Related papers: Causal-Anticausal Decomposition of Speech using Co…
We augment the nonnegative matrix factorization method for audio source separation with cues about directionality of sound propagation. This improves separation quality greatly and removes the need for training data, with only a twofold…
This paper addresses the problem of automatic detection of voice pathologies directly from the speech signal. For this, we investigate the use of the glottal source estimation as a means to detect voice disorders. Three sets of features are…
To further improve the speaking styles of synthesized speeches, current text-to-speech (TTS) synthesis systems commonly employ reference speeches to stylize their outputs instead of just the input texts. These reference speeches are…
For individuals who have experienced traumatic events such as strokes, speech may no longer be a viable means of communication. While text-to-speech (TTS) can be used as a communication aid since it generates synthetic speech, it fails to…
Ultrasound computed tomography (USCT) holds great promise for improving the detection and management of breast cancer. Because they are based on the acoustic wave equation, waveform inversion-based reconstruction methods can produce images…
Multimodal Large Language Models (MLLMs) excel in Open-Vocabulary (OV) emotion recognition but often neglect fine-grained acoustic modeling. Existing methods typically use global audio encoders, failing to capture subtle, local temporal…
Temporal reasoning is an important aspect of video analysis. 3D CNN shows good performance by exploring spatial-temporal features jointly in an unconstrained way, but it also increases the computational cost a lot. Previous works try to…
Majority of the recent approaches for text-independent speaker recognition apply attention or similar techniques for aggregation of frame-level feature descriptors generated by a deep neural network (DNN) front-end. In this paper, we…
End-to-end approaches open a new way for more accurate and efficient spoken language understanding (SLU) systems by alleviating the drawbacks of traditional pipeline systems. Previous works exploit textual information for an SLU model via…
While flow-matching text-to-speech (TTS) achieves strong zero-shot speaker similarity and naturalness, it remains susceptible to content fidelity issues, particularly skip and repeat errors from imperfect alignment. We propose…
Structured data offers a sophisticated mechanism for the organization of information. Existing methodologies for the text-serialization of structured data in the context of large language models fail to adequately address the heterogeneity…
Speech separation has recently made significant progress thanks to the fine-grained vision used in time-domain methods. However, several studies have shown that adopting Short-Time Fourier Transform (STFT) for feature extraction could be…
As an old and widely used tool, it is still possible to find new insights and applications from Fast Fourier Transform (FFT)-based analyses. The FFT is frequently used to generate the Power Spectral Density (PSD) function, by squaring the…
The diffusion models including Denoising Diffusion Probabilistic Models (DDPM) and score-based generative models have demonstrated excellent performance in speech synthesis tasks. However, its effectiveness comes at the cost of numerous…
While measurement advances now allow extensive surveys of gene activity (large numbers of genes across many samples), interpretation of these data is often confounded by noise -- expression counts can differ strongly across samples due to…
Extraction of concepts present in patient clinical records is an essential step in clinical research. The 2010 i2b2/VA Workshop on Natural Language Processing Challenges for clinical records presented concept extraction (CE) task, with aim…
Recent deep learning-based optical flow estimators have exhibited impressive performance in generating local flows between consecutive frames. However, the estimation of long-range flows between distant frames, particularly under complex…
Large Foundational Language Models are capable of performing many tasks at a high level but are difficult to deploy in many applications because of their size and proprietary ownership. Many will be motivated to distill specific…
Source analysis of Electroencephalography (EEG) data requires the computation of the scalp potential induced by current sources in the brain. This so-called EEG forward problem is based on an accurate estimation of the volume conduction…
Generative models have shown robust performance on speech enhancement and restoration tasks, but most prior approaches operate offline with high latency, making them unsuitable for streaming applications. In this work, we investigate the…