Related papers: Scattering Transform for Auditory Attention Decodi…

The recent emergence of joint CTC-Attention model shows significant improvement in automatic speech recognition (ASR). The improvement largely lies in the modeling of linguistic information by decoder. The decoder joint-optimized with an…

Nowadays, pre-trained sequence-to-sequence models such as BERTSUM and BART have shown state-of-the-art results in abstractive summarization. In these models, during fine-tuning, the encoder transforms sentences to context vectors in the…

Scattering hinders the passage of light through random media and consequently limits the usefulness of optical techniques for sensing and imaging. Thus, methods for increasing the transmission of light through such random media are of…

Alzheimer's disease and related dementias (ADRD) affect one in five adults over 60, yet more than half of individuals with cognitive decline remain undiagnosed. Speech-based assessments show promise for early detection, as phonetic motor…

Identifying multiple speakers without knowing where a speaker's voice is in a recording is a challenging task. This paper proposes a hierarchical network with transformer encoders and memory mechanism to address this problem. The proposed…

Over the past two decades, CNN architectures have produced compelling models of sound perception and cognition, learning hierarchical organizations of features. Analogous to successes in computer vision, audio feature classification can be…

Transformer architectures have emerged as promising deep learning (DL) tools for modeling complex sequence-to-sequence interactions in channel decoding. However, current transformer-based decoders for error correction codes (ECCs)…

At least 360 million people worldwide have disabling hearing loss that frequently causes difficulties in day-to-day conversations. Hearing aids often fail to offer enough benefits and have low adoption rates. However, people with hearing…

Most recent speaker verification systems are based on extracting speaker embeddings using a deep neural network. The pooling layer in the network aims to aggregate frame-level features extracted by the backbone. In this paper, we propose a…

Spatiotemporal predictive learning offers a self-supervised learning paradigm that enables models to learn both spatial and temporal patterns by predicting future sequences based on historical sequences. Mainstream methods are dominated by…

This paper studies interpretable and fair artificial intelligence architectures for understanding English reading. Introduced transformer-based models, integrating advanced attention mechanisms and gradient-based feature attribution. The…

We describe some recent advances in the numerical solution of acoustic scattering problems. A major focus of the paper is the efficient solution of high frequency scattering problems via hybrid numerical-asymptotic boundary element methods.…

An utterance that contains speech from multiple languages is known as a code-switched sentence. In this work, we propose a novel technique to predict whether given audio is mono-lingual or code-switched. We propose a multi-modal learning…

Deep learning based models have significantly improved the performance of speech separation with input mixtures like the cocktail party. Prominent methods (e.g., frequency-domain and time-domain speech separation) usually build regression…

Sound event detection (SED) methods that leverage a large pre-trained Transformer encoder network have shown promising performance in recent DCASE challenges. However, they still rely on an RNN-based context network to model temporal…

This thesis focuses on representation learning for sequence data over time or space, aiming to improve downstream sequence prediction tasks by using the learned representations. Supervised learning has been the most dominant approach for…

In this paper, we propose EDIT (Encoder-Decoder Image Transformer), a novel architecture designed to mitigate the attention sink phenomenon observed in Vision Transformer models. Attention sink occurs when an excessive amount of attention…

We present Translatotron 2, a neural direct speech-to-speech translation model that can be trained end-to-end. Translatotron 2 consists of a speech encoder, a linguistic decoder, an acoustic synthesizer, and a single attention module that…

Studies have shown that in noisy acoustic environments, providing binaural signals to the user of an assistive listening device may improve speech intelligibility and spatial awareness. This paper presents a binaural speech enhancement…

Speech pre-processing techniques such as denoising, de-reverberation, and separation, are commonly employed as front-ends for various downstream speech processing tasks. However, these methods can sometimes be inadequate, resulting in…