NDLI: Using Highway Connections to Enable Deep Small-footprint LSTM-RNNs for Speech Recognition

Content Provider	IET Digital Library
Author	G, Gaofeng C H E N I, Xin L N, Yonghong Y A
Abstract	Long short-term memory RNNs (LSTMRNNs) have shown great success in the Automatic speech recognition (ASR) field and have become the state-ofthe- art acoustic model for time-sequence modeling tasks. However, it is still difficult to train deep LSTM-RNNs while keeping the parameter number small. We use the highway connections between memory cells in adjacent layers to train a small-footprint highway LSTM-RNNs (HLSTM-RNNs), which are deeper and thinner compared to conventional LSTM-RNNs. The experiments on the Switchboard (SWBD) indicate that we can train thinner and deeper HLSTM-RNNs with a smaller parameter number than the conventional 3-layer LSTM-RNNs and a lower Word error rate (WER) than the conventional one. Compared with the counterparts of small-footprint LSTMRNNs, the small-footprint HLSTM-RNNs show greater reduction in WER.
Starting Page	107
Ending Page	112
Page Count	6
ISSN	10224653
Volume Number	28
e-ISSN	20755597
Issue Number	Issue 1, Jan (2019)
Alternate Webpage(s)	https://digital-library.theiet.org/content/journals/cje/28/1
Alternate Webpage(s)	https://digital-library.theiet.org/content/journals/10.1049/cje.2018.11.008
Journal	Chinese Journal of Electronics
Publisher Date	2019-01-01
Access Restriction	Open
Rights Holder	© Chinese Institute of Electronics
Subject Keyword	3-layer LSTM-RNNs Acoustic Model Automatic Speech Recognition Field Deep LSTM-RNNs Deep Small-footprint LSTM-RNNs Highway Connections Knowledge Engineering Technique Learning in AI Memory Cell Neural Computing Technique Recurrent Neural Nets Short-term Memory RNNs Small-footprint Highway LSTM-RNNs Small-footprint HLSTM-RNNs Speech Processing Technique Speech Recognition Speech Recognition And Synthesis Switchboard Time-sequence Modeling Task
Content Type	Text
Resource Type	Article
Subject	Applied Mathematics Electrical and Electronic Engineering

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Semi-supervised long short-term memory for human action recognition

LSTM network: a deep learning approach for short-term traffic forecast

Hidden variability subspace learning for adaptation of deep neural networks

Towards traffic matrix prediction with LSTM recurrent neural networks

Intra-pulse modulation radar signal recognition based on CLDN network

Human trajectory prediction for automatic guided vehicle with recurrent neural network

Pedestrian trajectory prediction via the Social-Grid LSTM model

Combining Long Short-Term Memory and Dynamic Bayesian Networks for Incremental Emotion-Sensitive Artificial Listening

Small-footprint Deep Neural Networks with Highway Connections for Speech Recognition

Using Highway Connections to Enable Deep Small-footprint LSTM-RNNs for Speech Recognition

Similar Documents

Semi-supervised long short-term memory for human action recognition

LSTM network: a deep learning approach for short-term traffic forecast

Hidden variability subspace learning for adaptation of deep neural networks

Towards traffic matrix prediction with LSTM recurrent neural networks

Intra-pulse modulation radar signal recognition based on CLDN network

Human trajectory prediction for automatic guided vehicle with recurrent neural network

Pedestrian trajectory prediction via the Social-Grid LSTM model

Combining Long Short-Term Memory and Dynamic Bayesian Networks for Incremental Emotion-Sensitive Artificial Listening

Small-footprint Deep Neural Networks with Highway Connections for Speech Recognition

Using Highway Connections to Enable Deep Small-footprint LSTM-RNNs for Speech Recognition