相关论文: Speech Slytherin: Examining the Performance and Ef…

Transformers have been the most successful architecture for various speech modeling tasks, including speech separation. However, the self-attention mechanism in transformers with quadratic complexity is inefficient in computation and…

This paper explores the capability of Mamba, a recently proposed architecture based on state space models (SSMs), as a competitive alternative to Transformer-based models. In the speech domain, well-designed Transformer-based models, such…

Transformer and its derivatives have achieved success in diverse tasks across computer vision, natural language processing, and speech processing. To reduce the complexity of computations within the multi-head self-attention mechanism in…

Despite the remarkable quality of LLM-based text-to-speech systems, their reliance on autoregressive Transformers leads to quadratic computational complexity, which severely limits practical applications. Linear-time alternatives, notably…

Selective state-space models (SSMs) like Mamba overcome some of the shortcomings of Transformers, such as quadratic computational complexity with sequence length and large inference-time memory requirements from the key-value cache.…

The Mamba-based model has demonstrated outstanding performance across tasks in computer vision, natural language processing, and speech processing. However, in the realm of speech processing, the Mamba-based model's performance varies…

Deep learning-based single-channel speaker separation has improved significantly in recent years largely due to the introduction of the transformer-based attention mechanism. However, these improvements come at the expense of intense…

Transformers have revolutionized deep learning across various tasks, including audio representation learning, due to their powerful modeling capabilities. However, they often suffer from quadratic complexity in both GPU memory usage and…

Video understanding requires the extraction of rich spatio-temporal representations, which transformer models achieve through self-attention. Unfortunately, self-attention poses a computational burden. In NLP, Mamba has surfaced as an…

Existing CNN-based speech separation models face local receptive field limitations and cannot effectively capture long time dependencies. Although LSTM and Transformer-based speech separation models can avoid this problem, their high…

The topic of speech separation involves separating mixed speech with multiple overlapping speakers into several streams, with each stream containing speech from only one speaker. Many highly effective models have emerged and proliferated…

Transformers are the current architecture of choice for NLP, but their attention layers do not scale well to long contexts. Recent works propose to replace attention with linear recurrent layers -- this is the case for state space models,…

Transformers are the cornerstone of modern large language models, but their quadratic computational complexity limits efficiency in long-sequence processing. Recent advancements in Mamba, a state space model (SSM) with linear complexity,…

While Mamba has demonstrated strong performance in language modeling, its potential as a speech self-supervised learning (SSL) model remains underexplored, with prior studies limited to isolated tasks. To address this, we explore…

In recent speech enhancement (SE) research, transformer and its variants have emerged as the predominant methodologies. However, the quadratic complexity of the self-attention mechanism imposes certain limitations on practical deployment.…

Transformer-based models have become increasingly popular and have impacted speech-processing research owing to their exceptional performance in sequence modeling. Recently, a promising model architecture, Mamba, has emerged as a potential…

Mamba is a newly proposed architecture which behaves like a recurrent neural network (RNN) with attention-like capabilities. These properties are promising for speaker diarization, as attention-based models have unsuitable memory…

Transformers have proven effective in language modeling but are limited by high computational and memory demands that grow quadratically with input sequence length. State space models (SSMs) offer a promising alternative by reducing…

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…

We propose TRAMBA, a hybrid transformer and Mamba architecture for acoustic and bone conduction speech enhancement, suitable for mobile and wearable platforms. Bone conduction speech enhancement has been impractical to adopt in mobile and…