Related papers: ComplexDec: A Domain-robust High-fidelity Neural A…
We investigate the task of retrieving information from compositional distributed representations formed by Hyperdimensional Computing/Vector Symbolic Architectures and present novel techniques which achieve new information rate bounds.…
In this paper, a novel method of designing a codebook for noise robust speaker identification purpose utilizing Genetic Algorithm has been proposed. Wiener filter has been used to remove the background noises from the source speech…
Audio codecs based on discretized neural autoencoders have recently been developed and shown to provide significantly higher compression levels for comparable quality speech output. However, these models are tightly coupled with speech…
Ultra-low-bitrate speech coding is pivotal for bandwidth-constrained communication and deep compression, yet maintaining naturalness and speaker identity at such extreme bit budgets remains challenging due to pronounced information loss and…
Built upon vector quantization (VQ), discrete audio codec models have achieved great success in audio compression and auto-regressive audio generation. However, existing models face substantial challenges in perceptual quality and signal…
This paper proposes StreamCodec, a streamable neural audio codec designed for real-time communication. StreamCodec adopts a fully causal, symmetric encoder-decoder structure and operates in the modified discrete cosine transform (MDCT)…
While recent neural codecs achieve strong performance at low bitrates when optimized for perceptual quality, their effectiveness deteriorates significantly under ultra-low bitrate conditions. To mitigate this, generative compression methods…
Neural audio codecs have recently gained traction for their ability to compress high-fidelity audio and provide discrete tokens for generative modeling. However, leading approaches often rely on resource-intensive models and complex…
Improving the interpretability of deep neural networks has recently gained increased attention, especially when the power of deep learning is leveraged to solve problems in physics. Interpretability helps us understand a model's ability to…
While existing speech audio codecs designed for compression exploit limited forms of temporal redundancy and allow for multi-scale representations, they tend to represent all features of audio in the same way. In contrast, generative voice…
Since Text-to-Speech systems typically don't produce waveforms directly, recent spoof detection studies use resynthesized waveforms from vocoders and neural audio codecs to simulate an attacker. Unlike vocoders, which are specifically…
Existing Audio Deepfake Detection (ADD) systems often struggle to generalise effectively due to the significantly degraded audio quality caused by audio codec compression and channel transmission effects in real-world communication…
Speech compression is commonly used to send voice over radio channels in applications such as mobile telephony and two-way push-to-talk (PTT) radio. In classical systems, the speech codec is combined with forward error correction,…
In bandwidth-constrained communication such as satellite and underwater channels, speech must often be transmitted at ultra-low bitrates where intelligibility is the primary objective. At such extreme compression levels, codecs trained with…
Recent advancements in neural vocoding are predominantly driven by Generative Adversarial Networks (GANs) operating in the time-domain. While effective, this approach neglects the inductive bias offered by time-frequency representations,…
Neural image compression (NIC) is increasingly used in computer vision pipelines, as learning-based models are able to surpass traditional algorithms in compression efficiency. However, learned codecs can be unstable and vulnerable to…
Generative models have shown significant achievements in audio generation tasks. However, existing models struggle with complex and detailed prompts, leading to potential performance degradation. We hypothesize that this problem stems from…
Neural speech coding is a rapidly developing topic, where state-of-the-art approaches now exhibit superior compression performance than conventional methods. Despite significant progress, existing methods still have limitations in…
Error resilient tools like Packet Loss Concealment (PLC) and Forward Error Correction (FEC) are essential to maintain a reliable speech communication for applications like Voice over Internet Protocol (VoIP), where packets are frequently…
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…