English
Related papers

Related papers: Efficient Conformer with Prob-Sparse Attention Mec…

200 papers

The recently proposed Conformer model has become the de facto backbone model for various downstream speech tasks based on its hybrid attention-convolution architecture that captures both local and global features. However, through a series…

Audio and Speech Processing · Electrical Eng. & Systems 2022-10-18 Sehoon Kim , Amir Gholami , Albert Shaw , Nicholas Lee , Karttikeya Mangalam , Jitendra Malik , Michael W. Mahoney , Kurt Keutzer

We explore options to use Transformer networks in neural transducer for end-to-end speech recognition. Transformer networks use self-attention for sequence modeling and comes with advantages in parallel computation and capturing contexts.…

Audio and Speech Processing · Electrical Eng. & Systems 2019-10-30 Ching-Feng Yeh , Jay Mahadeokar , Kaustubh Kalgaonkar , Yongqiang Wang , Duc Le , Mahaveer Jain , Kjell Schubert , Christian Fuegen , Michael L. Seltzer

Recently, attention-based encoder-decoder (AED) models have shown high performance for end-to-end automatic speech recognition (ASR) across several tasks. Addressing overconfidence in such models, in this paper we introduce the concept of…

Audio and Speech Processing · Electrical Eng. & Systems 2021-12-16 Timo Lohrenz , Patrick Schwarz , Zhengyang Li , Tim Fingscheidt

With increasingly more powerful compute capabilities and resources in today's devices, traditionally compute-intensive automatic speech recognition (ASR) has been moving from the cloud to devices to better protect user privacy. However, it…

Machine Learning · Computer Science 2024-05-15 Mingbin Xu , Alex Jin , Sicheng Wang , Mu Su , Tim Ng , Henry Mason , Shiyi Han , Zhihong Lei , Yaqiao Deng , Zhen Huang , Mahesh Krishnamoorthy

Attention layers are an integral part of modern end-to-end automatic speech recognition systems, for instance as part of the Transformer or Conformer architecture. Attention is typically multi-headed, where each head has an independent set…

Computation and Language · Computer Science 2022-09-14 Kartik Audhkhasi , Yinghui Huang , Bhuvana Ramabhadran , Pedro J. Moreno

Transformer models have achieved state-of-the-art results in a wide range of NLP tasks including summarization. Training and inference using large transformer models can be computationally expensive. Previous work has focused on one…

Computation and Language · Computer Science 2021-09-10 Potsawee Manakul , Mark J. F. Gales

The use of Transformer represents a recent success in speech enhancement. However, as its core component, self-attention suffers from quadratic complexity, which is computationally prohibited for long speech recordings. Moreover, it allows…

Sound · Computer Science 2023-05-16 Qiquan Zhang , Hongxu Zhu , Qi Song , Xinyuan Qian , Zhaoheng Ni , Haizhou Li

End-to-end model, especially Recurrent Neural Network Transducer (RNN-T), has achieved great success in speech recognition. However, transducer requires a great memory footprint and computing time when processing a long decoding sequence.…

Sound · Computer Science 2023-07-18 Xiaohui Zhang , Mangui Liang , Zhengkun Tian , Jiangyan Yi , Jianhua Tao

End-to-end automatic speech recognition (ASR) models, including both attention-based models and the recurrent neural network transducer (RNN-T), have shown superior performance compared to conventional systems. However, previous studies…

Conformers have recently been proposed as a promising modelling approach for automatic speech recognition (ASR), outperforming recurrent neural network-based approaches and transformers. Nevertheless, in general, the performance of these…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-25 Carlos Carvalho , Alberto Abad

Continuous speech separation plays a vital role in complicated speech related tasks such as conversation transcription. The separation model extracts a single speaker signal from a mixed speech. In this paper, we use transformer and…

Audio and Speech Processing · Electrical Eng. & Systems 2020-10-23 Sanyuan Chen , Yu Wu , Zhuo Chen , Jian Wu , Jinyu Li , Takuya Yoshioka , Chengyi Wang , Shujie Liu , Ming Zhou

We present a Conformer-based end-to-end neural diarization (EEND) model that uses both acoustic input and features derived from an automatic speech recognition (ASR) model. Two categories of features are explored: features derived directly…

Computation and Language · Computer Science 2022-07-13 Aparna Khare , Eunjung Han , Yuguang Yang , Andreas Stolcke

Self-attention has recently been adopted for a wide range of sequence modeling problems. Despite its effectiveness, self-attention suffers from quadratic compute and memory requirements with respect to sequence length. Successful approaches…

Machine Learning · Computer Science 2020-10-27 Aurko Roy , Mohammad Saffar , Ashish Vaswani , David Grangier

In this paper, we present a so-called interlaced sparse self-attention approach to improve the efficiency of the \emph{self-attention} mechanism for semantic segmentation. The main idea is that we factorize the dense affinity matrix as the…

Computer Vision and Pattern Recognition · Computer Science 2019-07-31 Lang Huang , Yuhui Yuan , Jianyuan Guo , Chao Zhang , Xilin Chen , Jingdong Wang

End-to-end approaches for automatic speech recognition (ASR) benefit from directly modeling the probability of the word sequence given the input audio stream in a single neural network. However, compared to conventional ASR systems, these…

Audio and Speech Processing · Electrical Eng. & Systems 2020-02-19 Ankur Gandhe , Ariya Rastrow

Self-attention in transformer models is an incremental associative memory that maps key vectors to value vectors. One way to speed up self-attention is to employ GPU-compatible vector search algorithms based on standard partitioning methods…

Computation and Language · Computer Science 2025-06-04 Pierre-Emmanuel Mazaré , Gergely Szilvasy , Maria Lomeli , Francisco Massa , Naila Murray , Hervé Jégou , Matthijs Douze

Transformer-based architectures have become the prevailing backbone of large language models. However, the quadratic time and memory complexity of self-attention remains a fundamental obstacle to efficient long-context modeling. To address…

Computation and Language · Computer Science 2026-02-10 Yutao Sun , Zhenyu Li , Yike Zhang , Tengyu Pan , Bowen Dong , Yuyi Guo , Jianyong Wang

Transformer models have achieved remarkable results in a wide range of applications. However, their scalability is hampered by the quadratic time and memory complexity of the self-attention mechanism concerning the sequence length. This…

Machine Learning · Computer Science 2024-02-27 Yury Nahshan , Joseph Kampeas , Emir Haleva

Various forms of sparse attention have been explored to mitigate the quadratic computational and memory cost of the attention mechanism in transformers. We study sparse transformers not through a lens of efficiency but rather in terms of…

Machine Learning · Computer Science 2025-06-19 Parikshit Ram , Kenneth L. Clarkson , Tim Klinger , Shashanka Ubaru , Alexander G. Gray

This work introduces \emph{cross-attention conformer}, an attention-based architecture for context modeling in speech enhancement. Given that the context information can often be sequential, and of different length as the audio that is to…

Audio and Speech Processing · Electrical Eng. & Systems 2021-11-02 Arun Narayanan , Chung-Cheng Chiu , Tom O'Malley , Quan Wang , Yanzhang He