相关论文: Emotion-Aware Quantization for Discrete Speech Rep…

Deep neural networks with discrete latent variables offer the promise of better symbolic reasoning, and learning abstractions that are more useful to new tasks. There has been a surge in interest in discrete latent variable models, however,…

One noted issue of vector-quantized variational autoencoder (VQ-VAE) is that the learned discrete representation uses only a fraction of the full capacity of the codebook, also known as codebook collapse. We hypothesize that the training…

Learning the latent representation of data in unsupervised fashion is a very interesting process that provides relevant features for enhancing the performance of a classifier. For speech emotion recognition tasks, generating effective…

We investigate the effects of post-training quantization and quantization-aware training on the generalization of Transformer language models. We present a new method called self-distilled quantization (SDQ) that minimizes accumulative…

Acoustic emotion recognition aims to categorize the affective state of the speaker and is still a difficult task for machine learning models. The difficulties come from the scarcity of training data, general subjectivity in emotion…

The Emotional Voice Conversion (EVC) aims to convert the discrete emotional state from the source emotion to the target for a given speech utterance while preserving linguistic content. In this paper, we propose regularizing emotion…

With advances in deep learning, neural network based speech enhancement (SE) has developed rapidly in the last decade. Meanwhile, the self-supervised pre-trained model and vector quantization (VQ) have achieved excellent performance on many…

Dimensional representations of speech emotions such as the arousal-valence (AV) representation provide a continuous and fine-grained description and control than their categorical counterparts. They have wide applications in tasks such as…

Vector quantization is a fundamental tool for compressing high-dimensional embeddings, yet existing multi-codebook methods rely on static codebooks that limit expressiveness under heterogeneous data geometry. While recent dynamic quantizers…

Recent advancements in learning Discrete Representations as opposed to continuous ones have led to state of art results in tasks that involve Language, Audio and Vision. Some latent factors such as words, phonemes and shapes are better…

Uncovering emergent concepts across transformer layers remains a significant challenge because the residual stream linearly mixes and duplicates information, obscuring how features evolve within large language models. Current research…

The field of emergent communication aims to understand the characteristics of communication as it emerges from artificial agents solving tasks that require information exchange. Communication with discrete messages is considered a desired…

The rapid growth of visual data under stringent storage and bandwidth constraints makes extremely low-bitrate image compression increasingly important. While Vector Quantization (VQ) offers strong structural fidelity, existing methods lack…

The rapid rise of real-time communication and large language models has significantly increased the importance of speech compression. Deep learning-based neural speech codecs have outperformed traditional signal-level speech codecs in terms…

Vector Quantization (VQ) has emerged as a prominent weight compression technique, showcasing substantially lower quantization errors than uniform quantization across diverse models, particularly in extreme compression scenarios. However,…

In Emotion Recognition in Conversations (ERC), the emotions of target utterances are closely dependent on their context. Therefore, existing works train the model to generate the response of the target utterance, which aims to recognise…

Emotion recognition (ER) from speech signals is a robust approach since it cannot be imitated like facial expression or text based sentiment analysis. Valuable information underlying the emotions are significant for human-computer…

In human-computer interaction (HCI), Speech Emotion Recognition (SER) is a key technology for understanding human intentions and emotions. Traditional SER methods struggle to effectively capture the long-term temporal correla-tions and…

Learning useful representations without supervision remains a key challenge in machine learning. In this paper, we propose a simple yet powerful generative model that learns such discrete representations. Our model, the Vector…

Powerful large language models (LLMs) are increasingly expected to be deployed with lower computational costs, enabling their capabilities on resource-constrained devices. Post-training quantization (PTQ) has emerged as a star approach to…