paper-with-me

Papers

Speech-Mamba: Long-Context Speech Recognition with Selective State Spaces Models

2024-09-27 · Xiaoxue Gao, Nancy F. Chen

Current automatic speech recognition systems struggle with modeling long speech sequences due to high quadratic complexity of Transformer-based models. Selective state space models such as Mamba has performed well on long-sequence modeling in natural language processing and computer vision tasks. However, research endeavors in speech technology tasks has been under-explored. We propose Speech-Mamba, which incorporates selective state space modeling in Transformer neural architectures. Long sequence representations with selective state space models in Speech-Mamba is complemented with lower-level representations from Transformer-based modeling. Speech-mamba achieves better capacity to model long-range dependencies, as it scales near-linearly with sequence length.

📄 PDF Abstract BibTeX arXiv:2409.18654

Code (0)

등록된 구현이 없습니다.

Tasks

Automatic Speech RecognitionMambaspeech-recognitionSpeech RecognitionState Space Models

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Adam 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Speech Slytherin: Examining the Performance and Efficiency of Mamba for Speech Separation, Recognition, and Synthesis

2024-07-13 · Xilin Jiang, Yinghao Aaron Li, Adrian Nicolas Florea, Cong Han 외

It is too early to conclude that Mamba is a better alternative to transformers for speech before comparing Mamba with transformers in terms of both performance and efficiency in multiple speech-related tasks. To reach th…

Mambaspeech-recognitionSpeech RecognitionSpeech Separation+1

Rethinking Mamba in Speech Processing by Self-Supervised Models

2024-09-11 · Xiangyu Zhang, Jianbo Ma, Mostafa Shahin, Beena Ahmed 외

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 perf…

MambaSpeech Enhancementspeech-recognitionSpeech Recognition

MLMA: Towards Multilingual ASR With Mamba-based Architectures

2025-10-21 · Mohamed Nabih Ali, Daniele Falavigna, Alessio Brutti arxiv

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 b…

Speech Recognition

SPMamba: State-space model is all you need in speech separation

2024-04-02 · Kai Li, Guo Chen, Runxuan Yang, Xiaolin Hu

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 proble…

AllMambaSpeech Separation

Mamba in Speech: Towards an Alternative to Self-Attention

2024-05-21 · Xiangyu Zhang, Qiquan Zhang, Hexin Liu, Tianyi Xiao 외

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-atten…

MambaSpeech Enhancementspeech-recognitionSpeech Recognition+1