Related papers: AmbiDrop: Array-Agnostic Speech Enhancement Using …

Multilingual automatic speech recognition (ASR) systems mostly benefit low resource languages but suffer degradation in performance across several languages relative to their monolingual counterparts. Limited studies have focused on…

Deep neural networks possess strong representational capacity yet remain vulnerable to overfitting, primarily because neurons tend to co-adapt in ways that, while capturing complex and fine-grained feature interactions, also reinforce…

Automatic speech recognition (ASR) has been widely researched with supervised approaches, while many low-resourced languages lack audio-text aligned data, and supervised methods cannot be applied on them. In this work, we propose a…

Neural transducers have achieved human level performance on standard speech recognition benchmarks. However, their performance significantly degrades in the presence of cross-talk, especially when the primary speaker has a low…

Increasing the volume of training data can enable the auxiliary diagnostic algorithms for Autism Spectrum Disorder (ASD) to learn more accurate and stable models. However, due to the significant heterogeneity and domain shift in rs-fMRI…

Textual-based prompt learning methods primarily employ multiple learnable soft prompts and hard class tokens in a cascading manner as text inputs, aiming to align image and text (category) spaces for downstream tasks. However, current…

Data augmentation is an inexpensive way to increase training data diversity and is commonly achieved via transformations of existing data. For tasks such as classification, there is a good case for learning representations of the data that…

Scene-based spatial audio formats, such as Ambisonics, are playback system agnostic and may therefore be favoured for delivering immersive audio experiences to a wide range of (potentially unknown) devices. The number of channels required…

In the domain of air traffic control (ATC) systems, efforts to train a practical automatic speech recognition (ASR) model always faces the problem of small training samples since the collection and annotation of speech samples are expert-…

Unsupervised Domain Adaptation (UDA) is the task of bridging the domain gap between a labeled source domain, e.g., synthetic data, and an unlabeled target domain. We observe that current UDA methods show inferior results on fine structures…

In this paper, we present a method for jointly-learning a microphone selection mechanism and a speech enhancement network for multi-channel speech enhancement with an ad-hoc microphone array. The attention-based microphone selection…

Training convolutional recurrent neural networks on first-order Ambisonics signals is a well-known approach when estimating the direction of arrival for speech/sound signals. In this work, we investigate whether increasing the order of…

Automatic Speech Recognition (ASR) is an integral component of modern technology, powering applications such as voice-activated assistants, transcription services, and accessibility tools. Yet ASR systems continue to struggle with the…

Speech separation with several speakers is a challenging task because of the non-stationarity of the speech and the strong signal similarity between interferent sources. Current state-of-the-art solutions can separate well the different…

Many mispronunciation detection and diagnosis (MD&D) research approaches try to exploit both the acoustic and linguistic features as input. Yet the improvement of the performance is limited, partially due to the shortage of large amount…

We propose BeamTransformer, an efficient architecture to leverage beamformer's edge in spatial filtering and transformer's capability in context sequence modeling. BeamTransformer seeks to optimize modeling of sequential relationship among…

Existing deep learning-based speech denoising approaches require clean speech signals to be available for training. This paper presents a deep learning-based approach to improve speech denoising in real-world audio environments by not…

This contribution introduces a dataset of 7th-order Ambisonic Room Impulse Responses (HOA-RIRs), created using the Image Source Method. By employing higher-order Ambisonics, our dataset enables precise spatial audio reproduction, a critical…

Pretrained language models have achieved remarkable success in natural language understanding. However, fine-tuning pretrained models on limited training data tends to overfit and thus diminish performance. This paper presents Bi-Drop, a…

Automatic dubbing, which generates a corresponding version of the input speech in another language, could be widely utilized in many real-world scenarios such as video and game localization. In addition to synthesizing the translated…