Texas Instruments Corporation

Kun-Shan Lin

Gene A Frantz

Kathleen M Goudie

Jay Bryan Reimer

Alva E Henderson

The present invention is a speech encoding technique useful in low data rate speech. Spoken input is analyzed to determine its basic phonological linguistic units and syllables. The pitch track for each syllable is compared with each of a predetermined set of pitch patterns. A pitch pattern forming the best match to the actual pitch track is selected for each syllable. Phonological linguistic unit indicia and pitch pattern indicia are transmitted to a speech synthesis apparatus. This synthesis apparatus matches the pitch pattern indicia to syllable groupings of the phonological linguistic unit indicia. During speech synthesis, sounds are produced corresponding to the phonological linguistic unit indicia with their primary pitch controlled by the pitch pattern indicia of the corresponding syllable. This achieves some measure of approximation to the primary pitch of the original spoken input at a low data rate. In the preferred embodiment, each pitch pattern includes an initial pitch slope, which may be zero indicating no change in pitch, a final pitch slope and a turning point between these two slopes.

Low data rate speech encoding employing syllable pitch patterns

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

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

Method and apparatus for converting voice characteristics of synthesized speech from a single applied source of synthesized speech in a manner obtaining modified voice characteristics pertaining to the apparent age and/or sex of the speaker. The apparatus is capable of altering the voice characteristics of synthesized speech to obtain modified voice sounds simulating child-like, teenage, adult, aged and sexual preference characteristics by control of vocal track parameters including pitch period, vocal tract model, and speech data rate. A source of synthesized speech having a predetermined pitch period, a predetermined vocal tract model, and a predetermined speech rate is separated into the respective speech parameters. The values of pitch, the speech data frame length, and the speech data rate are then varied in a preselected manner to modify the voice characteristics of the synthesized speech from the source thereof. Thereafter, the changed speech data parameters are re-combined into a modified synthesized speech data format having different voice characteristics with respect to the synthesized speech from the source, and an audio signal representative of human speech is generated from the modified synthesized speech data format from which audible synthesized speech may be generated.

Method and apparatus for converting voice characteristics of synthesized

An electronic apparatus for translation from a host language to a non-host language in which the individual word is evaluated as to its contextual meaning. The sequence of words, typically a sentence, within the host language, which is communicated to the electronic apparatus is translated, through a recognition device into a series of recognized words. These recognized words are further refined through analysis of their contextual meaning within the sequence (sentence) so as to differentiate between words of similar pronunciation and between homonyms. The present invention permits the direct entry, from voice, to a translator to a foreign language or alternatively to control language for use with an electronic or electromechanical apparatus.

Electronic apparatus from a host language

A formant tracker for receiving an analog speech signal and generating indicia representative of the formant. A pitch tracker determines the fundamental frequency of the analog speech input. The fundamental frequency is used to control a sinusoidal oscillator in the generation of a sinusoidal signal which when combined with the analog speech input generates a convolution over the chosen formant frequency. The process is repeated for each integer multiple of the fundamental frequency, thereby changing the sinusoidal oscillator. The optimal integer multiple is chosen which generates the formant identification. The optimal integer is also used to generate an appropriate bandwidth. Three formant frequency ranges are used to define human speech. The optimal integers for the other two formant identifications and the appropriate bandwidths are similarly determined. The three optimal integer values are combined with the fundamental frequency to get the three formant values and their associated bandwidths. These formant values and their bandwidths together with the fundamental frequency are communicated as output so as to identify in formant form the analog signal.

Formant tracker

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

Kun-Shan Lin