Parameter sharing plays an important role in statistical modeling since training data are usually limited. On the one hand, we would like to use models that are as detailed as possible. On the other hand, with models too detailed, we can no longer reliably estimate the parameters. Triphone generalization may force two models to be merged together when only parts of the model output distributions are similar, while the rest of the output distributions are different. This problem can be avoided if clustering is carried out at the distribution level. In this paper, a shared-distribution model is proposed to replace generalized triphone models for speaker-independent continuous speech recognition. Here, output distributions in the hidden Markov model are shared with each other if they exhibit acoustic similarity. In addition to detailed representation, it also gives us the freedom to use a large number of states for each phonetic model. Although an increase in the number of states will inc...

decide which contexts are similar and can share parameters. A key feature of this approach is that it allows the construction of models which are dependent upon contextual effects occurring across word boundaries. The use of cross word context dependent models presents problems for conventional decoders. The second part of the thesis therefore presents a new decoder design which is capable of using these models efficiently. The decoder is suitable for use with very large vocabularies and long span language models. It is also capable of generating a lattice of word hypotheses with little computational overhead. These lattices can be used to constrain further decoding, allowing efficient use of complex acoustic and language models. The effectiveness of these techniques has been assessed on a variety of large vocabulary continuous speech recognition tasks and results are presented which analyse performance in terms of computational complexity and recognition accuracy. The experiments dem

is granted. A Maximum-Likelihood Approach to Stochastic Matching for Robust Speech Recognition Ananth Sankar 2 and Chin-Hui Lee Speech Research Department AT&T Bell Laboratories Murray Hill, NJ 07974 1 Introduction Recently there has been much interest in the problem of improving the performance of automatic speech recognition (ASR) systems in adverse environments. When there is a mismatch between the training and testing environments, ASR systems suffer a degradation in performance. The goal of robust speech recognition is to remove the effect of this mismatch so as to bring the recognition performance as close as possible to the matched conditions. In speech recognition, the speech is usually modeled by a set of hidden Markov models (HMM) X . During recognition the observed utterance Y is decoded using these models. Due to the mismatch between training and testing conditions, this often results in a degradation in performance compared to the matched conditions. The mismatch b...

A text-based and spoken language processing framework based on the Constraint Dependency Grammar (CDG) developed by Maruyama [24, 25] is discussed. The scope of CDG is expanded to allow for the analysis of sentences containing lexically ambiguous words, to allow feature analysis in constraints, and to efficiently process multiple sentence candidates that are likely to arise in spoken language processing. The benefits of the CDG parsing approach are summarized. Additionally, the development of CDG grammars using our grammar tools and parser is discussed.

The question of how to integrate language models with speech recognition systems is becoming more important as speech recognition technology matures. For the purposes of this paper, we have classified the level of integration of current and past approaches into three categories: tightly-coupled, loosely-coupled, or semicoupled systems. We then argue that loose coupling is more appropriate given the current state of the art and given that it allows one to measure more precisely which components of the language model are most important. We will detail how the speech component in our approach interacts with the language model and discuss why we chose our language model. 1 Introduction State of the art speech recognition systems achieve high recognition accuracies only on tasks that have low perplexities. The perplexity of a task is, roughly speaking, the average number of choices at any decision point. The perplexity of a task is at a minimum when the true language model is known and co...

This paper investigates the impact of Constraint Dependency Grammars (CDG) on the accuracy of an integrated speech recognition and CDG parsing system. We compare a conventional CDG with CDGs that are induced from annotated sentences and template-expanded sentences. The grammars are evaluated on parsing speed, precision/coverage, and improvement of word and sentence accuracy of the integrated system. Sentence-derived CDGs significantly improve recognition accuracy over the conventional CDG but are less general. Expanding the sentences with templates provides us with a mechanism for increasing the coverage of the grammar with only minor reductions in recognition accuracy.

Constraint Dependency Grammar (CDG) is a constraint-based grammatical formalism which has a weak generative capacity beyond context-free grammars and supports a very flexible parsing algorithm for working with feature grammars; however, the running time of the parser is O(n 4 ). Hence, we have investigated how to improve the running time of the parser by applying feature constraints differentially and by using aggregate unary constraints, which can be applied in O(n 2 ) time. Additional speedup was achieved by integrating the filtering algorithm more tightly with the parser and by supporting the use of a varying number of roles for word classes. Key words: Parsing, NLP, Constraint Satisfaction. Introduction: CDG Parsing Constraint Dependency Grammar, introduced by Maruyama [1, 2, 3], uses constraints to determine which dependencies are grammatical for a sentence. The parsing algorithm is framed as a constraint satisfaction problem: the parsing rules are the constraints and the s...

ROLE VALUES A Thesis Submitted to the Faculty Purdue University by Christopher M. White In Partial Fulfillment of the Requirements for the Degree Doctor of Philosophy May 2000 - ii - To my loving wife Margit.

In this paper, we describe a prototype spoken language system that loosely integrates a speech recognition component based on hidden Markov models with a constraint dependency grammar (CDG) parser using a word graph to pass sentence candidates between the two modules. This loosely coupled system was able to improve the sentence selection accuracy and concept accuracy over the level achieved by the acoustic module with a stochastic grammar. Timing profiles suggest that a tighter coupling of the modules could reduce parsing times of the system, as could the development of better acoustic models and tighter parsing constraints for conjunctions. 1. INTRODUCTION In this paper, we describe a prototype of a spoken language system that integrates a speech recognition component based on hidden Markov models with a constraint dependency grammar (CDG) parser. The underlying goal of our combined system is to identify the 'best' overall sentence candidate with respect to all available knowledge s...

Most modern automatic speech recognition systems make use of acoustic models based on hidden Markov models. To obtain reasonable recognition performance within a large vocabulary framework, the acoustic models usually include a pronunciation model, together with complex parameter tying schemes. In many cases the pronunciation model operates on a phoneme level and is derived independently of the underlying models. In contrast, this work is aimed at improving pronunciation modelling on a sub-phone level in a combined framework. The modelling of pronunciation variation is assumed to be of special importance for recognition of spontaneous speech.