Related papers: High-Fidelity and Low-Latency Universal Neural Voc…

In recent years multilayer perceptrons (MLPs) with many hid- den layers Deep Neural Network (DNN) has performed sur- prisingly well in many speech tasks, i.e. speech recognition, speaker verification, speech synthesis etc. Although in the…

The integration of wind energy into power grids necessitates accurate ultra-short-term wind power forecasting to ensure grid stability and optimize resource allocation. This study introduces M2WLLM, an innovative model that leverages the…

We propose the multi-head convolutional neural network (MCNN) architecture for waveform synthesis from spectrograms. Nonlinear interpolation in MCNN is employed with transposed convolution layers in parallel heads. MCNN achieves more than…

The performance of speaker diarization is strongly affected by its clustering algorithm at the test stage. However, it is known that clustering algorithms are sensitive to random noises and small variations, particularly when the clustering…

This paper investigates the effects of limited speech data in the context of speaker verification using deep neural network (DNN) approach. Being able to reduce the length of required speech data is important to the development of speaker…

End-to-end speech recognition generally uses hand-engineered acoustic features as input and excludes the feature extraction module from its joint optimization. To extract learnable and adaptive features and mitigate information loss, we…

Albeit recent progress in speaker verification generates powerful models, malicious attacks in the form of spoofed speech, are generally not coped with. Recent results in ASVSpoof2015 and BTAS2016 challenges indicate that spoof-aware…

Modern sensors produce increasingly rich streams of high-resolution data. Due to resource constraints, machine learning systems discard the vast majority of this information via resolution reduction. Compressed-domain learning allows models…

State-of-the-art statistical parametric speech synthesis (SPSS) generally uses a vocoder to represent speech signals and parameterize them into features for subsequent modeling. Magnitude spectrum has been a dominant feature over the years.…

So far, many of the deep learning approaches for voice conversion produce good quality speech by using a large amount of training data. This paper presents a Deep Bidirectional Long Short-Term Memory (DBLSTM) based voice conversion…

Speech dereverberation is an important stage in many speech technology applications. Recent work in this area has been dominated by deep neural network models. Temporal convolutional networks (TCNs) are deep learning models that have been…

Probabilistic Latent Variable Models (LVMs) provide an alternative to self-supervised learning approaches for linguistic representation learning from speech. LVMs admit an intuitive probabilistic interpretation where the latent structure…

Pre-trained speech language models such as HuBERT and WavLM leverage unlabeled speech data for self-supervised learning and offer powerful representations for numerous downstream tasks. Despite the success of these models, their high…

In the scenario with reverberation, the experience of human-machine interaction will become worse. In order to solve this problem, many methods for the dereverberation have emerged. At present, how to update the parameters of the Kalman…

In this work we aim to discover high quality speech features and linguistic units directly from unlabeled speech data in a zero resource scenario. The results are evaluated using the metrics and corpora proposed in the Zero Resource Speech…

Current multi-channel speech enhancement systems mainly adopt single-output architecture, which face significant challenges in preserving spatio-temporal signal integrity during multiple-input multiple-output (MIMO) processing. To address…

This paper presents an improved deep embedding learning method based on convolutional neural network (CNN) for text-independent speaker verification. Two improvements are proposed for x-vector embedding learning: (1) Multi-scale convolution…

We propose multi-layer perceptron (MLP)-based architectures suitable for variable length input. MLP-based architectures, recently proposed for image classification, can only be used for inputs of a fixed, pre-defined size. However, many…

This paper presents a waveform modeling and generation method using hierarchical recurrent neural networks (HRNN) for speech bandwidth extension (BWE). Different from conventional BWE methods which predict spectral parameters for…

Generative Pre-trained Transformer (GPT) models have achieved remarkable performance on various natural language processing tasks, and have shown great potential as backbones for audio-and-text large language models (LLMs). Previous…