Related papers: Unified Microphone Conversion: Many-to-Many Device…

Although many efforts have been made on decreasing the model complexity for speaker verification, it is still challenging to deploy speaker verification systems with satisfactory result on low-resource terminals. We design a transformation…

Audio classification is vital in areas such as speech and music recognition. Feature extraction from the audio signal, such as Mel-Spectrograms and MFCCs, is a critical step in audio classification. These features are transformed into…

Federated learning has emerged as a promising approach for training machine learning models on decentralized data sources while preserving data privacy. However, challenges such as communication bottlenecks, heterogeneity of client devices,…

Recent progress on end-to-end neural diarization (EEND) has enabled overlap-aware speaker diarization with a single neural network. This paper proposes to enhance EEND by using multi-channel signals from distributed microphones. We replace…

Generative recommendation models often struggle with two key challenges: (1) the superficial integration of collaborative signals, and (2) the decoupled fusion of multimodal features. These limitations hinder the creation of a truly…

In this paper, we propose a multi-label classification framework to detect multiple speaking styles in a speech sample. Unlike previous studies that have primarily focused on identifying a single target style, our framework effectively…

In human conversation an input post is open to multiple potential responses, which is typically regarded as a one-to-many problem. Promising approaches mainly incorporate multiple latent mechanisms to build the one-to-many relationship.…

Recently, text-to-image generation models have achieved remarkable advancements, particularly with diffusion models facilitating high-quality image synthesis from textual descriptions. However, these models often struggle with achieving…

Multisequence Magnetic Resonance Imaging (MRI) provides a more reliable diagnosis in clinical applications through complementary information across sequences. However, in practice, the absence of certain MR sequences is a common problem…

We introduce an approach to multilingual speech synthesis which uses the meta-learning concept of contextual parameter generation and produces natural-sounding multilingual speech using more languages and less training data than previous…

With excellent generalization ability, self-supervised speech models have shown impressive performance on various downstream speech tasks in the pre-training and fine-tuning paradigm. However, as the growing size of pre-trained models,…

Goal-oriented communication has become one of the focal concepts in sixth-generation communication systems owing to its potential to provide intelligent, immersive, and real-time mobile services. The emerging paradigms of goal-oriented…

We propose a data-driven sparse recovery framework for hybrid spherical linear microphone arrays using singular value decomposition (SVD) of the transfer operator. The SVD yields orthogonal microphone and field modes, reducing to spherical…

Adapter parameters provide a mechanism to modify the behavior of machine learning models and have gained significant popularity in the context of large language models (LLMs) and generative AI. These parameters can be merged to support…

Deep generative models can generate high-fidelity audio conditioned on various types of representations (e.g., mel-spectrograms, Mel-frequency Cepstral Coefficients (MFCC)). Recently, such models have been used to synthesize audio waveforms…

Model fine-tuning and adaptation have become a common approach for model specialization for downstream tasks or domains. Fine-tuning the entire model or a subset of the parameters using light-weight adaptation has shown considerable success…

Recent parameter-efficient language model tuning (PELT) methods manage to match the performance of fine-tuning with much fewer trainable parameters and perform especially well when training data is limited. However, different PELT methods…

We propose a unified Transformer-based architecture for wireless signal processing tasks, offering a low-latency, task-adaptive alternative to conventional receiver pipelines. Unlike traditional modular designs, our model integrates channel…

Generative recommendation has recently emerged as a transformative paradigm that directly generates target items, surpassing traditional cascaded approaches. It typically involves two components: a tokenizer that learns item identifiers and…

While Unified Multimodal Models (UMMs) have achieved remarkable success in cross-modal comprehension, a significant gap persists in their ability to leverage such internal knowledge for high-quality generation. We formalize this discrepancy…