Related papers: SEMamba++: A General Speech Restoration Framework …

Recent sequence modeling approaches using selective state space sequence models, referred to as Mamba models, have seen a surge of interest. These models allow efficient processing of long sequences in linear time and are rapidly being…

Multilingual automatic speech recognition (ASR) remains a challenging task, especially when balancing performance across high- and low-resource languages. Recent advances in sequence modeling suggest that architectures beyond Transformers…

This paper proposes a novel joint multi-speaker tracking-and-separation method based on the generalized labeled multi-Bernoulli (GLMB) multi-target tracking filter, using sound mixtures recorded by microphones. Standard multi-speaker…

Large language models (LLMs) have advanced significantly due to the attention mechanism, but their quadratic complexity and linear memory demands limit their performance on long-context tasks. Recently, researchers introduced Mamba, an…

In this study, we propose a modulation decoupling based single channel speech enhancement subspace framework, in which the spectrogram of noisy speech is decoupled as the product of a spectral envelop subspace and a spectral details…

We propose FSB-LSTM, a novel long short-term memory (LSTM) based architecture that integrates full- and sub-band (FSB) modeling, for single- and multi-channel speech enhancement in the short-time Fourier transform (STFT) domain. The model…

Speech enhancement models should meet very low latency requirements typically smaller than 5 ms for hearing assistive devices. While various low-latency techniques have been proposed, comparing these methods in a controlled setup using DNNs…

High quality speech capture has been widely studied for both voice communication and human computer interface reasons. To improve the capture performance, we can often find multi-microphone speech enhancement techniques deployed on various…

Teleconferencing is becoming essential during the COVID-19 pandemic. However, in real-world applications, speech quality can deteriorate due to, for example, background interference, noise, or reverberation. To solve this problem, target…

The objective of this work is to develop a speaker recognition model to be used in diverse scenarios. We hypothesise that two components should be adequately configured to build such a model. First, adequate architecture would be required.…

The capability of the human to pay attention to both coarse and fine-grained regions has been applied to computer vision tasks. Motivated by that, we propose a collaborative learning framework in the complex domain for monaural noise…

Goal: Numerous studies had successfully differentiated normal and abnormal voice samples. Nevertheless, further classification had rarely been attempted. This study proposes a novel approach, using continuous Mandarin speech instead of a…

The recent surge in State Space Models (SSMs), particularly the emergence of Mamba, has established them as strong alternatives or complementary modules to Transformers across diverse domains. In this work, we aim to explore the potential…

The Transformer architecture has shown a remarkable ability in modeling global relationships. However, it poses a significant computational challenge when processing high-dimensional medical images. This hinders its development and…

With the explosive growth of data, long-sequence modeling has become increasingly important in tasks such as natural language processing and bioinformatics. However, existing methods face inherent trade-offs between efficiency and memory.…

Multi-channel speech separation in dynamic environments is challenging as time-varying spatial and spectral features evolve at different temporal scales. Existing methods typically employ sequential architectures, forcing a single network…

Deep learning models are widely used for speaker recognition and spoofing speech detection. We propose the GMM-ResNet2 for synthesis speech detection. Compared with the previous GMM-ResNet model, GMM-ResNet2 has four improvements. Firstly,…

When the parameters of Bayesian Short-time Spectral Amplitude (STSA) estimator for speech enhancement are selected based on the characteristics of the human auditory system, the gain function of the estimator becomes more flexible. Although…

This paper presents CleanUMamba, a time-domain neural network architecture designed for real-time causal audio denoising directly applied to raw waveforms. CleanUMamba leverages a U-Net encoder-decoder structure, incorporating the Mamba…

With new sequence models like Mamba and xLSTM, several studies have shown that these models match or outperform the state-of-the-art in single-channel speech enhancement and audio representation learning. However, prior research has…