Related papers: Learning spectro-temporal representations of compl…

We present TVF (Time-Varying Filtering), a low-latency speech enhancement model with 1 million parameters. Combining the interpretability of Digital Signal Processing (DSP) with the adaptability of deep learning, TVF bridges the gap between…

Speaker diarization is a task to label audio or video recordings with classes that correspond to speaker identity, or in short, a task to identify "who spoke when". In the early years, speaker diarization algorithms were developed for…

Multivariate time series have many applications, from healthcare and meteorology to life science. Although deep learning models have shown excellent predictive performance for time series, they have been criticised for being "black-boxes"…

This paper proposes a neural network based speech separation method using spatially distributed microphones. Unlike with traditional microphone array settings, neither the number of microphones nor their spatial arrangement is known in…

Speech separation refers to extracting each individual speech source in a given mixed signal. Recent advancements in speech separation and ongoing research in this area, have made these approaches as promising techniques for pre-processing…

Neural speaker embeddings trained using classification objectives have demonstrated state-of-the-art performance in multiple applications. Typically, such embeddings are trained on an out-of-domain corpus on a single task e.g., speaker…

Both speech and sensor time series data encode information in both the time- and frequency- domains, like spectral powers and waveform shapelets. We show that speech foundation models learn representations that generalize beyond the speech…

What do deep neural speech models know about phonology? Existing work has examined the encoding of individual linguistic units such as phonemes in these models. Here we investigate interactions between units. Inspired by classic experiments…

Respiratory diseases remain major global health challenges, and traditional auscultation is often limited by subjectivity, environmental noise, and inter-clinician variability. This study presents an explainable multimodal deep learning…

Nearly all Statistical Parametric Speech Synthesizers today use Mel Cepstral coefficients as the vocal tract parameterization of the speech signal. Mel Cepstral coefficients were never intended to work in a parametric speech synthesis…

Our ability to comprehend speech remains, to date, unrivaled by deep learning models. This feat could result from the brain's ability to fine-tune generic sound representations for speech-specific processes. To test this hypothesis, we…

We address the problem of acoustic source separation in a deep learning framework we call "deep clustering." Rather than directly estimating signals or masking functions, we train a deep network to produce spectrogram embeddings that are…

This paper presents a self-supervised learning framework, named MGF, for general-purpose speech representation learning. In the design of MGF, speech hierarchy is taken into consideration. Specifically, we propose to use generative learning…

Improving the interpretability of deep neural networks has recently gained increased attention, especially when the power of deep learning is leveraged to solve problems in physics. Interpretability helps us understand a model's ability to…

Pre-trained deep learning embeddings have consistently shown superior performance over handcrafted acoustic features in speech emotion recognition (SER). However, unlike acoustic features with clear physical meaning, these embeddings lack…

Accurate classification of respiratory sounds requires deep learning models that effectively capture fine-grained acoustic features and long-range temporal dependencies. Convolutional Neural Networks (CNNs) are well-suited for extracting…

Humans can robustly recognize and localize objects by integrating visual and auditory cues. While machines are able to do the same now with images, less work has been done with sounds. This work develops an approach for dense semantic…

To generate actions in the face of physiological delays, the brain must predict the future. Here we explore how prediction may lie at the core of brain function by considering a neuron predicting the future of a scalar time series input.…

This study investigates the explainability of embedding representations, specifically those used in modern audio spoofing detection systems based on deep neural networks, known as spoof embeddings. Building on established work in speaker…

The short-time Fourier transform (STFT) is widely used for analyzing non-stationary signals. However, its performance is highly sensitive to its parameters, and manual or heuristic tuning often yields suboptimal results. To overcome this…