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 have collected a corpus of data from natural meetings that occurred at the International Computer Science Institute (ICSI) in Berkeley, California over the last three years The corpus contains audio recorded simultaneously from head-worn and table-top microphones, word-level transcripts of meetings, and various metadata on participants, meetings, and hardware Such a corpus supports work in automatic speech recognition, noise robustness, dialog modeling, prosody, rich transcription, information retrieval, and more We present details on the contents of the corpus, as well as rationales for the decisions that led to its configuration The corpus were delivered to the Linguistic Data Consortium (LDC)

/pdf/the-icsi-meeting-corpus-1hle0448sk.pdf

The ICSI Meeting Corpus

When performing speaker diarization on recordings from meetings, multiple microphones of different qualities are usually available and distributed around the meeting room. Although several approaches have been proposed in recent years to take advantage of multiple microphones, they are either too computationally expensive and not easily scalable or they cannot outperform the simpler case of using the best single microphone. In this paper, the use of classic acoustic beamforming techniques is proposed together with several novel algorithms to create a complete frontend for speaker diarization in the meeting room domain. New techniques we are presenting include blind reference-channel selection, two-step time delay of arrival (TDOA) Viterbi postprocessing, and a dynamic output signal weighting algorithm, together with using such TDOA values in the diarization to complement the acoustic information. Tests on speaker diarization show a 25% relative improvement on the test set compared to using a single most centrally located microphone. Additional experimental results show improvements using these techniques in a speech recognition task.

/pdf/acoustic-beamforming-for-speaker-diarization-of-meetings-26ampyixrb.pdf

Acoustic Beamforming for Speaker Diarization of Meetings

The present invention pertains to control systems and provides a run time configurable control system for selecting and operating one of a plurality of operating room devices from a single input source, the system comprising a master controller having a voice control interface and means for routing control signals. The system additionally may include a plurality of slave controllers to provide expandability of the system. Also, the system includes output means for generating messages to the user relating to the status of the control system in general and to the status of devices connected thereto.

General purpose distributed operating room control system

In this paper, we present a novel speaker segmentation and clustering algorithm. The algorithm automatically performs both speaker segmentation and clustering without any prior knowledge of the identities or the number of speakers. Our algorithm uses "standard" speech processing components and techniques such as HMM, agglomerative clustering, and the Bayesian information criterion. However, we have combined and modified these so as to produce an algorithm with the following advantages: no threshold adjustment requirements; no need for training/development data; and robustness to different data conditions. This paper also reports the performance of this algorithm on different datasets released by the USA National Institute of Standards and Technology (NIST) with different initial conditions and parameter settings. The consistently low speaker-diarization error rate clearly indicates the robustness and utility of the algorithm.

/pdf/a-robust-speaker-clustering-algorithm-467in5oy3y.pdf

A robust speaker clustering algorithm

In this paper, we present the ICSI speaker diarization system. This system was used in the 2007 National Institute of Standards and Technology (NIST) Rich Transcription evaluation. The ICSI system automatically performs both speaker segmentation and clustering without any prior knowledge of the identities or the number of speakers. Our system uses "standard" speech processing components and techniques such as HMMs, agglomerative clustering, and the Bayesian Information Criterion. However, we have developed the system with an eye towards robustness and ease of portability. Thus we have avoided the use of any sort of model that requires training on "outside" data and we have attempted to develop algorithms that require as little tuning as possible.

The system is simular to last year's system [1] except for three aspects. We used the most recent available version of the beam-forming toolkit, we implemented a new speech/non-speech detector that does not require models trained on meeting data and we performed our development on a much larger set of recordings.

Chuck Wooters

Papers

The ICSI Meeting Corpus

Acoustic Beamforming for Speaker Diarization of Meetings

General purpose distributed operating room control system

A robust speaker clustering algorithm

The ICSI RT07s Speaker Diarization System