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
Internal Language Model Estimation for Domain-Adaptive End-to-End Speech Recognition
Zhong Meng,Sarangarajan Parthasarathy,Eric Sun,Yashesh Gaur,Naoyuki Kanda,Liang Lu,Xie Chen,Rui Zhao,Jinyu Li,Yifan Gong +9 more
TL;DR: This paper proposed an internal language models estimation (ILME) method to facilitate a more effective integration of the external LM with all pre-existing E2E models with no additional model training, including the most popular recurrent neural network transducer and attention-based encoder-decoder (AED) models.
Posted Content
An End-to-End Architecture for Keyword Spotting and Voice Activity Detection.
TL;DR: Novel inference algorithms for an end-to-end Recurrent Neural Network trained with the Connectionist Temporal Classification loss function are developed which allow the model to achieve high accuracy on both keyword spotting and voice activity detection without retraining.
Book ChapterDOI
Evolving modular fast-weight networks for control
TL;DR: An approach to problems that evolves fast-weight neural networks, although capable of implementing arbitrary non-linear mappings, can more easily exploit the piecewise linearity inherent in most systems, in order to produce simpler and more comprehensible controllers.
Proceedings Article
Connectionist Temporal Classification with Maximum Entropy Regularization
Hu Liu,Sheng Jin,Changshui Zhang +2 more
TL;DR: This work proposes a regularization method based on maximum conditional entropy which penalizes peaky distributions and encourages exploration and introduces an entropy-based pruning method to dramatically reduce the number of CTC feasible paths by ruling out unreasonable alignments.
Proceedings ArticleDOI
Improved Knowledge Distillation from Bi-Directional to Uni-Directional LSTM CTC for End-to-End Speech Recognition
Gakuto Kurata,Kartik Audhkhasi +1 more
TL;DR: An improved knowledge distillation algorithm is proposed that relaxes this assumption of shared frame-wise time alignments between the two models and improves the accuracy of the UniLSTM model.
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.