Related papers: PeriodNet: A non-autoregressive waveform generatio…

Separating target speech from mixed signals containing flexible speaker quantities presents a challenging task. While existing methods demonstrate strong separation performance and noise robustness, they predominantly assume prior knowledge…

Analog machine learning hardware platforms promise to be faster and more energy-efficient than their digital counterparts. Wave physics, as found in acoustics and optics, is a natural candidate for building analog processors for…

In this work, we propose a new solution for parallel wave generation by WaveNet. In contrast to parallel WaveNet (van den Oord et al., 2018), we distill a Gaussian inverse autoregressive flow from the autoregressive WaveNet by minimizing a…

In this work, we propose WaveFlow, a small-footprint generative flow for raw audio, which is directly trained with maximum likelihood. It handles the long-range structure of 1-D waveform with a dilated 2-D convolutional architecture, while…

In a recent paper, we have presented a generative adversarial network (GAN)-based model for unconditional generation of the mel-spectrograms of singing voices. As the generator of the model is designed to take a variable-length sequence of…

Time-domain audio separation network (TasNet) has achieved remarkable performance in blind source separation (BSS). Classic multi-channel speech processing framework employs signal estimation and beamforming. For example, Beam-TasNet links…

Modern time series are usually composed of multiple oscillatory components, with time-varying frequency and amplitude contaminated by noise. The signal processing mission is further challenged if each component has an oscillatory pattern,…

Transformers have recently dominated the ASR field. Although able to yield good performance, they involve an autoregressive (AR) decoder to generate tokens one by one, which is computationally inefficient. To speed up inference,…

Speech separation algorithms are often used to separate the target speech from other interfering sources. However, purely neural network based speech separation systems often cause nonlinear distortion that is harmful for automatic speech…

Recent work in synthetic data generation in the time-series domain has focused on the use of Generative Adversarial Networks. We propose a novel architecture for synthetically generating time-series data with the use of Variational…

Developing architectures suitable for modeling raw audio is a challenging problem due to the high sampling rates of audio waveforms. Standard sequence modeling approaches like RNNs and CNNs have previously been tailored to fit the demands…

This paper proposes speaker-adaptive neural vocoders for parametric text-to-speech (TTS) systems. Recently proposed WaveNet-based neural vocoding systems successfully generate a time sequence of speech signal with an autoregressive…

Speech separation models are used for isolating individual speakers in many speech processing applications. Deep learning models have been shown to lead to state-of-the-art (SOTA) results on a number of speech separation benchmarks. One…

We introduce CrossNet, a complex spectral mapping approach to speaker separation and enhancement in reverberant and noisy conditions. The proposed architecture comprises an encoder layer, a global multi-head self-attention module, a…

Time series are ubiquitous in many applications that involve forecasting, classification and causal inference tasks, such as healthcare, finance, audio signal processing and climate sciences. Still, large, high-quality time series datasets…

Whispered speech is produced when the vocal folds are not used, either intentionally, or due to a temporary or permanent voice condition. The essential difference between natural speech and whispered speech is that periodic signal…

Imagine generating a city's electricity demand pattern based on weather, the presence of an electric vehicle, and location, which could be used for capacity planning during a winter freeze. Such real-world time series are often enriched…

This paper introduces UnDiff, a diffusion probabilistic model capable of solving various speech inverse tasks. Being once trained for speech waveform generation in an unconditional manner, it can be adapted to different tasks including…

Non-autoregressive automatic speech recognition (ASR) has become a mainstream of ASR modeling because of its fast decoding speed and satisfactory result. To further boost the performance, relaxing the conditional independence assumption and…

This paper introduces a new method for multi-channel time domain speech separation in reverberant environments. A fully-convolutional neural network structure has been used to directly separate speech from multiple microphone recordings,…