Results 41 to 50 of about 47,965 (148)

End-to-End Speech Recognition Sequence Training With Reinforcement Learning

IEEE Access, 2019
End-to-end sequence modeling has become a popular choice for automatic speech recognition (ASR) because of the simpler pipeline compared to the conventional system and its excellent performance.
Andros Tjandra, Sakriani Sakti, Satoshi Nakamura   +2 more
doaj   +1 more source

Ubranch Conformer: Integrating Up-Down Sampling and Branch Attention for Speech Recognition

IEEE Access
Conformer has become one of the most popular models in the field of automatic speech recognition, achieving superior speech recognition performance by integrating a convolutional module into Transformer. However, existing Conformer models face challenges
Yang Yang, Feng Yao, Mingke Liao, Yucheng Huang   +3 more
doaj   +1 more source

An Improvement to Conformer-Based Model for High-Accuracy Speech Feature Extraction and Learning

Entropy, 2022
Owing to the loss of effective information and incomplete feature extraction caused by the convolution and pooling operations in a convolution subsampling network, the accuracy and speed of current speech processing architectures based on the conformer ...
Mengzhuo Liu, Yangjie Wei
doaj   +1 more source

Multi-Stream End-to-End Speech Recognition

IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2020
submitted to IEEE TASLP (In review).
Ruizhi Li, Xiaofei Wang 0007, Sri Harish Mallidi, Shinji Watanabe 0001, Takaaki Hori, Hynek Hermansky   +5 more
openaire   +2 more sources

End-to-End Training of a Large Vocabulary End-to-End Speech Recognition System [PDF]

2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 2019
In this paper, we present an end-to-end training framework for building state-of-the-art end-to-end speech recognition systems. Our training system utilizes a cluster of Central Processing Units(CPUs) and Graphics Processing Units (GPUs). The entire data reading, large scale data augmentation, neural network parameter updates are all performed "on-the ...
Chanwoo Kim 0001, Minkyoo Shin, Shatrughan Singh, Larry Heck, Dhananjaya Gowda, Sungsoo Kim, Kwangyoun Kim, Mehul Kumar, Jiyeon Kim, Kyungmin Lee, Changwoo Han, Abhinav Garg, Eunhyang Kim   +12 more
openaire   +2 more sources

End-To-End Multi-Speaker Speech Recognition With Transformer [PDF]

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020
Recently, fully recurrent neural network (RNN) based end-to-end models have been proven to be effective for multi-speaker speech recognition in both the single-channel and multi-channel scenarios. In this work, we explore the use of Transformer models for these tasks by focusing on two aspects.
Xuankai Chang, Wangyou Zhang, Yanmin Qian, Jonathan Le Roux, Shinji Watanabe 0001   +4 more
openaire   +2 more sources

JSUM: A Multitask Learning Speech Recognition Model for Jointly Supervised and Unsupervised Learning

Applied Sciences, 2023
In recent years, the end-to-end speech recognition model has emerged as a popular alternative to the traditional Deep Neural Network—Hidden Markov Model (DNN-HMM).
Nurmemet Yolwas, Weijing Meng
doaj   +1 more source

Deep Context: End-to-end Contextual Speech Recognition [PDF]

2018 IEEE Spoken Language Technology Workshop (SLT), 2018
In automatic speech recognition (ASR) what a user says depends on the particular context she is in. Typically, this context is represented as a set of word n-grams. In this work, we present a novel, all-neural, end-to-end (E2E) ASR sys- tem that utilizes such context.
Golan Pundak, Tara N. Sainath, Rohit Prabhavalkar, Anjuli Kannan, Ding Zhao   +4 more
openaire   +2 more sources

Streaming End-to-end Speech Recognition for Mobile Devices [PDF]

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019
End-to-end (E2E) models, which directly predict output character sequences given input speech, are good candidates for on-device speech recognition. E2E models, however, present numerous challenges: In order to be truly useful, such models must decode speech utterances in a streaming fashion, in real time; they must be robust to the long tail of use ...
Yanzhang He, Tara N. Sainath, Rohit Prabhavalkar, Ian McGraw, Raziel Alvarez, Ding Zhao, David Rybach, Anjuli Kannan, Yonghui Wu, Ruoming Pang, Qiao Liang 0001, Deepti Bhatia, Yuan Shangguan, Bo Li 0028, Golan Pundak, Khe Chai Sim, Tom Bagby, Shuo-Yiin Chang, Kanishka Rao, Alexander Gruenstein   +19 more
openaire   +2 more sources

Segment boundary detection directed attention for online end-to-end speech recognition

EURASIP Journal on Audio, Speech, and Music Processing, 2020
Attention-based encoder-decoder models have recently shown competitive performance for automatic speech recognition (ASR) compared to conventional ASR systems.
Junfeng Hou, Wu Guo, Yan Song, Li-Rong Dai   +3 more
doaj   +1 more source