Related papers: Neural Speech Coding for Real-time Communications …
Neural audio codecs are initially introduced to compress audio data into compact codes to reduce transmission latency. Researchers recently discovered the potential of codecs as suitable tokenizers for converting continuous audio into…
Quantum devices with low qubits are common in the Noisy Intermediate-Scale Quantum (NISQ) era. However, Quantum Neural Network (QNN) running on low-qubit quantum devices would be difficult since it is based on Variational Quantum Circuit…
The emerging conditional coding-based neural video codec (NVC) shows superiority over commonly-used residual coding-based codec and the latest NVC already claims to outperform the best traditional codec. However, there still exist critical…
Speech tokenizers are essential for connecting speech to large language models (LLMs) in multimodal systems. These tokenizers are expected to preserve both semantic and acoustic information for downstream understanding and generation.…
One-shot voice conversion (VC), which performs conversion across arbitrary speakers with only a single target-speaker utterance for reference, can be effectively achieved by speech representation disentanglement. Existing work generally…
Quantization-aware training (QAT) is essential for deploying large models under strict memory and latency constraints, yet achieving stable and robust optimization at ultra-low bitwidths remains challenging. Common approaches based on the…
Recent advancements in end-to-end neural speech codecs enable compressing audio at extremely low bitrates while maintaining high-fidelity reconstruction. Meanwhile, low computational complexity and low latency are crucial for real-time…
Language models (LMs) have recently flourished in natural language processing and computer vision, generating high-fidelity texts or images in various tasks. In contrast, the current speech generative models are still struggling regarding…
Speech codecs serve as a crucial bridge in unifying speech and text language models. Existing codec methods face several challenges in semantic encoding, such as residual paralinguistic information (e.g., timbre, emotion), insufficient…
Generative Adversarial Network (GAN) based vocoders are superior in both inference speed and synthesis quality when reconstructing an audible waveform from an acoustic representation. This study focuses on improving the discriminator for…
Discrete Audio codecs (or audio tokenizers) have recently regained interest due to the ability of Large Language Models (LLMs) to learn their compressed acoustic representations. Various publicly available trainable discrete tokenizers…
This paper applies energy conservation principles to the Daala video codec using gain-shape vector quantization to encode a vector of AC coefficients as a length (gain) and direction (shape). The technique originates from the CELT mode of…
Existing vector quantization (VQ) methods struggle with scalability, largely attributed to the instability of the codebook that undergoes partial updates during training. The codebook is prone to collapse as utilization decreases, due to…
Inspired by recent developments in neural speech coding and diffusion-based language modeling, we tackle speech enhancement by modeling the conditional distribution of clean speech codes given noisy speech codes using absorbing discrete…
Creating universal speaker encoders which are robust for different acoustic and speech duration conditions is a big challenge today. According to our observations systems trained on short speech segments are optimal for short phrase speaker…
Recently, generative speech enhancement has garnered considerable interest; however, existing approaches are hindered by excessive complexity, limited efficiency, and suboptimal speech quality. To overcome these challenges, this paper…
Signal compression based on implicit neural representation (INR) is an emerging technique to represent multimedia signals with a small number of bits. While INR-based signal compression achieves high-quality reconstruction for relatively…
Although discrete speech tokens have exhibited strong potential for language model-based speech generation, their high bitrates and redundant timbre information restrict the development of such models. In this work, we propose LSCodec, a…
Neural vocoders have recently advanced waveform generation, yielding natural and expressive audio. Among these approaches, iSTFT-based vocoders have recently gained attention. They predict a complex-valued spectrogram and then synthesize…
Vector quantization, which discretizes a continuous vector space into a finite set of representative vectors (a codebook), has been widely adopted in modern machine learning. Despite its effectiveness, vector quantization poses a…