English
Related papers

Related papers: GPU-Accelerated WFST Beam Search Decoder for CTC-b…

200 papers

In this paper, we review various end-to-end automatic speech recognition algorithms and their optimization techniques for on-device applications. Conventional speech recognition systems comprise a large number of discrete components such as…

Machine Learning · Computer Science 2021-08-30 Chanwoo Kim , Dhananjaya Gowda , Dongsoo Lee , Jiyeon Kim , Ankur Kumar , Sungsoo Kim , Abhinav Garg , Changwoo Han

This study presents a reconstruction of the Gaussian Beam Tracing solution using CUDA, with a particular focus on the utilisation of GPU acceleration as a means of overcoming the performance limitations of traditional CPU algorithms in…

Performance · Computer Science 2025-01-24 Zhang Sheng , Lishu Duan , Hanbo Jiang

Finite-state transducers (FSTs) are frequently used in speech recognition. Transducer composition is an essential operation for combining different sources of information at different granularities. However, composition is also one of the…

Computation and Language · Computer Science 2021-10-07 Shubho Sengupta , Vineel Pratap , Awni Hannun

The rapidly-changing deep learning landscape presents a unique opportunity for building inference accelerators optimized for specific datacenter-scale workloads. We propose Full-stack Accelerator Search Technique (FAST), a hardware…

Machine Learning · Computer Science 2022-02-02 Dan Zhang , Safeen Huda , Ebrahim Songhori , Kartik Prabhu , Quoc Le , Anna Goldie , Azalia Mirhoseini

We design an online end-to-end speech recognition system based on Time-Depth Separable (TDS) convolutions and Connectionist Temporal Classification (CTC). We improve the core TDS architecture in order to limit the future context and hence…

The growing demand for high-quality point cloud transmission over wireless networks presents significant challenges, primarily due to the large data sizes and the need for efficient encoding techniques. In response to these challenges, we…

Multimedia · Computer Science 2024-08-12 Cixiao Zhang , Mufan Liu , Wenjie Huang , Yin Xu , Yiling Xu , Dazhi He

In this paper, we design a new class of high-efficiency deep joint source-channel coding methods to achieve end-to-end video transmission over wireless channels. The proposed methods exploit nonlinear transform and conditional coding…

Computer Vision and Pattern Recognition · Computer Science 2022-11-03 Sixian Wang , Jincheng Dai , Zijian Liang , Kai Niu , Zhongwei Si , Chao Dong , Xiaoqi Qin , Ping Zhang

Multi-channel inputs offer several advantages over single-channel, to improve the robustness of on-device speech recognition systems. Recent work on multi-channel transformer, has proposed a way to incorporate such inputs into end-to-end…

Audio and Speech Processing · Electrical Eng. & Systems 2021-08-31 Feng-Ju Chang , Martin Radfar , Athanasios Mouchtaris , Maurizio Omologo

Due to the flexible representation of arbitrary-shaped scene text and simple pipeline, bottom-up segmentation-based methods begin to be mainstream in real-time scene text detection. Despite great progress, these methods show deficiencies in…

Computer Vision and Pattern Recognition · Computer Science 2023-08-15 Xugong Qin , Pengyuan Lyu , Chengquan Zhang , Yu Zhou , Kun Yao , Peng Zhang , Hailun Lin , Weiping Wang

Connectionist Temporal Classification (CTC) and attention mechanism are two main approaches used in recent scene text recognition works. Compared with attention-based methods, CTC decoder has a much shorter inference time, yet a lower…

Computer Vision and Pattern Recognition · Computer Science 2020-02-05 Wenyang Hu , Xiaocong Cai , Jun Hou , Shuai Yi , Zhiping Lin

Achieving high accuracy with low latency has always been a challenge in streaming end-to-end automatic speech recognition (ASR) systems. By attending to more future contexts, a streaming ASR model achieves higher accuracy but results in…

Sound · Computer Science 2023-09-12 Huaibo Zhao , Yosuke Higuchi , Yusuke Kida , Tetsuji Ogawa , Tetsunori Kobayashi

Connectionist temporal classification (CTC) is a popular sequence prediction approach for automatic speech recognition that is typically used with models based on recurrent neural networks (RNNs). We explore whether deep convolutional…

Computation and Language · Computer Science 2018-02-16 Kalpesh Krishna , Liang Lu , Kevin Gimpel , Karen Livescu

This paper presents the design and evaluation of a GPU-accelerated inference pipeline for transformer models using NVIDIA TensorRT with mixed-precision optimization. We evaluate BERT-base (110M parameters) and GPT-2 (124M parameters) across…

Machine Learning · Computer Science 2026-03-31 Soutrik Mukherjee , Sangwhan Cha

A streaming style inference of encoder-decoder automatic speech recognition (ASR) system is important for reducing latency, which is essential for interactive use cases. To this end, we propose a novel blockwise synchronous decoding…

Audio and Speech Processing · Electrical Eng. & Systems 2022-01-26 Emiru Tsunoo , Chaitanya Narisetty , Michael Hentschel , Yosuke Kashiwagi , Shinji Watanabe

The recent emergence of joint CTC-Attention model shows significant improvement in automatic speech recognition (ASR). The improvement largely lies in the modeling of linguistic information by decoder. The decoder joint-optimized with an…

Computation and Language · Computer Science 2022-10-27 Xulong Zhang , Jianzong Wang , Ning Cheng , Mengyuan Zhao , Zhiyong Zhang , Jing Xiao

We introduce a framework for automatic differentiation with weighted finite-state transducers (WFSTs) allowing them to be used dynamically at training time. Through the separation of graphs from operations on graphs, this framework enables…

Machine Learning · Computer Science 2020-10-05 Awni Hannun , Vineel Pratap , Jacob Kahn , Wei-Ning Hsu

An inferior performance of the streaming automatic speech recognition models versus non-streaming model is frequently seen due to the absence of future context. In order to improve the performance of the streaming model and reduce the…

Sound · Computer Science 2022-03-30 Jingyu Sun , Guiping Zhong , Dinghao Zhou , Baoxiang Li

Current continuous sign language recognition (CSLR) methods struggle with handling diverse samples. Although dynamic convolutions are ideal for this task, they mainly focus on spatial modeling and fail to capture the temporal dynamics and…

Computer Vision and Pattern Recognition · Computer Science 2025-07-08 Sheng Liu , Yiheng Yu , Yuan Feng , Min Xu , Zhelun Jin , Yining Jiang , Tiantian Yuan

We introduce asynchronous dynamic decoder, which adopts an efficient A* algorithm to incorporate big language models in the one-pass decoding for large vocabulary continuous speech recognition. Unlike standard one-pass decoding with…

Sound · Computer Science 2021-03-17 Hang Lv , Zhehuai Chen , Hainan Xu , Daniel Povey , Lei Xie , Sanjeev Khudanpur

The recent introduction of powerful embedded graphics processing units (GPUs) has allowed for unforeseen improvements in real-time computer vision applications. It has enabled algorithms to run onboard, well above the standard video rates,…

Computer Vision and Pattern Recognition · Computer Science 2020-08-04 Balazs Nagy , Philipp Foehn , Davide Scaramuzza