English
Related papers

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

200 papers

CTC-based ASR systems face computational and memory bottlenecks in resource-limited environments. Traditional CTC decoders, requiring up to 90% of processing time in systems (e.g., wav2vec2-large on L4 GPUs), face inefficiencies due to…

Machine Learning · Computer Science 2025-10-13 Atul Shree , Harshith Jupuru

There is often a trade-off between performance and latency in streaming automatic speech recognition (ASR). Traditional methods such as look-ahead and chunk-based methods, usually require information from future frames to advance…

Audio and Speech Processing · Electrical Eng. & Systems 2022-07-07 Zehan Li , Haoran Miao , Keqi Deng , Gaofeng Cheng , Sanli Tian , Ta Li , Yonghong Yan

In this paper, we propose an efficient and accurate streaming speech recognition model based on the FastConformer architecture. We adapted the FastConformer architecture for streaming applications through: (1) constraining both the…

Computation and Language · Computer Science 2024-05-06 Vahid Noroozi , Somshubra Majumdar , Ankur Kumar , Jagadeesh Balam , Boris Ginsburg

Automatic Speech Recognition (ASR) plays a crucial role in voice-based applications. For applications requiring real-time feedback like Voice Search, streaming capability becomes vital. While LSTM/RNN and CTC based ASR systems are commonly…

Sound · Computer Science 2023-05-31 Abhinav Goyal , Nikesh Garera

We present a state-of-the-art end-to-end Automatic Speech Recognition (ASR) model. We learn to listen and write characters with a joint Connectionist Temporal Classification (CTC) and attention-based encoder-decoder network. The encoder is…

Computation and Language · Computer Science 2017-06-12 Takaaki Hori , Shinji Watanabe , Yu Zhang , William Chan

Streaming ASR with strict latency constraints is required in many speech recognition applications. In order to achieve the required latency, streaming ASR models sacrifice accuracy compared to non-streaming ASR models due to lack of future…

Computation and Language · Computer Science 2022-03-30 Jay Mahadeokar , Yangyang Shi , Ke Li , Duc Le , Jiedan Zhu , Vikas Chandra , Ozlem Kalinli , Michael L Seltzer

This paper introduces a fast-slow encoder based transducer with streaming deliberation for end-to-end automatic speech recognition. We aim to improve the recognition accuracy of the fast-slow encoder based transducer while keeping its…

Audio and Speech Processing · Electrical Eng. & Systems 2022-12-16 Ke Li , Jay Mahadeokar , Jinxi Guo , Yangyang Shi , Gil Keren , Ozlem Kalinli , Michael L. Seltzer , Duc Le

The Recurrent Neural Network-Transducer (RNN-T) is widely adopted in end-to-end (E2E) automatic speech recognition (ASR) tasks but depends heavily on large-scale, high-quality annotated data, which are often costly and difficult to obtain.…

Computation and Language · Computer Science 2025-11-07 Dongji Gao , Chenda Liao , Changliang Liu , Matthew Wiesner , Leibny Paola Garcia , Daniel Povey , Sanjeev Khudanpur , Jian Wu

Although Transformers have gained success in several speech processing tasks like spoken language understanding (SLU) and speech translation (ST), achieving online processing while keeping competitive performance is still essential for…

Computation and Language · Computer Science 2022-04-20 Keqi Deng , Shinji Watanabe , Jiatong Shi , Siddhant Arora

This paper introduces a novel training framework called Focused Discriminative Training (FDT) to further improve streaming word-piece end-to-end (E2E) automatic speech recognition (ASR) models trained using either CTC or an interpolation of…

Machine Learning · Computer Science 2024-08-26 Adnan Haider , Xingyu Na , Erik McDermott , Tim Ng , Zhen Huang , Xiaodan Zhuang

For real-world deployment of automatic speech recognition (ASR), the system is desired to be capable of fast inference while relieving the requirement of computational resources. The recently proposed end-to-end ASR system based on…

Audio and Speech Processing · Electrical Eng. & Systems 2021-02-17 Yosuke Higuchi , Hirofumi Inaguma , Shinji Watanabe , Tetsuji Ogawa , Tetsunori Kobayashi

The Conformer model is an excellent architecture for speech recognition modeling that effectively utilizes the hybrid losses of connectionist temporal classification (CTC) and attention to train model parameters. To improve the decoding…

Sound · Computer Science 2022-04-11 Nick J. C. Wang , Zongfeng Quan , Shaojun Wang , Jing Xiao

In the present paper, an attempt is made to combine Mask-CTC and the triggered attention mechanism to construct a streaming end-to-end automatic speech recognition (ASR) system that provides high performance with low latency. The triggered…

Sound · Computer Science 2021-10-22 Huaibo Zhao , Yosuke Higuchi , Tetsuji Ogawa , Tetsunori Kobayashi

Automatic speech recognition (ASR) tasks are resolved by end-to-end deep learning models, which benefits us by less preparation of raw data, and easier transformation between languages. We propose a novel end-to-end deep learning model…

Audio and Speech Processing · Electrical Eng. & Systems 2018-10-31 Xinpei Zhou , Jiwei Li , Xi Zhou

The RNN-Transducers and improved attention-based encoder-decoder models are widely applied to streaming speech recognition. Compared with these two end-to-end models, the CTC model is more efficient in training and inference. However, it…

Audio and Speech Processing · Electrical Eng. & Systems 2021-04-06 Zhengkun Tian , Jiangyan Yi , Ye Bai , Jianhua Tao , Shuai Zhang , Zhengqi Wen

This paper presents a novel algorithm for building an automatic speech recognition (ASR) model with imperfect training data. Imperfectly transcribed speech is a prevalent issue in human-annotated speech corpora, which degrades the…

Computation and Language · Computer Science 2023-06-05 Dongji Gao , Matthew Wiesner , Hainan Xu , Leibny Paola Garcia , Daniel Povey , Sanjeev Khudanpur

We present a GPU-accelerated transient detection pipeline developed for time-domain surveys with the Dark Energy Camera (DECam). It enables real-time-capable image processing, incorporating science-driven candidate filtering to support…

Instrumentation and Methods for Astrophysics · Physics 2026-03-10 Lei Hu , Tomás Cabrera , Antonella Palmese , Lifan Wang , Igor Andreoni , Xander J. Hall , Xingzhuo Chen , Jiawen Yang , Frank Valdes , Brendan O'Connor , Yuhan Chen

GPU decoding significantly accelerates the output of ASR predictions. While GPUs are already being used for online ASR decoding, post-processing and rescoring on GPUs have not been properly investigated yet. Rescoring with available…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-29 Iuliia Nigmatulina , Srikanth Madikeri , Esaú Villatoro-Tello , Petr Motliček , Juan Zuluaga-Gomez , Karthik Pandia , Aravind Ganapathiraju

Connectionist Temporal Classification (CTC) suffers from the latency problem when applied to streaming models. We argue that in CTC lattice, the alignments that can access more future context are preferred during training, thereby leading…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-22 Zengwei Yao , Wei Kang , Fangjun Kuang , Liyong Guo , Xiaoyu Yang , Yifan Yang , Long Lin , Daniel Povey

We propose an accurate and efficient scene text detection framework, termed FAST (i.e., faster arbitrarily-shaped text detector). Different from recent advanced text detectors that used complicated post-processing and hand-crafted network…

Computer Vision and Pattern Recognition · Computer Science 2023-01-12 Zhe Chen , Jiahao Wang , Wenhai Wang , Guo Chen , Enze Xie , Ping Luo , Tong Lu