Open AccessProceedings Article
Framewise phoneme classification with bidirectional LSTM and other neural network architectures
Alex Graves,Jürgen Schmidhuber +1 more
- Vol. 18, pp 602-610
Reads0
Chats0
TLDR
In this article, a modified, full gradient version of the LSTM learning algorithm was used for framewise phoneme classification, using the TIMIT database, and the results support the view that contextual information is crucial to speech processing, and suggest that bidirectional networks outperform unidirectional ones.Abstract:
In this paper, we present bidirectional Long Short Term Memory (LSTM) networks, and a modified, full gradient version of the LSTM learning algorithm. We evaluate Bidirectional LSTM (BLSTM) and several other network architectures on the benchmark task of framewise phoneme classification, using the TIMIT database. Our main findings are that bidirectional networks outperform unidirectional ones, and Long Short Term Memory (LSTM) is much faster and also more accurate than both standard Recurrent Neural Nets (RNNs) and time-windowed Multilayer Perceptrons (MLPs). Our results support the view that contextual information is crucial to speech processing, and suggest that BLSTM is an effective architecture with which to exploit it'.read more
Citations
More filters
Proceedings ArticleDOI
Document Image Binarization using LSTM: A Sequence Learning Approach
Muhammad Zeshan Afzal,Joan Pastor-Pellicer,Faisal Shafait,Thomas M. Breuel,Andreas Dengel,Marcus Liwicki +5 more
TL;DR: The proposed approach significantly outperforms standard binarization approaches both for F-Measure and OCR accuracy with the availability of enough training samples.
Proceedings ArticleDOI
Large-Scale Item Categorization in e-Commerce Using Multiple Recurrent Neural Networks
TL;DR: Experimental results show the method improves the categorization accuracy compared to the model using single RNN as well as a standard classification model using unigram-based bag-of-words, and how much the model parameters and the used attributes influence categorization performances is investigated.
Posted Content
Temporal Convolutional Neural Networks for Diagnosis from Lab Tests
Narges Razavian,David Sontag +1 more
TL;DR: This work introduces a multi-resolution convolutional neural network for early detection of multiple diseases from irregularly measured sparse lab values and shows that the temporal signatures learned via convolution are significantly more predictive than baselines commonly used for early disease diagnosis.
Proceedings ArticleDOI
Hardware architecture of Bidirectional Long Short-Term Memory Neural Network for Optical Character Recognition
TL;DR: It is shown that computationally intensive visual recognition task benefits from being migrated to the dedicated hardware accelerator and outperforms high-performance CPU in terms of runtime, while consuming less energy than low power systems with negligible loss of recognition accuracy.
Posted Content
Gated Word-Character Recurrent Language Model
Yasumasa Miyamoto,Kyunghyun Cho +1 more
TL;DR: This paper introduced a gate that adaptively finds the optimal mixture of the character-level and word-level inputs to create the final vector representation of a word by combining two distinct representations of the word.
References
More filters
Journal ArticleDOI
Long short-term memory
TL;DR: A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.
Book
Neural networks for pattern recognition
TL;DR: This is the first comprehensive treatment of feed-forward neural networks from the perspective of statistical pattern recognition, and is designed as a text, with over 100 exercises, to benefit anyone involved in the fields of neural computation and pattern recognition.
Journal ArticleDOI
Bidirectional recurrent neural networks
Mike Schuster,Kuldip K. Paliwal +1 more
TL;DR: It is shown how the proposed bidirectional structure can be easily modified to allow efficient estimation of the conditional posterior probability of complete symbol sequences without making any explicit assumption about the shape of the distribution.
Darpa Timit Acoustic-Phonetic Continuous Speech Corpus CD-ROM {TIMIT} | NIST
John S. Garofolo,Lori Lamel,W M. Fisher,Jonathan G. Fiscus,David S. Pallett,Nancy L. Dahlgren +5 more
Gradient Flow in Recurrent Nets: the Difficulty of Learning Long-Term Dependencies
Sepp Hochreiter,Yoshua Bengio +1 more
TL;DR: D3EGF(FIH)J KMLONPEGQSRPETN UCV.