Texas Instruments Corporation

Kathleen M Goudie

Kun-Shan Lin

Gene A Frantz

Speech is analyzed for phonological linguistic units (phonemes or allophones), along with their duration pattern and pitch pattern contour as a group or string of a syllable. The patterns are encoded as the best-match pattern in a set of prestored standard patterns. This data is transmitted to a synthesizer to help in the intonation reconstruction of speech.

Low data rate speech encoding employing syllable duration patterns

The present invention provides an artificial pitch contour to phonological linguistic phoneme unit string data. In the event that the phonological linguistic string data includes some information on intonation contour, such as primary accent, secondary accents and rising or falling intonation mode data, this data is employed along with a determination of syllable type for each syllable to assign one of a predetermined plurality of pitch patterns to each syllable. If such intonation data is not available, as for example in a bar code or text-to-speech system, then primary and secondary accent data are generated based upon the presence or absence of strong vowels involved in word stress syllables. This invention is most useful in improving the spoken intonation contour in low data rate speech applications in which some intonation data is available.

constructed syllable pitch patterns from phonological linguistic unit

The present invention provides a conversion between a speech mode in which each word is clearly enunciated as if spoken in isolation and in which a phrase is spoken as a whole taking into account the influence of adjacent words. In the phrase mode, word ending final phonological linguistic units are replaced with their corresponding internal versions, and short strong vowels are substituted for the corresponding long strong vowels except at the word ends. In the word mode, a word final pronunciation is given when a corresponding internal phonological linguistic unit occurs at a word end, and short strong vowels are replaced by the corresponding long strong vowel when the short strong vowel occurs at the end of a word or prior to a set of voiced consonants. In either mode, a substitution may be made for the pronunciation of frequently used words. This invention is most useful in speaking electronic learning aids which permit word or phrase speech synthesis from the same data.

Speaking apparatus having differing speech modes for word and phrase

The present invention provides syllable boundaries from a string of phonological linguistic unit indicia and word boundary data. The syllable boundary recognizer places a syllable boundary either at the next following word boundary or prior to the second vowel phonological linguistic unit indicia following the prior syllable boundary based upon the sequence of consonant phonological linguistic unit indicia prior to that second vowel. A permitted syllable initial consonant cluster includes an optional fricative consonant, an optional stop consonant and an optional sonorant consonant. The syllable boundary recognizer searches backward from the second vowel phonological linguistic unit indicia until the permitted sequence is violated, whereupon a syllable boundary is inserted. In the preferred embodiment, a refinement permits certain strong vowel phonological linguistic unit indicia to 'capture' the following phonological linguistic unit indicia and shift the syllable boundary. This technique is most useful in low data rate speech systems which provide intonation based upon syllables.

Syllable boundary recognition from phonological linguistic unit string

A text-to-speech synthesis system receives digital code representative of characters from a local or remote source, and converts those character codes into speech. A set of allophone rules is contained in a memory and each incoming character set is matched with the proper character set to describe the sound of that particular character set. A microcontroller is dedicated to the comparison procedure which provides allophonic code when a match is made. The allophonic code is provided to a speech producing system which has a system microcontroller for controlling the retrieval, from a read-only memory, of digital signals representative of the individual allophone parameters. The addresses at which such allophone parameters are located are directly related to the allophonic code. A dedicated microcontroller concatenates the digital signals representative of the allophone parameters, including code indicating stress and intonation patterns for the allophones. An LPC speech synthesizer receives the digital signals and provides analog signals corresponding thereto to a loud speaker to produce speech-like sounds with stress and intonation.

Text-to-speech synthesis system

An electronic, speech producing system receives allophonic codes and produces speech-like sounds corresponding to these codes, through a loud speaker. A micro-controller controls the retrieval, from a read-only memory, of digital signals representative of individual allophone parameters. The addresses at which such allophone parameters are located are directly related to the allophonic code. A dedicated microcontroller concatenates the digital signals representative of the allophone parameters, including code indicating stress and intonation patterns for the allophones. The allophones are divided into a plurality of frames with one digital position indicating whether the frame is the last frame in the allophone, in which event an extra frame is introduced to provide smoothing between allophones when no stop is present and when the present allophone is voiced and the subsequent allophone is voiced, or when the present allophone is unvoiced and the subsequent allophone is unvoiced. An LPC speech synthesizer receives the digital signals and provides analog signals corresponding thereto to the loud speaker to produce speech-like sounds with stress and intonation.

Growing community of inventors

Lubbock, TX, United States of America

Kathleen M Goudie