Related papers: Noise Robust Speech Recognition Using Multi-Channe…

Over the recent years, various deep learning-based methods were proposed for extracting a fixed-dimensional embedding vector from speech signals. Although the deep learning-based embedding extraction methods have shown good performance in…

This paper proposes a multi-task learning network with phoneme-aware and channel-wise attentive learning strategies for text-dependent Speaker Verification (SV). In the proposed structure, the frame-level multi-task learning along with the…

Recent advances in large language models (LLMs) have promoted generative error correction (GER) for automatic speech recognition (ASR), which leverages the rich linguistic knowledge and powerful reasoning ability of LLMs to improve…

In this study, we try to address the problem of leveraging visual signals to improve Automatic Speech Recognition (ASR), also known as visual context-aware ASR (VC-ASR). We explore novel VC-ASR approaches to leverage video and text…

This paper proposes AS-ASR, a lightweight aphasia-specific speech recognition framework based on Whisper-tiny, tailored for low-resource deployment on edge devices. Our approach introduces a hybrid training strategy that systematically…

Speech communication systems are prone to performance degradation in reverberant and noisy acoustic environments. Dereverberation and noise reduction algorithms typically require several model parameters, e.g. the speech, reverberation and…

We introduce a noisy channel approach for language model prompting in few-shot text classification. Instead of computing the likelihood of the label given the input (referred as direct models), channel models compute the conditional…

Multi-channel acoustic signal processing is a well-established and powerful tool to exploit the spatial diversity between a target signal and non-target or noise sources for signal enhancement. However, the textbook solutions for optimal…

Discretized representations of speech signals are efficient alternatives to continuous features for various speech applications, including automatic speech recognition (ASR) and speech language models. However, these representations, such…

State-of-the-art language models (LMs) represented by long-short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming increasingly complex and expensive for practical applications. Low-bit neural network…

Learning robust speaker representations under noisy conditions presents significant challenges, which requires careful handling of both discriminative and noise-invariant properties. In this work, we proposed an anchor-based stage-wise…

In recent years, monaural speech separation has been formulated as a supervised learning problem, which has been systematically researched and shown the dramatical improvement of speech intelligibility and quality for human listeners.…

Obtaining channel covariance knowledge is of great importance in various Multiple-Input Multiple-Output MIMO communication applications, including channel estimation and covariance-based user grouping. In a massive MIMO system, covariance…

In automatic speech recognition (ASR), wideband (WB) and narrowband (NB) speech signals with different sampling rates typically use separate acoustic models. Therefore mixed-bandwidth (MB) acoustic modeling has important practical values…

Multimodal large language models (MLLMs) have recently become a focal point of research due to their formidable multimodal understanding capabilities. For example, in the audio and speech domains, an LLM can be equipped with (automatic)…

Recently, deep end-to-end learning has been studied for intent classification in Spoken Language Understanding (SLU). However, end-to-end models require a large amount of speech data with intent labels, and highly optimized models are…

In existing Audio-Visual Speech Enhancement (AVSE) methods, objectives such as Scale-Invariant Signal-to-Noise Ratio (SI-SNR) and Mean Squared Error (MSE) are widely used; however, they often correlate poorly with perceptual quality and…

In the intricate acoustic landscapes where speech intelligibility is challenged by noise and reverberation, multichannel speech enhancement emerges as a promising solution for individuals with hearing loss. Such algorithms are commonly…

In end-to-end multi-channel speech enhancement, the traditional approach of designating one microphone signal as the reference for processing may not always yield optimal results. The limitation is particularly in scenarios with large…

This study addresses a key limitation in deep learning Automatic Modulation Classification (AMC) models, which perform well at high signal-to-noise ratios (SNRs) but degrade under noisy conditions due to conventional feature extraction…