in partial ful llment of the requirements for the degree of

When a musician gives a recital or concert, the music performed generally includes accompaniment. To render a good performance, the soloist and the accompanist must know the musical score and must follow the other musician's performance. Both performing and rehearsing are limited by constraints on the time and money available for bringing musicians together. Computer systems that automatically provide musical accompaniment offer an inexpensive, readily available alternative. Effective computer accompaniment requires software that can listen to live performers and follow along in a musical score. This work presents an implemented system and method for automatically accompanying a singer given a musical score. Specifically, I offer a method for robust, real-time detection of a singer's score position and tempo. Robust score following requires combining information obtained both from analyzing a complex signal (the singer's performance) and from processing symbolic notation (the score). Unfortunately, the mapping from the available information to score position does not define a function. Consequently, this work investigated a statistical characterization of a singer's score position and a model that combines the available musical information to produce a probabilistic position estimate. By making

Abstract. This tutorial presents an overview of automatic speech recognition systems. First, a mathematical formulation and related aspects are described. Then, some background on speech production/perception is presented. An historical review of the efforts in developing automatic recognition systems is presented. The main algorithms of each component of a speech recognizer and current techniques for improving speech recognition performance are explained. The current development of speech recognizers for Portuguese and English languages is discussed. Some campaigns to evaluate and assess speech recognition systems are described. Finally, this tutorial concludes by discussing some research trends in automatic speech recognition.

An interaction has been found between the true source language model, training language model, and the testing language model. This interaction has implications for vocabulary independent modeling, testing methodologies, discriminative training, and the adequacy of our current databases for continuous speech recognition (CSR) development. The current DARPA databases suffer from the described difficulties which suggests that new CSR databases are needed if we are to further advance the state-of-the-art.

It is generally acknowledged today that, while the intonational features speakers select when they utter a sentence are not determined by the syntax, semantics or discourse context of that sentence, knowledge of these factors can help to constrain the possible intonational features speakers are likely to choose. So, while intonational variation poses a challenge to speech recognition in one sense- in presenting yet another indicator of over-all utterance meaning to be recognized noted between intonational features and the syntax, semantics and discourse features of an utterance also present rich possibilities for help in the recognition task. The many-to-many mapping between intonational features and syntactic and discourse features can be illustrated by considering the various ways of uttering the sentences in (1). 1 (1) a. 560 CAN KIRK GET TO KODIAK BY MONDAY b. Kirk can get to Kodiak by Monday. For example, a senior officer might choose a falling pitch contour over (la) to