Related papers: A Speech Intelligibility Enhancement Model based o…

We introduce a deep learning model for speech denoising, a long-standing challenge in audio analysis arising in numerous applications. Our approach is based on a key observation about human speech: there is often a short pause between each…

Accurate uncertainty quantification is crucial for the safe deployment of machine learning models, and prior research has demonstrated improvements in the calibration of modern language models (LMs). We study in-context learning (ICL), a…

This study presents a deep learning-based speech signal-processing mobile application known as CITISEN. The CITISEN provides three functions: speech enhancement (SE), model adaptation (MA), and background noise conversion (BNC), allowing…

Despite the recent success of machine learning algorithms, most models face drawbacks when considering more complex tasks requiring interaction between different sources, such as multimodal input data and logical time sequences. On the…

Many speech enhancement (SE) methods rely on continuous representations. Recently, discrete audio tokens have been explored to enable autoregressive generation for SE. However, it remains unclear whether discretization itself consistently…

In-context learning (ICL) has emerged as an effective approach to enhance the performance of large language models (LLMs). However, its effectiveness varies significantly across models and tasks, posing challenges for practitioners to…

Speech emotion recognition (SER) systems often struggle in real-world environments, where ambient noise severely degrades their performance. This paper explores a novel approach that exploits prior knowledge of testing environments to…

Conversational AI has made significant progress, yet generating expressive and controllable text-to-speech (TTS) remains challenging. Specifically, controlling fine-grained voice styles and emotions is notoriously difficult and typically…

Although LLM-based conversational agents demonstrate strong fluency and coherence, they still produce undesirable behaviors (errors) that are challenging to prevent from reaching users during deployment. Recent research leverages large…

Large Audio Language Models (LALMs), which couple acoustic perception with large language models (LLMs) to extract and understand diverse information from audio, have attracted intense interest from both academic and industrial communities.…

In this paper we show how we have achieved the state-of-the-art performance on the industry-standard NIST 2000 Hub5 English evaluation set. We explore densely connected LSTMs, inspired by the densely connected convolutional networks…

Speech intelligibility can be degraded due to multiple factors, such as noisy environments, technical difficulties or biological conditions. This work is focused on the development of an automatic non-intrusive system for predicting the…

Softwarized radio access networks (RANs), such as those based on the Open RAN (O-RAN) architecture, generate rich streams of key performance indicators (KPIs) that can be leveraged to extract actionable intelligence for network…

Identifying the target speaker in hearing aid applications is crucial to improve speech understanding. Recent advances in electroencephalography (EEG) have shown that it is possible to identify the target speaker from single-trial EEG…

The widespread use of automated voice assistants along with other recent technological developments have increased the demand for applications that process audio signals and human voice in particular. Voice recognition tasks are typically…

Deep embedding based text-independent speaker verification has demonstrated superior performance to traditional methods in many challenging scenarios. Its loss functions can be generally categorized into two classes, i.e., verification and…

For a speech-enhancement algorithm, it is highly desirable to simultaneously improve perceptual quality and recognition rate. Thanks to computational costs and model complexities, it is challenging to train a model that effectively…

We propose a method to perform audio event detection under the common constraint that only limited training data are available. In training a deep learning system to perform audio event detection, two practical problems arise. Firstly, most…

The deep learning-based speech enhancement (SE) methods always take the clean speech's waveform or time-frequency spectrum feature as the learning target, and train the deep neural network (DNN) by reducing the error loss between the DNN's…

Lack of training data presents a grand challenge to scaling out spoken language understanding (SLU) to low-resource languages. Although various data augmentation approaches have been proposed to synthesize training data in low-resource…