Related papers: Unified Microphone Conversion: Many-to-Many Device…

The performance of deep learning-based multi-channel speech enhancement methods often deteriorates when the geometric parameters of the microphone array change. Traditional approaches to mitigate this issue typically involve training on…

Voice conversion (VC) refers to transforming the speaker characteristics of an utterance without altering its linguistic contents. Many works on voice conversion require to have parallel training data that is highly expensive to acquire.…

In the evolving wireless communications landscape, addressing the challenges of multipath fading and high mobility remains paramount. This paper introduces the Unified Sequency-Frequency Multiplexing (USFM) framework, a pioneering…

Speech separation refers to extracting each individual speech source in a given mixed signal. Recent advancements in speech separation and ongoing research in this area, have made these approaches as promising techniques for pre-processing…

This paper proposes a voice conversion (VC) method based on a sequence-to-sequence (S2S) learning framework, which enables simultaneous conversion of the voice characteristics, pitch contour, and duration of input speech. We previously…

Generative adversarial networks (GAN) have recently been shown to be efficient for speech enhancement. However, most, if not all, existing speech enhancement GANs (SEGAN) make use of a single generator to perform one-stage enhancement…

Recently, there has been growing interest in multi-speaker speech recognition, where the utterances of multiple speakers are recognized from their mixture. Promising techniques have been proposed for this task, but earlier works have…

With the rise of diffusion models, audio-video generation has been revolutionized. However, most existing methods rely on separate modules for each modality, with limited exploration of unified generative architectures. In addition, many…

Nowadays vast amounts of speech data are recorded from low-quality recorder devices such as smartphones, tablets, laptops, and medium-quality microphones. The objective of this research was to study the automatic generation of high-quality…

Various applications of voice synthesis have been developed independently despite the fact that they generate "voice" as output in common. In addition, the majority of voice synthesis models currently rely on annotated audio data, but it is…

Real-world audio recordings often contain multiple speakers and various degradations, which limit both the quantity and quality of speech data available for building state-of-the-art speech processing models. Although end-to-end approaches…

We investigated an enhancement and a domain adaptation approach to make speaker verification systems robust to perturbations of far-field speech. In the enhancement approach, using paired (parallel) reverberant-clean speech, we trained a…

Systems for synthesizer sound matching, which automatically set the parameters of a synthesizer to emulate an input sound, have the potential to make the process of synthesizer programming faster and easier for novice and experienced…

Building a single universal speech enhancement (SE) system that can handle arbitrary input is a demanded but underexplored research topic. Towards this ultimate goal, one direction is to build a single model that handles diverse audio…

In this study, we present an approach to train a single speech enhancement network that can perform both personalized and non-personalized speech enhancement. This is achieved by incorporating a frame-wise conditioning input that specifies…

Machine learning algorithms, when trained on audio recordings from a limited set of devices, may not generalize well to samples recorded using other devices with different frequency responses. In this work, a relatively straightforward…

We introduce UniMuMo, a unified multimodal model capable of taking arbitrary text, music, and motion data as input conditions to generate outputs across all three modalities. To address the lack of time-synchronized data, we align unpaired…

A dynamic and flexible generalized spatial modulation (GSM) framework is proposed for massive MIMO systems. Our framework is leveraged on the utilization of machine learning methods for GSM in order to improve the error performance in…

Recent multimodal systems often rely on separate expert modality encoders which cause linearly scaling complexity and computational overhead with added modalities. While unified Omni-models address this via Mixture-of-Expert (MoE)…

This work defines a new framework for performance evaluation of polyphonic sound event detection (SED) systems, which overcomes the limitations of the conventional collar-based event decisions, event F-scores and event error rates. The…