Related papers: Performance Based Cost Functions for End-to-End Sp…
Many deep learning-based speech enhancement algorithms are designed to minimize the mean-square error (MSE) in some transform domain between a predicted and a target speech signal. However, optimizing for MSE does not necessarily guarantee…
Mean square error (MSE) has been the preferred choice as loss function in the current deep neural network (DNN) based speech separation techniques. In this paper, we propose a new cost function with the aim of optimizing the extended short…
The performance of single channel source separation algorithms has improved greatly in recent times with the development and deployment of neural networks. However, many such networks continue to operate on the magnitude spectrogram of a…
The mean squared error (MSE) is a ubiquitous loss function for speech enhancement, but its problem is that the error cannot reflect the auditory perception quality. This is because MSE causes models to over-emphasize low-frequency…
Many state-of-the-art neural network-based source separation systems use the averaged Signal-to-Distortion Ratio (SDR) as a training objective function. The basic SDR is, however, undefined if the network reconstructs the reference signal…
We investigate which loss functions provide better separations via benchmarking an extensive set of those for music source separation. To that end, we first survey the most representative audio source separation losses we identified, to…
Evaluation of musical source separation (MSS) has traditionally relied on Blind Source Separation Evaluation (BSS-Eval) metrics. However, recent work suggests that BSS-Eval metrics exhibit low correlation between metrics and perceptual…
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…
For voice communication, it is important to extract the speech from its noisy version without introducing unnaturally artificial noise. By studying the subband mean-squared error (MSE) of the speech for unsupervised speech enhancement…
Recent work in the domain of speech enhancement has explored the use of self-supervised speech representations to aid in the training of neural speech enhancement models. However, much of this work focuses on using the deepest or final…
Usually, hearing impaired people use hearing aids which are implemented with speech enhancement algorithms. Estimation of speech and estimation of nose are the components in single channel speech enhancement system. The main objective of…
Traditional Blind Source Separation Evaluation (BSS-Eval) metrics were originally designed to evaluate linear audio source separation models based on methods such as time-frequency masking. However, recent generative models may introduce…
Music source separation aims to extract individual sound sources (e.g., vocals, drums, guitar) from a mixed music recording. However, evaluating the quality of separated audio remains challenging, as commonly used metrics like the…
Time-domain training criteria have proven to be very effective for the separation of single-channel non-reverberant speech mixtures. Likewise, mask-based beamforming has shown impressive performance in multi-channel reverberant speech…
Minimizing the Mean Squared Error (MSE) is a key objective in machine learning and is commonly used for imputing missing values. While this approach provides accurate point estimates, it introduces systematic biases in downstream analyses.…
Measuring performance of an automatic speech recognition (ASR) system without ground-truth could be beneficial in many scenarios, especially with data from unseen domains, where performance can be highly inconsistent. In conventional ASR…
Speech separation has been successfully applied as a frontend processing module of conversation transcription systems thanks to its ability to handle overlapped speech and its flexibility to combine with downstream tasks such as automatic…
Source separation and other audio applications have traditionally relied on the use of short-time Fourier transforms as a front-end frequency domain representation step. The unavailability of a neural network equivalent to forward and…
New bounds on the rate distortion function of certain non-Gaussian sources, with a proportional-weighted mean-square error (MSE) distortion measure, are given. The growth, g, of the rate distortion function, as a result of changing from a…
Supervised learning based on a deep neural network recently has achieved substantial improvement on speech enhancement. Denoising networks learn mapping from noisy speech to clean one directly, or to a spectrum mask which is the ratio…