相关论文: Blind Normalization of Speech From Different Chann…

This paper addresses the problem of speech separation and enhancement from multichannel convolutive and noisy mixtures, \emph{assuming known mixing filters}. We propose to perform the speech separation and enhancement task in the short-time…

We analyze, theoretically and empirically, the performance of generative diffusion models based on \emph{blind denoisers}, in which the denoiser is not given the noise amplitude in either the training or sampling processes. Assuming that…

Voice disorders affect patients profoundly, and acoustic tools can potentially measure voice function objectively. Nonetheless, existing tools are limited to analysing voices displaying near periodicity, and do not account for inherent…

This paper presents a general framework for modeling dependence in multivariate time series. Its fundamental approach relies on decomposing each signal in a system into various frequency components and then studying the dependence…

Purely neural network (NN) based speech separation and enhancement methods, although can achieve good objective scores, inevitably cause nonlinear speech distortions that are harmful for the automatic speech recognition (ASR). On the other…

There are many deterministic mathematical operations (e.g. compression, clipping, downsampling) that degrade speech quality considerably. In this paper we introduce a neural network architecture, based on a modification of the DiffWave…

We present a method for audio denoising that combines processing done in both the time domain and the time-frequency domain. Given a noisy audio clip, the method trains a deep neural network to fit this signal. Since the fitting is only…

Some glottal analysis approaches based upon linear prediction or complex cepstrum approaches have been proved to be effective to estimate glottal source from real speech utterances. We propose a new approach employing both an all-pole…

The speech signal is a consummate example of time-series data. The acoustics of the signal change over time, sometimes dramatically. Yet, the most common type of comparison we perform in phonetics is between instantaneous acoustic…

Single-channel speech separation in time domain and frequency domain has been widely studied for voice-driven applications over the past few years. Most of previous works assume known number of speakers in advance, however, which is not…

Most current speech enhancement models use spectrogram features that require an expensive transformation and result in phase information loss. Previous work has overcome these issues by using convolutional networks to learn long-range…

Sound in noise is better detected or understood if target and masking sources originate from different locations. Mammalian physiology suggests that the neurocomputational process that underlies this binaural unmasking is based on two…

Deep convolutional networks often append additive constant ("bias") terms to their convolution operations, enabling a richer repertoire of functional mappings. Biases are also used to facilitate training, by subtracting mean response over…

Noise simulation is a very powerful tool in signal analysis helping to foresee the system performance in real experimental situations. Time series generation is however a hard challenge when a robust model of the noise sources is missing.…

Speaker Identification refers to the process of identifying a person using one's voice from a collection of known speakers. Environmental noise, reverberation and distortion make the task of automatic speaker identification challenging as…

We present a voice conversion framework that converts normal speech into dysarthric speech while preserving the speaker identity. Such a framework is essential for (1) clinical decision making processes and alleviation of patient stress,…

We consider the problem of reconstructing a discrete-time signal (sequence) with continuous-valued components corrupted by a known memoryless channel. When performance is measured using a per-symbol loss function satisfying mild regularity…

This paper addresses the problems of blind channel identification and multichannel equalization for speech dereverberation and noise reduction. The time-domain cross-relation method is not suitable for blind room impulse response…

This paper focuses on single-channel semi-supervised speech enhancement. We learn a speaker-independent deep generative speech model using the framework of variational autoencoders. The noise model remains unsupervised because we do not…

Language exhibits structure at different scales, ranging from subwords to words, sentences, paragraphs, and documents. To what extent do deep models capture information at these scales, and can we force them to better capture structure…