Related papers: A Universal Harmonic Discriminator for High-qualit…
The phase vocoder (PV) is a widely spread technique for processing audio signals. It employs a short-time Fourier transform (STFT) analysis-modify-synthesis loop and is typically used for time-scaling of signals by means of using different…
Accurate spectrum prediction is crucial for dynamic spectrum access (DSA) and resource allocation. However, due to the unique characteristics of spectrum data, existing methods based on the time or frequency domain often struggle to…
In the human ear, the basilar membrane plays a central role in sound recognition. When excited by sound, this membrane responds with a frequency-dependent displacement pattern that is detected and identified by the auditory hair cells…
In recent years, deep networks have led to dramatic improvements in speech enhancement by framing it as a data-driven pattern recognition problem. In many modern enhancement systems, large amounts of data are used to train a deep network to…
The short-time Fourier transform (STFT) usually computes the same number of frequency components as the frame length while overlapping adjacent time frames by more than half. As a result, the number of components of a spectrogram matrix…
Most machine learning models for audio tasks are dealing with a handcrafted feature, the spectrogram. However, it is still unknown whether the spectrogram could be replaced with deep learning based features. In this paper, we answer this…
In text-to-speech (TTS) and voice conversion (VC), acoustic features, such as mel spectrograms, are typically used as synthesis or conversion targets owing to their compactness and ease of learning. However, because the ultimate goal is to…
We introduce asynchronous dynamic decoder, which adopts an efficient A* algorithm to incorporate big language models in the one-pass decoding for large vocabulary continuous speech recognition. Unlike standard one-pass decoding with…
Flow matching offers a robust and stable approach to training diffusion models. However, directly applying flow matching to neural vocoders can result in subpar audio quality. In this work, we present WaveFM, a reparameterized flow matching…
Neural vocoders are now being used in a wide range of speech processing applications. In many of those applications, the vocoder can be the most complex component, so finding lower complexity algorithms can lead to significant practical…
Non-autoregressive GAN-based neural vocoders are widely used due to their fast inference speed and high perceptual quality. However, they often suffer from audible artifacts such as tonal artifacts in their generated results. Therefore, we…
In recent years, the synchrosqueezing transform (SST) has gained popularity as a method for the analysis of signals that can be broken down into multiple components determined by instantaneous amplitudes and phases. One such version of SST,…
Since the introduction of Generative Adversarial Networks (GANs) in speech synthesis, remarkable achievements have been attained. In a thorough exploration of vocoders, it has been discovered that audio waveforms can be generated at speeds…
A target recognition framework relying on near-field integrated sensing and communication (ISAC) systems is proposed. By exploiting the distance-dependent spatial signatures provided by the near-field spherical wavefront, high-accuracy…
In this work, we propose a full-band real-time speech enhancement system with GAN-based stochastic regeneration. Predictive models focus on estimating the mean of the target distribution, whereas generative models aim to learn the full…
For audio source separation applications, it is common to estimate the magnitude of the short-time Fourier transform (STFT) of each source. In order to further synthesizing time-domain signals, it is necessary to recover the phase of the…
Voice spoofing attacks pose a significant threat to automated speaker verification systems. Existing anti-spoofing methods often simulate specific attack types, such as synthetic or replay attacks. However, in real-world scenarios, the…
Neural vocoders based on the generative adversarial neural network (GAN) have been widely used due to their fast inference speed and lightweight networks while generating high-quality speech waveforms. Since the perceptually important…
The objective of deep learning methods based on encoder-decoder architectures for music source separation is to approximate either ideal time-frequency masks or spectral representations of the target music source(s). The spectral…
Unsupervised anomalous sound detection aims to detect unknown abnormal sounds of machines from normal sounds. However, the state-of-the-art approaches are not always stable and perform dramatically differently even for machines of the same…