Related papers: Performance Modeling for Correlation-based Neural …
Speech-based depression detection tools could aid early screening. Here, we propose an interpretable speech foundation model approach to enhance the clinical applicability of such tools. We introduce a speech-level Audio Spectrogram…
The attention mechanism is a core component of the Transformer architecture. Various methods have been developed to compute attention scores, including multi-head attention (MHA), multi-query attention, group-query attention and so on. We…
Interleaving is a mechanism universally used in wireless access technologies to alleviate the effect of channel correlation. In spite of its wide adoption, to the best of our knowledge, there are no analytical models proposed so far. In…
Factorizing speech as disentangled speech representations is vital to achieve highly controllable style transfer in voice conversion (VC). Conventional speech representation learning methods in VC only factorize speech as speaker and…
Audio-visual speech enhancement system is regarded as one of promising solutions for isolating and enhancing speech of desired speaker. Typical methods focus on predicting clean speech spectrum via a naive convolution neural network based…
Today, data collection has improved in various areas, and the medical domain is no exception. Auscultation, as an important diagnostic technique for physicians, due to the progress and availability of digital stethoscopes, lends itself well…
Contextual biasing improves automatic speech recognition (ASR) by integrating external knowledge, such as user-specific phrases or entities, during decoding. In this work, we use an attention-based biasing decoder to produce scores for…
The conventional wisdom has been that designing ultra-compact, battery-constrained wireless hearables with on-device speech AI models is challenging due to the high computational demands of streaming deep learning models. Speech AI models…
Recently, end-to-end speech recognition with a hybrid model consisting of the connectionist temporal classification(CTC) and the attention encoder-decoder achieved state-of-the-art results. In this paper, we propose a novel CTC decoder…
The forecasting skill of numerical weather prediction (NWP) models critically depends on the accurate initial conditions, also known as analysis, provided by data assimilation (DA). Traditional DA methods often face a trade-off between…
Measuring performance of an automatic speech recognition (ASR) system without ground-truth could be beneficial in many scenarios, especially with data from unseen domains, where performance can be highly inconsistent. In conventional ASR…
At the end of Moore's law, new computing paradigms are required to prolong the battery life of wearable and IoT smart audio devices. Theoretical analysis and physical validation have shown that analog signal processing (ASP) can be more…
Active speaker detection (ASD) systems are important modules for analyzing multi-talker conversations. They aim to detect which speakers or none are talking in a visual scene at any given time. Existing research on ASD does not agree on the…
Most current speech technology systems are designed to operate well even in the presence of multiple active speakers. However, most solutions assume that the number of co-current speakers is known. Unfortunately, this information might not…
Audio-visual navigation tasks require agents to locate and navigate toward continuously vocalizing targets using only visual observations and acoustic cues. However, existing methods mainly rely on simple feature concatenation or late…
Adding explanations to audio deepfake detection (ADD) models will boost their real-world application by providing insight on the decision making process. In this paper, we propose a relevancy-based explainable AI (XAI) method to analyze the…
Developing and selecting hearing aids is a time consuming process which is simplified by using objective models. Previously, the framework for auditory discrimination experiments (FADE) accurately simulated benefits of hearing aid…
Auditory attention to natural speech is a complex brain process. Its quantification from physiological signals can be valuable to improving and widening the range of applications of current brain-computer-interface systems, however it…
Most machine learning and data analytics applications, including performance engineering in software systems, require a large number of annotations and labelled data, which might not be available in advance. Acquiring annotations often…
Attention mechanisms are widely used in current encoder/decoder frameworks of image captioning, where a weighted average on encoded vectors is generated at each time step to guide the caption decoding process. However, the decoder has…