Related papers: Generative Speech Foundation Model Pretraining for…
Self-supervised learning (SSL) has garnered significant attention in speech processing, excelling in linguistic tasks such as speech recognition. However, jointly improving the performance of pre-trained models on various downstream tasks,…
Speech quality in online conferencing applications is typically assessed through human judgements in the form of the mean opinion score (MOS) metric. Since such a labor-intensive approach is not feasible for large-scale speech quality…
This paper proposes a novel unsupervised autoregressive neural model for learning generic speech representations. In contrast to other speech representation learning methods that aim to remove noise or speaker variabilities, ours is…
Generative models are capable to address difficult problems with non-unique solutions like bandwidth extension and gap filling, removing highly non-linear artifacts from codecs, clipping and distortion, as opposed to removing linear…
Speech enhancement involves the distinction of a target speech signal from an intrusive background. Although generative approaches using Variational Autoencoders or Generative Adversarial Networks (GANs) have increasingly been used in…
Diffusion models have shown a great ability at bridging the performance gap between predictive and generative approaches for speech enhancement. We have shown that they may even outperform their predictive counterparts for non-additive…
Target speaker extraction (TSE) aims to recover the speech of a desired speaker from a mixture given a short enrollment utterance, while speech enhancement (SE) focuses on improving speech quality under noisy conditions. Most existing TSE…
Classical parametric speech coding techniques provide a compact representation for speech signals. This affords a very low transmission rate but with a reduced perceptual quality of the reconstructed signals. Recently, autoregressive deep…
Large, pre-trained representation models trained using self-supervised learning have gained popularity in various fields of machine learning because they are able to extract high-quality salient features from input data. As such, they have…
Speech enhancement has seen great improvement in recent years mainly through contributions in denoising, speaker separation, and dereverberation methods that mostly deal with environmental effects on vocal audio. To enhance speech beyond…
While recent advancements in speech language models have achieved significant progress, they face remarkable challenges in modeling the long acoustic sequences of neural audio codecs. In this paper, we introduce \textbf{G}enerative…
Modern speech enhancement (SE) networks typically implement noise suppression through time-frequency masking, latent representation masking, or discriminative signal prediction. In contrast, some recent works explore SE via generative…
Speaker-aware source separation methods are promising workarounds for major difficulties such as arbitrary source permutation and unknown number of sources. However, it remains challenging to achieve satisfying performance provided a very…
We explore pretraining strategies including choice of base corpus with the aim of choosing the best strategy for zero-shot multi-speaker end-to-end synthesis. We also examine choice of neural vocoder for waveform synthesis, as well as…
Most neural network speech enhancement models ignore speech production mathematical models by directly mapping Fourier transform spectrums or waveforms. In this work, we propose a neural source filter network for speech enhancement.…
Diffusion models have recently been shown to be relevant for high-quality speech generation. Most work has been focused on generating spectrograms, and as such, they further require a subsequent model to convert the spectrogram to a…
In recent years, self-supervised learning paradigm has received extensive attention due to its great success in various down-stream tasks. However, the fine-tuning strategies for adapting those pre-trained models to speaker verification…
Recent advances in neural-network based generative modeling of speech has shown great potential for speech coding. However, the performance of such models drops when the input is not clean speech, e.g., in the presence of background noise,…
Speech super-resolution (SR) is a task to increase speech sampling rate by generating high-frequency components. Existing speech SR methods are trained in constrained experimental settings, such as a fixed upsampling ratio. These strong…
The recent emergence of machine-learning based generative models for speech suggests a significant reduction in bit rate for speech codecs is possible. However, the performance of generative models deteriorates significantly with the…