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

We propose a novel context-dependent (CD) model for large-vocabulary speech recognition (LVSR) that leverages recent advances in using deep belief networks for phone recognition. We describe a pre-trained deep neural network hidden Markov model (DNN-HMM) hybrid architecture that trains the DNN to produce a distribution over senones (tied triphone states) as its output. The deep belief network pre-training algorithm is a robust and often helpful way to initialize deep neural networks generatively that can aid in optimization and reduce generalization error. We illustrate the key components of our model, describe the procedure for applying CD-DNN-HMMs to LVSR, and analyze the effects of various modeling choices on performance. Experiments on a challenging business search dataset demonstrate that CD-DNN-HMMs can significantly outperform the conventional context-dependent Gaussian mixture model (GMM)-HMMs, with an absolute sentence accuracy improvement of 5.8% and 9.2% (or relative error reduction of 16.0% and 23.2%) over the CD-GMM-HMMs trained using the minimum phone error rate (MPE) and maximum-likelihood (ML) criteria, respectively.

/pdf/context-dependent-pre-trained-deep-neural-networks-for-large-14o17jhkzd.pdf

Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition

is one of the most recognizablecharacters in 20th century cinema. HAL is an artiﬁcial agent capable of such advancedlanguage behavior as speaking and understanding English, and at a crucial moment inthe plot, even reading lips. It is now clear that HAL’s creator, Arthur C. Clarke, wasa little optimistic in predicting when an artiﬁcial agent such as HAL would be avail-able. But just how far off was he? What would it take to create at least the language-relatedpartsofHAL?WecallprogramslikeHALthatconversewithhumansinnatural

/pdf/speech-and-language-processing-1xjlmt8snu.pdf

Speech and Language Processing

Recurrent neural networks are powerful sequence learners. They are able to incorporate context information in a flexible way, and are robust to localised distortions of the input data. These properties make them well suited to sequence labelling, where input sequences are transcribed with streams of labels. The aim of this thesis is to advance the state-of-the-art in supervised sequence labelling with recurrent networks. Its two main contributions are (1) a new type of output layer that allows recurrent networks to be trained directly for sequence labelling tasks where the alignment between the inputs and the labels is unknown, and (2) an extension of the long short-term memory network architecture to multidimensional data, such as images and video sequences.

https://mediatum.ub.tum.de/doc/673554/file.pdf

Supervised Sequence Labelling with Recurrent Neural Networks

Performance of even the best current stochastic recognizers severely degrades in an unexpected communications environment. In some cases, the environmental effect can be modeled by a set of simple transformations and, in particular, by convolution with an environmental impulse response and the addition of some environmental noise. Often, the temporal properties of these environmental effects are quite different from the temporal properties of speech. We have been experimenting with filtering approaches that attempt to exploit these differences to produce robust representations for speech recognition and enhancement and have called this class of representations relative spectra (RASTA). In this paper, we review the theoretical and experimental foundations of the method, discuss the relationship with human auditory perception, and extend the original method to combinations of additive noise and convolutional noise. We discuss the relationship between RASTA features and the nature of the recognition models that are required and the relationship of these features to delta features and to cepstral mean subtraction. Finally, we show an application of the RASTA technique to speech enhancement. >

RASTA processing of speech

We present a method to extract speaker turn segmentation from multiple distant microphones (MDM) using only delay values found via a cross-correlation between the available channels. The method is robust against the number of speakers (which is unknown to the system), the number of channels, and the acoustics of the room. The delays between channels are processed and clustered to obtain a segmentation hypothesis. We have obtained a 31.2% diarization error rate (DER) for the NIST's RT05s MDM conference room evaluation set. For a MDM subset of NIST's RT04s development set, we have obtained 36.93% DER and 35.73% DER*. Comparing those results with the ones presented by Ellis and Liu [8], who also used between-channels differences for the same data, we have obtained 43% relative improvement in the error rate.

Speaker diarization for multi-microphone meetings using only between-channel differences

We describe the development of our speech recognition system for the National Institute of Standards and Technology (NIST) Spring 2005 Meeting Rich Transcription (RT-05S) evaluation, highlighting improvements made since last year [1]. The system is based on the SRI-ICSI-UW RT-04F conversational telephone speech (CTS) recognition system, with meeting-adapted models and various audio preprocessing steps. This year's system features better delay-sum processing of distant microphone channels and energy-based crosstalk suppression for close-talking microphones. Acoustic modeling is improved by virtue of various enhancements to the background (CTS) models, including added training data, decision-tree based state tying, and the inclusion of discriminatively trained phone posterior features estimated by multilayer perceptrons. In particular, we make use of adaptation of both acoustic models and MLP features to the meeting domain. For distant microphone recognition we obtained considerable gains by combining and cross-adapting narrow-band (telephone) acoustic models with broadband (broadcast news) models. Language models (LMs) were improved with the inclusion of new meeting and web data. In spite of a lack of training data, we created effective LMs for the CHIL lecture domain. Results are reported on RT-04S and RT-05S meeting data. Measured on RT-04S conference data, we achieved an overall improvement of 17% relative in both MDM and IHM conditions compared to last year's evaluation system. Results on lecture data are comparable to the best reported results for that task.

Further progress in meeting recognition : The ICSI-SRI spring 2005 speech-to-text evaluation system

Over the past 40 years, significant progress has been made in the fields of speech recognition and speech understanding. Current state-of-the-art speech recognition systems are capable of achieving word-level accuracies of 90% to 95% on continuous speech recognition tasks using 5000 words. Even larger systems, capable of recognizing 20,000 words are just now being developed. Speech understanding systems have recently been developed that perform fairly well within a restricted domain.
While the size and performance of modern speech recognition and understanding systems are impressive, it is evident to anyone who has used these systems that the technology is primitive compared to our own human ability to understand speech. Some of the difficulties hampering progress in the fields of speech recognition and understanding stem from the many sources of variation that occur during human communication.
One of the sources of variation that occurs in human communication is the different ways that words can be pronounced. There are many causes of pronunciation variation, such as: the phonetic environment in which the word occurs, the dialect of the speaker, the speaker's age, the speaker's gender, and the speaking rate. Some researchers have shown improvements in speech recognition performance on a read-speech task through the use of explicit pronunciation modeling, while others have not shown any significant improvements.
This thesis presents an algorithm for the construction of models that attempt to capture the variation that occurs in the pronunciations of words in spontaneous (i.e., non-read) speech. A technique for developing alternate pronunciations of words and then estimating the probabilities of the alternate pronunciations is presented. Additionally, we describe the development and implementation of a spoken-language understanding system called the Berkeley Restaurant Project (BeRP). Multiple pronunciation word models constructed using the algorithm proposed in this thesis are evaluated within the context of the BeRP system. The results of this evaluation show that the explicit modeling of variation in the pronunciation of words improves the performance of both the speech recognition and the speech understanding components of the BeRP system.

Lexical modeling in a speaker independent speech understanding system

T he merger of medicine and technology often relies upon serendipity--a given set of circumstances, a chance meeting. Such is the case with robotic applications to surgery. The cessation of the Cold Wa.r has left many corporations that had been engaged in research projects for the defense industry without gainful employment. At the same time, the development of laparoscopic surgery and diminishing financial resources in medicine created the need for creative solutions to specific problems, such as the development that is the subject of this article.

Voice activation of a surgical robotic assistant

The authors investigate the use of continuous features derived by perceptual linear predictive (PLP) analysis, examine the effect of adding temporal features, and compare it to the previously studied use of multiframe input. Comparisons of the MLP (multilayer perceptron) and conventional Gaussian classifiers are also reported. The speaker-dependent portion of the Resource Management database was used for this test. Additionally, some experiments were performed with a perplexity-2200 speaker-independent recognition task on a subset of the TIMIT database. In each case, the PLP features were used as input to the networks. The experiments show the advantage of continuous PLP features and their first and second temporal derivatives. >

Chuck Wooters

Papers

Speaker diarization for multi-microphone meetings using only between-channel differences

Further progress in meeting recognition : The ICSI-SRI spring 2005 speech-to-text evaluation system

Lexical modeling in a speaker independent speech understanding system

Voice activation of a surgical robotic assistant

Continuous speech recognition using PLP analysis with multilayer perceptrons