Related papers: Ultra-Low-Bitrate Mel-Spectrogram-based Neural Spe…
There are many deterministic mathematical operations (e.g. compression, clipping, downsampling) that degrade speech quality considerably. In this paper we introduce a neural network architecture, based on a modification of the DiffWave…
Recent advances in speech spoofing necessitate stronger verification mechanisms in neural speech codecs to ensure authenticity. Current methods embed numerical watermarks before compression and extract them from reconstructed speech for…
Low and ultra-low-bitrate neural speech coding achieves unprecedented coding gain by generating speech signals from compact speech features. This paper introduces additional coding efficiency in neural speech coding by reducing the temporal…
Online multichannel speech enhancement has been intensively studied recently. Though Mel-scale frequency is more matched with human auditory perception and computationally efficient than linear frequency, few works are implemented in a…
Precise control over speech characteristics, such as pitch, duration, and speech rate, remains a significant challenge in the field of voice conversion. The ability to manipulate parameters like pitch and syllable rate is an important…
Large language models (LLMs) have significantly advanced audio processing through audio codecs that convert audio into discrete tokens, enabling the application of language modeling techniques to audio data. However, audio codecs often…
Conventional audio coding technologies commonly leverage human perception of sound, or psychoacoustics, to reduce the bitrate while preserving the perceptual quality of the decoded audio signals. For neural audio codecs, however, the…
We introduce a state-of-the-art real-time, high-fidelity, audio codec leveraging neural networks. It consists in a streaming encoder-decoder architecture with quantized latent space trained in an end-to-end fashion. We simplify and speed-up…
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.…
Audio coding is an essential module in the real-time communication system. Neural audio codecs can compress audio samples with a low bitrate due to the strong modeling and generative capabilities of deep neural networks. To address the poor…
Neural audio coding has shown very promising results recently in the literature to largely outperform traditional codecs but limited attention has been paid on its error resilience. Neural codecs trained considering only source coding tend…
The recent advancement of end-to-end neural audio codecs enables compressing audio at very low bitrates while reconstructing the output audio with high fidelity. Nonetheless, such improvements often come at the cost of increased model…
With recent rapid growth of large language models (LLMs), discrete speech tokenization has played an important role for injecting speech into LLMs. However, this discretization gives rise to a loss of information, consequently impairing…
Neural audio/speech coding has recently demonstrated its capability to deliver high quality at much lower bitrates than traditional methods. However, existing neural audio/speech codecs employ either acoustic features or learned blind…
This paper proposes a novel neural denoising vocoder that can generate clean speech waveforms from noisy mel-spectrograms. The proposed neural denoising vocoder consists of two components, i.e., a spectrum predictor and a enhancement…
Image compression and reconstruction are crucial for various digital applications. While contemporary neural compression methods achieve impressive compression rates, the adoption of such technology has been largely hindered by the…
This paper presents a new neural speech compression method that is practical in the sense that it operates at low bitrate, introduces a low latency, is compatible in computational complexity with current mobile devices, and provides a…
Neural speech codecs aim to compress input signals into minimal bits while maintaining content quality in a low-latency manner. However, existing neural codecs often trade model complexity for reconstruction performance. These codecs…
The quality of speech codecs deteriorates at low bitrates due to high quantization noise. A post-filter is generally employed to enhance the quality of the coded speech. In this paper, a data-driven post-filter relying on masking in the…
Flow matching offers a robust and stable approach to training diffusion models. However, directly applying flow matching to neural vocoders can result in subpar audio quality. In this work, we present WaveFM, a reparameterized flow matching…