Related papers: Adaptive Slimming for Scalable and Efficient Speec…

An embedding-based speaker adaptive training (SAT) approach is proposed and investigated in this paper for deep neural network acoustic modeling. In this approach, speaker embedding vectors, which are a constant given a particular speaker,…

It has been shown that the intelligibility of noisy speech can be improved by speech enhancement (SE) algorithms. However, monaural SE has not been established as an effective frontend for automatic speech recognition (ASR) in noisy…

In this paper, we present a dynamically reconfigurable hardware accelerator called FADES (Fused Architecture for DEnse and Sparse matrices). The FADES design offers multiple configuration options that trade off parallelism and complexity…

We study speech enhancement using deep learning (DL) for virtual meetings on cellular devices, where transmitted speech has background noise and transmission loss that affects speech quality. Since the Deep Noise Suppression (DNS) Challenge…

Despite speaker verification has achieved significant performance improvement with the development of deep neural networks, domain mismatch is still a challenging problem in this field. In this study, we propose a novel framework to…

The recently proposed Conformer model has become the de facto backbone model for various downstream speech tasks based on its hybrid attention-convolution architecture that captures both local and global features. However, through a series…

Current hearing aids normally provide amplification based on a general prescriptive fitting, and the benefits provided by the hearing aids vary among different listening environments despite the inclusion of noise suppression feature.…

Understanding the internal representations of large language models (LLMs) remains a central challenge for interpretability research. Sparse autoencoders (SAEs) offer a promising solution by decomposing activations into interpretable…

With the rapid development of speech assistants, adapting server-intended automatic speech recognition (ASR) solutions to a direct device has become crucial. Researchers and industry prefer to use end-to-end ASR systems for on-device speech…

An inferior performance of the streaming automatic speech recognition models versus non-streaming model is frequently seen due to the absence of future context. In order to improve the performance of the streaming model and reduce the…

Continuous speech can be converted into a discrete sequence by deriving discrete units from the hidden features of self-supervised learned (SSL) speech models. Although SSL models are becoming larger and trained on more data, they are often…

The last decade has witnessed significant advancements in deep learning-based speech enhancement (SE). However, most existing SE research has limitations on the coverage of SE sub-tasks, data diversity and amount, and evaluation metrics. To…

While Mixture-of-Experts (MoE) scales model capacity without proportionally increasing computation, its massive total parameter footprint creates significant storage and memory-access bottlenecks, which hinder efficient end-side deployment…

The integration of pre-trained text-based large language models (LLM) with speech input has enabled instruction-following capabilities for diverse speech tasks. This integration requires the use of a speech encoder, a speech adapter, and an…

In this work, we further develop the conformer-based metric generative adversarial network (CMGAN) model for speech enhancement (SE) in the time-frequency (TF) domain. This paper builds on our previous work but takes a more in-depth look by…

We consider network-based decentralized optimization problems, where each node in the network possesses a local function and the objective is to collectively attain a consensus solution that minimizes the sum of all the local functions. A…

Fine-tuning large language models is essential for task-specific adaptation, yet it remains computationally prohibitive. Parameter-Efficient Fine-Tuning (PEFT) methods have emerged as a solution, but current approaches typically ignore the…

We investigate the integration of stacked intelligent metasurfaces (SIMs) into cell-free massive multiple input multiple output (CF-mMIMO) system to enhance the simultaneous wireless information and power transfer (SWIPT) performance.…

In this paper, we propose a novel Adaptive Transmission Strategy to improve energy efficiency~(EE) in a wireless point-to-point transmission system with Quality of Service~(QoS) requirement, i.e., delay-outage probability considered. The…

In recent years, there have been studies to further improve the end-to-end neural speaker diarization (EEND) systems. This letter proposes the EEND-DEMUX model, a novel framework utilizing demultiplexed speaker embeddings. In this work, we…