Texas Instruments Corporation

William M Fisher

George R Doddington

Michael L McMahan

Enrico L Bocchieri

Kathleen M Marshall

Speech recognition is improved using prestored words and prestored sentences which provide grammar or context rules. Multiple word hypotheses and plural sentence hypotheses are used. A speech recognition system uses a word hypothesizer to generate hypothesized words for a sentence recognizer. The sentence recognizer receives information containing the hypothesized word and its beginning and end points. The sentence recognizer compares each incoming hypothesis with words allowed by a grammar, and generates a partial or complete sentence hypothesis for each state in which the hypothesis is allowed by the grammar. A dynamic programming technique using backpointer is used to retain all currently valid partial and complete sentence hypotheses. When a complete sentence satisfies suitable criteria, it is output as a recognized sentence. Gaps and overlaps between hypothesized words are used in calculation of a sentence error for each partial and complete sentence hypothesis.

Speech recognition system

The specification discloses a method of transforming input symbolic data to output symbolic data for use in text-to-speech and other environments. A string of digital byte values representing the input symbolic data is stored in a first buffer memory location in rules processor (10). A set of rules defining a desired mapping of byte values is stored in a rules storage (12), along with a set of user special symbols. The rules ae sequentially mapped to transform the stored byte values in accordance with the rules and the special symbols from a first buffer memory location to a second buffer memory location.

Method for transforming symbolic data

In a text to speech system, digital text ASCII is examined for syllable boundaries to help accent generation for speech synthesis, and hyphenation in word processing. Digital allophone code characters in the form of a byte string are compared with prestored rules. Byte string segments which may comprise consonant clusters, and left and right adjacent environments thereof are examined.

Growing community of inventors

Plano, TX, United States of America

William M Fisher