Related papers: Entropy-Guided GRVQ for Ultra-Low Bitrate Neural S…

This letter introduces EGGCodec, a robust neural Encodec framework engineered for electroglottography (EGG) signal reconstruction and F0 extraction. We propose a multi-scale frequency-domain loss function to capture the nuanced relationship…

Vector Quantized Variational Autoencoders (VQ-VAEs) leverage self-supervised learning through reconstruction tasks to represent continuous vectors using the closest vectors in a codebook. However, issues such as codebook collapse persist in…

Most existing approaches for image and video compression perform transform coding in the pixel space to reduce redundancy. However, due to the misalignment between the pixel-space distortion and human perception, such schemes often face the…

Vector quantization (VQ) underpins modern generative and representation models by turning continuous latents into discrete tokens. Yet hard nearest-neighbor assignments are non-differentiable and are typically optimized with heuristic…

In this paper we introduce a recurrent neural network (RNN) based variational autoencoder (VAE) model with a new constrained loss function that can generate more meaningful electroencephalography (EEG) features from raw EEG features to…

Variational encoder-decoders (VEDs) have shown promising results in dialogue generation. However, the latent variable distributions are usually approximated by a much simpler model than the powerful RNN structure used for encoding and…

Accurate, low-latency endpointing is crucial for effective spoken dialogue systems. While traditional endpointers often rely on spectrum-based audio features, this work proposes real-time speech endpointing for multi-turn dialogues using…

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…

In this paper, we propose a novel deep neural network architecture, Sequence-to-Sequence Audio2Vec, for unsupervised learning of fixed-length vector representations of audio segments excised from a speech corpus, where the vectors contain…

Most discrete visual tokenizers rely on a default design: every position in the sequence shares the same codebook. Researchers try to scale the codebook size $K$ to get better reconstruction performance. Such a constant-codebook design hits…

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…

Speech tokenization is crucial in digital speech processing, converting continuous speech signals into discrete units for various computational tasks. This paper introduces a novel speech tokenizer with broad applicability across downstream…

Neural codecs have demonstrated strong performance in high-fidelity compression of audio signals at low bitrates. The token-based representations produced by these codecs have proven particularly useful for generative modeling. While much…

Incremental redundancy with ACK/NACK feedback produces a variable-length stop-feedback (VLSF) code constrained to have $m$ decoding times, with an ACK/NACK feedback to the transmitter at each decoding time. This paper focuses on the…

Continuous value prediction plays a crucial role in industrial-scale recommendation systems, including tasks such as predicting users' watch-time and estimating the gross merchandise value (GMV) in e-commerce transactions. However, it…

In streaming settings, speech recognition models have to map sub-sequences of speech to text before the full audio stream becomes available. However, since alignment information between speech and text is rarely available during training,…

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…

We propose \textbf{U-Codec}, an \textbf{U}ltra low frame-rate neural speech \textbf{Codec} that achieves high-fidelity reconstruction and fast speech generation at an extremely low frame-rate of 5Hz (5 frames per second). Extreme…

We introduce LMCodec, a causal neural speech codec that provides high quality audio at very low bitrates. The backbone of the system is a causal convolutional codec that encodes audio into a hierarchy of coarse-to-fine tokens using residual…

Vector Quantized Variational AutoEncoders (VQ-VAEs) are designed to compress a continuous input to a discrete latent space and reconstruct it with minimal distortion. They operate by maintaining a set of vectors -- often referred to as the…