Related papers: Generative Speech Foundation Model Pretraining for…

In speech synthesis and speech enhancement systems, melspectrograms need to be precise in acoustic representations. However, the generated spectrograms are over-smooth, that could not produce high quality synthesized speech. Inspired by…

This paper presents a generative approach to speech enhancement based on a recurrent variational autoencoder (RVAE). The deep generative speech model is trained using clean speech signals only, and it is combined with a nonnegative matrix…

This paper proposes an approach to the joint modeling of the short-time Fourier transform magnitude and phase spectrograms with a deep generative model. We assume that the magnitude follows a Gaussian distribution and the phase follows a…

In this work, we propose a new mathematical vocoder algorithm(modified spectral inversion) that generates a waveform from acoustic features without phase estimation. The main benefit of using our proposed method is that it excludes the…

In this paper we address the problem of enhancing speech signals in noisy mixtures using a source separation approach. We explore the use of neural networks as an alternative to a popular speech variance model based on supervised…

Recent advancements in neural vocoding are predominantly driven by Generative Adversarial Networks (GANs) operating in the time-domain. While effective, this approach neglects the inductive bias offered by time-frequency representations,…

While recent neural sequence-to-sequence models have greatly improved the quality of speech synthesis, there has not been a system capable of fast training, fast inference and high-quality audio synthesis at the same time. We propose a…

We propose a novel spectral generative modeling framework for natural language processing that jointly learns a global time varying Fourier dictionary and per token mixing coefficients, replacing the ubiquitous self attention mechanism in…

In this paper, we address the problem of multichannel speech enhancement in the short-time Fourier transform (STFT) domain. A long short-time memory (LSTM) network takes as input a sequence of STFT coefficients associated with a frequency…

Target Language Extraction aims to extract speech in a specific language from a mixture waveform that contains multiple speakers speaking different languages. The human auditory system is adept at performing this task with the knowledge of…

Recently, attention-based transformers have become a de facto standard in many deep learning applications including natural language processing, computer vision, signal processing, etc.. In this paper, we propose a transformer-based…

Language Model (LM)-based generative modeling has emerged as a promising direction for TSE, offering potential for improved generalization and high-fidelity speech. We present GenTSE, a two-stage decoder-only generative LM approach for TSE:…

We propose a way to use a transformer-based language model in conversational speech recognition. Specifically, we focus on decoding efficiently in a weighted finite-state transducer framework. We showcase an approach to lattice re-scoring…

Reverberation encodes spatial information regarding the acoustic source environment, yet traditional Speech Restoration (SR) usually completely removes reverberation. We propose ReverbMiipher, an SR model extending parametric resynthesis…

Neural autoencoders underpin generative models. Practical, large-scale use of neural autoencoders for generative modeling necessitates fast encoding, low latent rates, and a single model across representations. Existing approaches are…

Speech super-resolution (SR) is the task that restores high-resolution speech from low-resolution input. Existing models employ simulated data and constrained experimental settings, which limit generalization to real-world SR. Predictive…

Speech pre-processing techniques such as denoising, de-reverberation, and separation, are commonly employed as front-ends for various downstream speech processing tasks. However, these methods can sometimes be inadequate, resulting in…

Improving the accuracy of single-channel automatic speech recognition (ASR) in noisy conditions is challenging. Strong speech enhancement front-ends are available, however, they typically require that the ASR model is retrained to cope with…

Currently, the development of Foreign Accent Conversion (FAC) models utilizes deep neural network architectures, as well as ensembles of neural networks for speech recognition and speech generation. The use of these models is limited by…

Target speech extraction (TSE) isolates the speech of a specific speaker from a multi-talker overlapped speech mixture. Most existing TSE models rely on discriminative methods, typically predicting a time-frequency spectrogram mask for the…