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
Posted Content
Failures of Gradient-Based Deep Learning
TL;DR: This work describes four types of simple problems, for which the gradient-based algorithms commonly used in deep learning either fail or suffer from significant difficulties.
Journal ArticleDOI
Exploiting deep neural networks for detection-based speech recognition
TL;DR: It is shown that DNNs can be used to boost the classification accuracy of basic speech units, such as phonetic attributes (phonological features) and phonemes, and results in improved word recognition accuracy, which is better than previously reported word lattice rescoring results.
Proceedings ArticleDOI
ECG-based biometrics using recurrent neural networks
Ronald Salloum,C.-C. Jay Kuo +1 more
TL;DR: The use of recurrent neural networks (RNNs) to develop an effective solution to two problems in electrocardiogram (ECG)-based biometrics: identification/classification and authentication was proposed.
Proceedings ArticleDOI
Deep Learning approach for sentiment analysis of short texts
Abdalraouf Hassan,Ausif Mahmood +1 more
TL;DR: Empirical results show that ConvLstm achieved comparable performances with less parameters on sentiment analysis tasks, and exploit LSTM as a substitute of pooling layer in CNN to reduce the loss of detailed local information and capture long term dependencies in sequence of sentences.
Proceedings ArticleDOI
Context-sensitive learning for enhanced audiovisual emotion classification (Extended abstract)
Angeliki Metallinou,Athanasios Katsamanis,Martin Wöllmer,Florian Eyben,Björn Schuller,Shrikanth S. Narayanan +5 more
TL;DR: The experimental results indicate that incorporating long-term temporal context is beneficial for emotion recognition systems that encounter a variety of emotional manifestations and context-sensitive approaches outperform those without context for classification tasks such as discrimination between valence levels or between clusters in the valence-activation space.
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.