Related papers: Loud-loss: A Perceptually Motivated Loss Function …
Acoustic word embeddings (AWEs) are discriminative representations of speech segments, and learned embedding space reflects the phonetic similarity between words. With multi-view learning, where text labels are considered as supplementary…
Popular rotated detection methods usually use five parameters (coordinates of the central point, width, height, and rotation angle) to describe the rotated bounding box and l1-loss as the loss function. In this paper, we argue that the…
The S{\o}rensen--Dice Coefficient has recently seen rising popularity as a loss function (also known as Dice loss) due to its robustness in tasks where the number of negative samples significantly exceeds that of positive samples, such as…
We derive the mapping between two of the most pervasive utility functions, the mean square error ($MSE$) and the concordance correlation coefficient (CCC, $\rho_c$). Despite its drawbacks, $MSE$ is one of the most popular performance…
Diffusion models are a new class of generative models that have shown outstanding performance in image generation literature. As a consequence, studies have attempted to apply diffusion models to other tasks, such as speech enhancement. A…
Diffusion models learn to restore noisy data, which is corrupted with different levels of noise, by optimizing the weighted sum of the corresponding loss terms, i.e., denoising score matching loss. In this paper, we show that restoring data…
In this paper, the coherence between speech and noise signals is used to obtain a Speech Enhancement (SE) gain function, in combination with a Super Gaussian Joint Maximum a Posteriori (SGJMAP) single microphone SE gain function. The…
Personalized speech enhancement (PSE) models utilize additional cues, such as speaker embeddings like d-vectors, to remove background noise and interfering speech in real-time and thus improve the speech quality of online video conferencing…
In neural networks, the loss function represents the core of the learning process that leads the optimizer to an approximation of the optimal convergence error. Convolutional neural networks (CNN) use the loss function as a supervisory…
Noise robustness is a key aspect of successful speech applications. Speech enhancement (SE) has been investigated to improve automatic speech recognition accuracy; however, its effectiveness for keyword spotting (KWS) is still…
Although supervised learning based on a deep neural network has recently achieved substantial improvement on speech enhancement, the existing schemes have either of two critical issues: spectrum or metric mismatches. The spectrum mismatch…
In real-world scenarios, speech signals are inevitably corrupted by various types of interference, making speech enhancement (SE) a critical task for robust speech processing. However, most existing SE methods only handle a limited range of…
We propose an end-to-end model based on convolutional and recurrent neural networks for speech enhancement. Our model is purely data-driven and does not make any assumptions about the type or the stationarity of the noise. In contrast to…
To train Variational Autoencoders (VAEs) to generate realistic imagery requires a loss function that reflects human perception of image similarity. We propose such a loss function based on Watson's perceptual model, which computes a…
Generative models have excelled in audio tasks using approaches such as language models, diffusion, and flow matching. However, existing generative approaches for speech enhancement (SE) face notable challenges: language model-based methods…
Contextualized end-to-end automatic speech recognition has been an active research area, with recent efforts focusing on the implicit learning of contextual phrases based on the final loss objective. However, these approaches ignore the…
We propose the Signal Dice Similarity Coefficient (SDSC), a structure-aware metric function for time series self-supervised representation learning. Most Self-Supervised Learning (SSL) methods for signals commonly adopt distance-based…
Speech emotion recognition (SER) plays a critical role in building emotion-aware speech systems, but its performance degrades significantly under noisy conditions. Although speech enhancement (SE) can improve robustness, it often introduces…
The discrepancy between the cost function used for training a speech enhancement model and human auditory perception usually makes the quality of enhanced speech unsatisfactory. Objective evaluation metrics which consider human perception…
Consider the minimum mean-square error (MMSE) of estimating an arbitrary random variable from its observation contaminated by Gaussian noise. The MMSE can be regarded as a function of the signal-to-noise ratio (SNR) as well as a functional…