arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.02832cs.CLcs.AIcs.SDeess.AS
收藏

Samba-ASR:利用结构化状态空间模型实现最先进语音识别

Samba-ASR: State-Of-The-Art Speech Recognition Leveraging Structured State-Space Models

SandLogic Technologies Pvt Ltd(SandLogic科技私人有限公司)

Syed Abdul Gaffar Shakhadri, Kruthika KR, Kartik Basavaraj Angadi

AI总结:

提出以 Mamba SSM 同时作为编码器和解码器的 Samba ASR,在公开基准上以更高效率和更低 WER 超越开源 transformer ASR。

摘要:

我们提出 Samba ASR,这是首个同时采用新型 Mamba 架构作为编码器和解码器的最先进自动语音识别(ASR)模型,构建于状态空间模型(SSMs)基础之上。不同于基于 transformer、依赖自注意力机制捕捉依赖关系的 ASR 模型,Samba ASR 使用高效的状态空间动态,对局部和全局时间依赖进行有效建模,取得显著性能提升。通过解决 transformer 的局限,例如随输入长度呈二次扩展以及难以处理长程依赖,Samba ASR 实现了更优的准确性和效率。实验结果表明,Samba ASR 在多个标准基准上超越现有开源的基于 transformer 的 ASR 模型,确立其为 ASR 领域新的最先进水平。在基准数据集上的广泛评估显示,词错误率(WER)显著改善,即使在低资源场景下也具有有竞争力的性能。此外,Mamba 架构固有的计算效率和参数优化,使 Samba ASR 成为适用于多种 ASR 任务的可扩展且稳健的解决方案。我们的贡献包括开发用于自动语音识别(ASR)的新型 Samba ASR 架构,并证明结构化状态空间模型(SSMs)在语音序列处理方面优于基于 transformer 的模型。我们在公开基准上提供全面评估,展示最先进(SOTA)性能,并对计算效率、噪声稳健性和序列泛化进行深入分析。本工作凸显 Mamba SSM 作为无 transformer 替代方案,用于高效、准确 ASR 的可行性。通过利用状态空间建模的进展,Samba ASR 重新定义 ASR 性能标准,并为该领域未来研究设立新的基准。

英文摘要:

We propose Samba ASR,the first state of the art Automatic Speech Recognition(ASR)model leveraging the novel Mamba architecture as both encoder and decoder,built on the foundation of state space models(SSMs).Unlike transformerbased ASR models,which rely on self-attention mechanisms to capture dependencies,Samba ASR effectively models both local and global temporal dependencies using efficient statespace dynamics,achieving remarkable performance gains.By addressing the limitations of transformers,such as quadratic scaling with input length and difficulty in handling longrange dependencies,Samba ASR achieves superior accuracy and efficiency.Experimental results demonstrate that Samba ASR surpasses existing opensource transformerbased ASR models across various standard benchmarks,establishing it as the new state of theart in ASR.Extensive evaluations on the benchmark dataset show significant improvements in Word Error Rate(WER),with competitive performance even in lowresource scenarios.Furthermore,the inherent computational efficiency and parameter optimization of the Mamba architecture make Samba ASR a scalable and robust solution for diverse ASR tasks.Our contributions include the development of a new Samba ASR architecture for automatic speech recognition(ASR),demonstrating the superiority of structured statespace models(SSMs)over transformer based models for speech sequence processing.We provide a comprehensive evaluation on public benchmarks,showcasing stateoftheart(SOTA)performance,and present an indepth analysis of computational efficiency,robustness to noise,and sequence generalization.This work highlights the viability of Mamba SSMs as a transformerfree alternative for efficient and accurate ASR.By leveraging the advancements of statespace modeling,Samba ASR redefines ASR performance standards and sets a new benchmark for future research in this field.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑