Related papers: Fast and Flexible Audio Bandwidth Extension via Vo…
A highly efficient fast boundary element method (BEM) for solving large-scale engineering acoustic problems in a broad frequency range is developed and implemented. The acoustic problems are modeled by the Burton-Miller boundary integral…
A wide-band current preamplifier based on a composite operational amplifier is proposed. It has been shown that the bandwidth of the preamplifier can be significantly increased by enhancing the effective open-loop gain of the composite…
Removing background noise from speech audio has been the subject of considerable effort, especially in recent years due to the rise of virtual communication and amateur recordings. Yet background noise is not the only unpleasant disturbance…
A Low-Power Variable Gain (VG) mm-Wave Low Noise Amplifier (LNA) is designed and simulated in a 28-nm CMOS process. The LNA utilizes a simple, yet novel, technique presented in this paper to vary the small-signal output resistance to…
We theoretically and experimentally propose two designs of broadband low-frequency acoustic metasurface absorbers (Sample I/Sample II) for the frequency ranges of 458Hz~968Hz and 231Hz~491Hz (larger than 1 octave), with absorption larger…
Speech enhancement (SE) aims to extract the clean waveform from noise-contaminated measurements to improve the speech quality and intelligibility. Although learning-based methods can perform much better than traditional counterparts, the…
This paper revisits the neural vocoder task through the lens of audio restoration and propose a novel diffusion vocoder called BridgeVoC. Specifically, by rank analysis, we compare the rank characteristics of Mel-spectrum with other common…
In recent years, various flow-based generative models have been proposed to generate high-fidelity waveforms in real-time. However, these models require either a well-trained teacher network or a number of flow steps making them…
In real-time speech synthesis, neural vocoders often require low-latency synthesis through causal processing and streaming. However, streaming introduces inefficiencies absent in batch synthesis, such as limited parallelism, inter-frame…
Voice communication using the air conduction microphone in noisy environments suffers from the degradation of speech audibility. Bone conduction microphones (BCM) are robust against ambient noises but suffer from limited effective bandwidth…
Intense bandwidth depletion within consumer and constrained networks has the potential to undermine the stability of real-time video conferencing: encoder rate management becomes saturated, packet loss escalates, frame rates deteriorate,…
Neural audio codecs have been widely adopted in audio-generative tasks because their compact and discrete representations are suitable for both large-language-model-style and regression-based generative models. However, most neural codecs…
Traditional parametric coding of speech facilitates low rate but provides poor reconstruction quality because of the inadequacy of the model used. We describe how a WaveNet generative speech model can be used to generate high quality speech…
Speed-of-sound is a biomechanical property for quantitative tissue differentiation, with great potential as a new ultrasound-based image modality. A conventional ultrasound array transducer can be used together with an acoustic mirror, or…
In this work, we propose WaveFlow, a small-footprint generative flow for raw audio, which is directly trained with maximum likelihood. It handles the long-range structure of 1-D waveform with a dilated 2-D convolutional architecture, while…
Vector Quantized Variational AutoEncoders (VQ-VAE) are a powerful representation learning framework that can discover discrete groups of features from a speech signal without supervision. Until now, the VQ-VAE architecture has previously…
Autoregressive video diffusion models have emerged as a scalable paradigm for long video generation. However, they often suffer from severe extrapolation failure, where rapid error accumulation leads to significant temporal degradation when…
In order to efficiently transmit and store speech signals, speech codecs create a minimally redundant representation of the input signal which is then decoded at the receiver with the best possible perceptual quality. In this work we…
Diffusion speech enhancement on discrete audio codec features gain immense attention due to their improved speech component reconstruction capability. However, they usually suffer from high inference computational complexity due to multiple…
Audio and speech coding lack unified evaluation and open-source testing. Many candidate systems were evaluated on proprietary, non-reproducible, or small data, and machine learning-based codecs are often tested on datasets with similar…