Related papers: UBGAN: Enhancing Coded Speech with Blind and Guide…

UWB has a very large bandwidth in a WPAN network, which is best used for HD-video applications. Meanwhile, MBWA is a WMAN option optimized for wireless-IP in a fast moving vehicle. In this paper, we propose a practical engineering scenario…

In this article, we develop an end-to-end wireless communication system using deep neural networks (DNNs), in which DNNs are employed to perform several key functions, including encoding, decoding, modulation, and demodulation. However, an…

Training of speech enhancement systems often does not incorporate knowledge of human perception and thus can lead to unnatural sounding results. Incorporating psychoacoustically motivated speech perception metrics as part of model training…

Both reverberation and additive noises degrade the speech quality and intelligibility. Weighted prediction error (WPE) method performs well on the dereverberation but with limitations. First, WPE doesn't consider the influence of the…

Sixth-generation (6G) wireless networks must support heterogeneous services: enhanced Mobile Broadband (eMBB) requiring 1 Tbps data rates, massive Machine-Type Communications (mMTC) supporting 10 million devices per km, and Ultra-Reliable…

The advent of Large Models marks a new era in machine learning, significantly outperforming smaller models by leveraging vast datasets to capture and synthesize complex patterns. Despite these advancements, the exploration into scaling,…

Brain-computer interfaces (BCI) offer numerous human-centered application possibilities, particularly affecting people with neurological disorders. Text or speech decoding from brain activities is a relevant domain that could augment the…

In underwater acoustic (UWA) communication, orthogonal frequency division multiplexing (OFDM) is commonly employed to mitigate the inter-symbol interference (ISI) caused by delay spread. However, path-specific Doppler effects in UWA…

Besides the well-known classification task, these days neural networks are frequently being applied to generate or transform data, such as images and audio signals. In such tasks, the conventional loss functions like the mean squared error…

Recent advancements in deep learning led to human-level performance in single-speaker speech synthesis. However, there are still limitations in terms of speech quality when generalizing those systems into multiple-speaker models especially…

Noise robustness remains a critical challenge for deploying neural speech codecs in real-world acoustic scenarios where background noise is often inevitable. A key observation we make is that even slight input noise perturbations can cause…

Recent approaches in text-to-speech (TTS) synthesis employ neural network strategies to vocode perceptually-informed spectrogram representations directly into listenable waveforms. Such vocoding procedures create a computational bottleneck…

Generative speech enhancement methods based on generative adversarial networks (GANs) and diffusion models have shown promising results in various speech enhancement tasks. However, their performance in very low signal-to-noise ratio (SNR)…

The most striking successes in image retrieval using deep hashing have mostly involved discriminative models, which require labels. In this paper, we use binary generative adversarial networks (BGAN) to embed images to binary codes in an…

Recently, neural networks have proven to be effective in performing speech coding task at low bitrates. However, under-utilization of intra-frame correlations and the error of quantizer specifically degrade the reconstructed audio quality.…

Neural network based approaches to speech enhancement have shown to be particularly powerful, being able to leverage a data-driven approach to result in a significant performance gain versus other approaches. Such approaches are reliant on…

Speech enhancement plays an essential role in improving the quality of speech signals in noisy environments. This paper investigates the efficacy of integrating Bidirectional Gated Recurrent Units (BGRU) and Transformer models for speech…

Neural speech codecs have demonstrated their ability to compress high-quality speech and audio by converting them into discrete token representations. Most existing methods utilize Residual Vector Quantization (RVQ) to encode speech into…

In this paper, we address the design of high spectral-efficiency Barnes-Wall (BW) lattice codes which are amenable to low-complexity decoding in additive white Gaussian noise (AWGN) channels. We propose a new method of constructing complex…

Millimeter-wave (mmWave) radar captures are band-limited and noisy, making for difficult reconstruction of intelligible full-bandwidth speech. In this work, we propose a two-stage speech reconstruction pipeline for mmWave using a…