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
Efficient, Lexicon-Free OCR using Deep Learning
Marcin Namysl,Iuliu Konya +1 more
TL;DR: In this article, a segmentation-free OCR system that combines deep learning methods, synthetic training data generation, and data augmentation techniques is presented, which surpasses the accuracy of leading commercial and open-source engines on distorted text samples.
Proceedings ArticleDOI
Towards acoustic model unification across dialects
TL;DR: Two techniques are presented: Distillation and MultiTask Learning (MTL), which show that both techniques are superior to the jointly-trained model that is trained on all dialectal data, reducing word error rates by 4:2% and 0:6%, respectively.
Patent
Semantically-relevant discovery of solutions
TL;DR: In this article, a machine learning approach is used to train a model with click-through data to provide semantically-relevant discovery of solutions, such as an answer to a query.
Proceedings ArticleDOI
End-to-End Training of Acoustic Models for Large Vocabulary Continuous Speech Recognition with TensorFlow
TL;DR: An overall training architecture developed in light of TensorFlow components makes it possible to take advantage of both data parallelism and high speed computation on GPU for state-of-the-art sequence training of acoustic models.
Journal ArticleDOI
Fast End-to-End Speech Recognition Via Non-Autoregressive Models and Cross-Modal Knowledge Transferring From BERT
TL;DR: Li et al. as discussed by the authors proposed an end-to-end non-autoregressive speech recognition model called LASO (Listen Attentively, and Spell Once) which aggregates encoded speech features into the hidden representations corresponding to each token with attention mechanisms.
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.