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
Proceedings ArticleDOI
CRF-based Single-stage Acoustic Modeling with CTC Topology
Hongyu Xiang,Zhijian Ou +1 more
TL;DR: In a head-to-head comparison, the CTC-CRF model using simple Bidirectional LSTMs consistently outperforms the strong SS-LF-MMI, across all the three benchmarking datasets and in both cases of mono-phones and mono-chars.
Journal ArticleDOI
Keyword spotting for self-training of BLSTM NN based handwriting recognition systems
TL;DR: A set of experiments shows the high potential of self-training for bootstrapping handwriting recognition systems, both for modern and historical handwritings, and demonstrates the benefits of using keyword spotting over previously published self- training schemes.
Proceedings ArticleDOI
Spike-Triggered Non-Autoregressive Transformer for End-to-End Speech Recognition.
TL;DR: In this paper, a spike-triggered non-autoregressive transformer model was proposed for end-to-end speech recognition, which introduces a CTC module to predict the length of the target sequence and accelerate the convergence.
Book ChapterDOI
Handwritten Digit String Recognition by Combination of Residual Network and RNN-CTC
TL;DR: In this article, a residual network is designed to extract features from input images, then a RNN is employed to model the contextual information within feature sequences and predict recognition results, and a standard CTC is applied to calculate the loss and yield the final results.
Journal ArticleDOI
An Efficient and Perceptually Motivated Auditory Neural Encoding and Decoding Algorithm for Spiking Neural Networks
TL;DR: In this paper, a neural encoding and decoding scheme called Biologically plausible Auditory Encoding (BAE) was proposed for audio processing, which emulates the functions of the perceptual components of the human auditory system, including the cochlear filter bank, inner hair cells, auditory masking effects from psychoacoustic models, and the spike neural encoding by the auditory nerve.
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.