Proceedings ArticleDOI
Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks
Alex Graves,Santiago Fernández,Faustino Gomez,Jürgen Schmidhuber +3 more
- pp 369-376
TLDR
This paper presents a novel method for training RNNs to label unsegmented sequences directly, thereby solving both problems of sequence learning and post-processing.Abstract:
Many real-world sequence learning tasks require the prediction of sequences of labels from noisy, unsegmented input data. In speech recognition, for example, an acoustic signal is transcribed into words or sub-word units. Recurrent neural networks (RNNs) are powerful sequence learners that would seem well suited to such tasks. However, because they require pre-segmented training data, and post-processing to transform their outputs into label sequences, their applicability has so far been limited. This paper presents a novel method for training RNNs to label unsegmented sequences directly, thereby solving both problems. An experiment on the TIMIT speech corpus demonstrates its advantages over both a baseline HMM and a hybrid HMM-RNN.read more
Citations
More filters
Journal ArticleDOI
Ligature based Urdu Nastaleeq sentence recognition using gated bidirectional long short term memory
TL;DR: This paper proposes a novel gated BLSTM (GBLSTM) model for recognition of printed Urdu Nastaleeq text based on ligature information that incorporates raw pixel values as features instead of human crafted features, because of the latter being more error prone.
Journal ArticleDOI
Long Short-Term Memory Projection Recurrent Neural Network Architectures for Piano’s Continuous Note Recognition
TL;DR: This paper combines LSTM and LSTMP with Connectionist Temporal Classification (CTC) to study piano’s continuous note recognition for robotics and shows that the single layer L STMP proves performing much better than the single layers L STM in both time and the recognition rate.
Proceedings ArticleDOI
DNNGuard: An Elastic Heterogeneous DNN Accelerator Architecture against Adversarial Attacks
TL;DR: DNNGuard is proposed, an elastic heterogeneous DNN accelerator architecture that can efficiently orchestrate the simultaneous execution of original (target) DNN networks and the detect algorithm or network that detects adversary sample attacks, and is implemented based on RISC-V and NVDLA.
Proceedings ArticleDOI
Fully Convolutional Networks for Handwriting Recognition
TL;DR: In this article, a fully convolutional handwriting model takes in a handwriting sample of unknown length and outputs an arbitrary stream of symbols, which is shown to be quite competitive with state-of-the-art dictionary based methods on the popular IAM and RIMES datasets.
Posted Content
Streaming Chunk-Aware Multihead Attention for Online End-to-End Speech Recognition
TL;DR: Experimental results on the open 170-hour AISHELL-1 and an industrial-level 20000-hour Mandarin speech recognition tasks show that the proposed approach can significantly outperform the MoChA-based baseline system under comparable setup.
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.
Journal ArticleDOI
A tutorial on hidden Markov models and selected applications in speech recognition
TL;DR: In this paper, the authors provide an overview of the basic theory of hidden Markov models (HMMs) as originated by L.E. Baum and T. Petrie (1966) and give practical details on methods of implementation of the theory along with a description of selected applications of HMMs to distinct problems in speech recognition.
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.
Proceedings Article
Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
TL;DR: This work presents iterative parameter estimation algorithms for conditional random fields and compares the performance of the resulting models to HMMs and MEMMs on synthetic and natural-language data.