Related papers: Fine-grained Early Frequency Attention for Deep Sp…

State-of-the-art Deep Learning systems for speaker verification are commonly based on speaker embedding extractors. These architectures are usually composed of a feature extractor front-end together with a pooling layer to encode…

We introduce a two-stage self-supervised framework that combines the Joint-Embedding Predictive Architecture (JEPA) with a Density Adaptive Attention Mechanism (DAAM) for learning robust speech representations. Stage~1 uses JEPA with DAAM…

Speech contains both acoustic and linguistic patterns that reflect cognitive decline, and therefore models describing only one domain cannot fully capture such complexity. This study investigates how early fusion (EF) of speech and its…

Transformer-based architectures have become the prevailing backbone of large language models. However, the quadratic time and memory complexity of self-attention remains a fundamental obstacle to efficient long-context modeling. To address…

Despite their exceptional performance on various tasks after fine-tuning, pre-trained language models (PLMs) face significant challenges due to growing privacy concerns with data in centralized training methods. We consider federated…

Recent work on speech representation models jointly pre-trained with text has demonstrated the potential of improving speech representations by encoding speech and text in a shared space. In this paper, we leverage such shared…

Deep learning is progressively gaining popularity as a viable alternative to i-vectors for speaker recognition. Promising results have been recently obtained with Convolutional Neural Networks (CNNs) when fed by raw speech samples directly.…

This paper proposes a speech emotion recognition method based on speech features and speech transcriptions (text). Speech features such as Spectrogram and Mel-frequency Cepstral Coefficients (MFCC) help retain emotion-related low-level…

Existing methods for deepfake audio detection have demonstrated some effectiveness. However, they still face challenges in generalizing to new forgery techniques and evolving attack patterns. This limitation mainly arises because the models…

Transformer-based models have been widely adopted for sentiment analysis tasks due to their exceptional ability to capture contextual information. However, these methods often exhibit suboptimal accuracy in certain scenarios. By analyzing…

Speaker recognition models face challenges in multi-lingual settings due to the entanglement of linguistic information within speaker embeddings. The overlap between vocal traits such as accent, vocal anatomy, and a language's phonetic…

Most deep learning-based models for speech enhancement have mainly focused on estimating the magnitude of spectrogram while reusing the phase from noisy speech for reconstruction. This is due to the difficulty of estimating the phase of…

Multi-speaker speech recognition has been one of the keychallenges in conversation transcription as it breaks the singleactive speaker assumption employed by most state-of-the-artspeech recognition systems. Speech separation is consideredas…

Spectrogram is commonly used as the input feature of deep neural networks to learn the high(er)-level time-frequency pattern of speech signal for speech emotion recognition (SER). \textcolor{black}{Generally, different emotions correspond…

Developing comprehensive assistive technologies requires the seamless integration of visual and auditory perception. This research evaluates the feasibility of a modular architecture inspired by core functionalities of perceptive systems…

Previous research has shown that the principal singular vectors of a pre-trained model's weight matrices capture critical knowledge. In contrast, those associated with small singular values may contain noise or less reliable information. As…

Speaker individuality information is among the most critical elements within speech signals. By thoroughly and accurately modeling this information, it can be utilized in various intelligent speech applications, such as speaker recognition,…

Speaker identification systems in a real-world scenario are tasked to identify a speaker amongst a set of enrolled speakers given just a few samples for each enrolled speaker. This paper demonstrates the effectiveness of meta-learning and…

Large, pre-trained representation models trained using self-supervised learning have gained popularity in various fields of machine learning because they are able to extract high-quality salient features from input data. As such, they have…

Advances in deep learning have led to state-of-the-art performance across a multitude of speech recognition tasks. Nevertheless, the widespread deployment of deep neural networks for on-device speech recognition remains a challenge,…