural language processing in which purely neural models have not yet superseded more traditional symbolic models. Hybrid systems combining phrase-based statistical machine…
A brain-computer interface (BCI) based on the motor imagery (MI) paradigm translates one's motor intention into a control signal by classifying the Electroencephalogram (EEG) signal of different tasks. However, most existing systems either…
An important and difficult task in code-switched speech recognition is to recognize the language, as lots of words in two languages can sound similar, especially in some accents. We focus on improving performance of end-to-end Automatic…
Language models (LMs) are increasingly extended with new learnable vocabulary tokens for domain-specific tasks, such as Semantic-ID tokens in generative recommendation. The standard practice initializes these new tokens as the mean of…