Multilayer neural networks trained with the back-propagation algorithm constitute the best example of a successful gradient based learning technique. Given an appropriate network architecture, gradient-based learning algorithms can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters, with minimal preprocessing. This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task. Convolutional neural networks, which are specifically designed to deal with the variability of 2D shapes, are shown to outperform all other techniques. Real-life document recognition systems are composed of multiple modules including field extraction, segmentation recognition, and language modeling. A new learning paradigm, called graph transformer networks (GTN), allows such multimodule systems to be trained globally using gradient-based methods so as to minimize an overall performance measure. Two systems for online handwriting recognition are described. Experiments demonstrate the advantage of global training, and the flexibility of graph transformer networks. A graph transformer network for reading a bank cheque is also described. It uses convolutional neural network character recognizers combined with global training techniques to provide record accuracy on business and personal cheques. It is deployed commercially and reads several million cheques per day.

Gradient-based learning applied to document recognition

Most current speech recognition systems use hidden Markov models (HMMs) to deal with the temporal variability of speech and Gaussian mixture models (GMMs) to determine how well each state of each HMM fits a frame or a short window of frames of coefficients that represents the acoustic input. An alternative way to evaluate the fit is to use a feed-forward neural network that takes several frames of coefficients as input and produces posterior probabilities over HMM states as output. Deep neural networks (DNNs) that have many hidden layers and are trained using new methods have been shown to outperform GMMs on a variety of speech recognition benchmarks, sometimes by a large margin. This article provides an overview of this progress and represents the shared views of four research groups that have had recent successes in using DNNs for acoustic modeling in speech recognition.

Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups

Recurrent neural networks can be used to map input sequences to output sequences, such as for recognition, production or prediction problems. However, practical difficulties have been reported in training recurrent neural networks to perform tasks in which the temporal contingencies present in the input/output sequences span long intervals. We show why gradient based learning algorithms face an increasingly difficult problem as the duration of the dependencies to be captured increases. These results expose a trade-off between efficient learning by gradient descent and latching on information for long periods. Based on an understanding of this problem, alternatives to standard gradient descent are considered. >

http://cslt.riit.tsinghua.edu.cn/mediawiki/images/0/03/Learning_Long-Term_Dependencies_with_Gradient_Descent_is_Difficult.pdf

Learning long-term dependencies with gradient descent is difficult

SRILM is a collection of C++ libraries, executable programs, and helper scripts designed to allow both production of and experimentation with statistical language models for speech recognition and other applications. SRILM is freely available for noncommercial purposes. The toolkit supports creation and evaluation of a variety of language model types based on N-gram statistics, as well as several related tasks, such as statistical tagging and manipulation of N-best lists and word lattices. This paper summarizes the functionality of the toolkit and discusses its design and implementation, highlighting ease of rapid prototyping, reusability, and combinability of tools.

SRILM – An Extensible Language Modeling Toolkit

From the Publisher:
This book takes an empirical approach to language processing, based on applying statistical and other machine-learning algorithms to large corpora.Methodology boxes are included in each chapter. Each chapter is built around one or more worked examples to demonstrate the main idea of the chapter. Covers the fundamental algorithms of various fields, whether originally proposed for spoken or written language to demonstrate how the same algorithm can be used for speech recognition and word-sense disambiguation. Emphasis on web and other practical applications. Emphasis on scientific evaluation. Useful as a reference for professionals in any of the areas of speech and language processing.

/pdf/speech-and-language-processing-an-introduction-to-natural-atzaecqfem.pdf

Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition

Speech-recognition systems must often decide between competing ways of breaking up the acoustic input into strings of words. Since the possible strings may be acoustically similar, a language model is required; given a word string, the model returns its linguistic probability. Several Markov language models are discussed. A novel kind of language model which reflects short-term patterns of word use by means of a cache component (analogous to cache memory in hardware terminology) is presented. The model also contains a 3g-gram component of the traditional type. The combined model and a pure 3g-gram model were tested on samples drawn from the Lancaster-Oslo/Bergen (LOB) corpus of English text. The relative performance of the two models is examined, and suggestions for the future improvements are made. >

/pdf/a-cache-based-natural-language-model-for-speech-recognition-4ska0ikucg.pdf

A cache-based natural language model for speech recognition

https://hal.archives-ouvertes.fr/hal-00499180/document

Automatic speech recognition and speech variability: A review

The integration of multilayered and recurrent artificial neural networks (ANNs) with hidden Markov models (HMMs) is addressed. ANNs are suitable for approximating functions that compute new acoustic parameters, whereas HMMs have been proven successful at modeling the temporal structure of the speech signal. In the approach described, the ANN outputs constitute the sequence of observation vectors for the HMM. An algorithm is proposed for global optimization of all the parameters. Results on speaker-independent recognition experiments using this integrated ANN-HMM system on the TIMIT continuous speech database are reported. >

Global optimization of a neural network-hidden Markov model hybrid

Semantics deals with the organization of meanings and the relations between sensory signs or symbols and what they denote or mean. Computational semantics performs a conceptualization of the world using computational processes for composing a meaning representation structure from available signs and their features present, for example, in words and sentences. Spoken language understanding (SLU) is the interpretation of signs conveyed by a speech signal. SLU and natural language understanding (NLU) share the goal of obtaining a conceptual representation of natural language sentences. Specific to SLU is the fact that signs to be used for interpretation are coded into signals along with other information such as speaker identity. Furthermore, spoken sentences often do not follow the grammar of a language; they exhibit self-corrections, hesitations, repetitions, and other irregular phenomena. SLU systems contain an automatic speech recognition (ASR) component and must be robust to noise due to the spontaneous nature of spoken language and the errors introduced by ASR. Moreover, ASR components output a stream of words with no structure information like punctuation and sentence boundaries. Therefore, SLU systems cannot rely on such markers and must perform text segmentation and understanding at the same time.

Spoken language understanding

This article describes a new method for building a natural language understanding (NLU) system, in which the system's rules are learnt automatically from training data. The method has been applied to design of a speech understanding (SU) system. Designers of such systems rely increasingly on robust matchers to perform the task of extracting meaning from one or several word sequence hypotheses generated by a speech recognizer. We describe a new data structure, the semantic classification tree (SCT), that learns semantic rules from training data and can be a building block for robust matchers for NLU tasks. By reducing the need for handcoding and debugging a large number of rules, this approach facilitates rapid construction of an NLU system. In the case of an SU system, the rules learned by an SCT are highly resistant to errors by the speaker or by the speech recognizer because they depend on a small number of words in each utterance. Our work shows that semantic rules can be learned automatically from training data, yielding successful NLU for a realistic application. >

R. De Mori

Papers

A cache-based natural language model for speech recognition

Automatic speech recognition and speech variability: A review

Global optimization of a neural network-hidden Markov model hybrid

Spoken language understanding

The application of semantic classification trees to natural language understanding