Text to speech

A method for converting text to speech using a computing device having a memory, comprising:

• (a) receiving a text comprising a plurality of words into said memory of said computing device;
• (b) deriving a plurality of phonemes from said text;
• (c) associating with each of said phonemes a prosody record based on a database of prosody records associated with a plurality of words;
• (d) applying a first set of the artificial intelligence rules to determine context information associated with said text;
• (e) for each of said phonemes:
• (i) determining context influenced prosody changes;
• (ii) applying a second set of rules based on Lessac theory to determine Lessac derived prosody changes;
• (iii) amending the prosody record in response to said context influenced prosody changes and said Lessac derived prosody changes;
• (iv) reading from said memory sound information associated with said phonemes;
• (v) amending said sound information based on the prosody record as amended in response to said context influenced prosody changes and said Lessac derived prosody changes to generate amended sound information;
• and
• (f) outputting said sound information to generate a speech signal.

A method, comprising:

• (a) examining a text to be spoken to an audience for a specific communications purpose;
• (b) marking-up said text according to a phonetic markup systems, wherein the phonetic markup system comprises the Lessac System pronunciation rules notations;
• (c) implementing a set of rules to control a speech to text generator based on speech principles, wherein the speech principles are Lessac principles;
• (d) using a computer to speak said marked-up text expressively;
• (e) repeating the step of using a computer to speak said marked-up text expressively using alternative pronunciations of the selected style of expression wherein each of the tonal, structural, and consonant energies having a different balance in the speech, are also spoken;
• (f) listening to said spoken speech generated by said computer;
• (g) evaluating said spoken speech generated by said computer for consistency with style criteria and/or expressiveness;
• (h) assembling an audience;
• (i) playing back said spoken speech generated by said computer to said audience;
• (j) evaluating comprehension by said audience of spoken speech generated by said computer correlated to a particular implemented rule or rules;
• and
• (k) selecting out those rules providing high audience comprehension.

A method for converting input text to a synthesized speech output using a computing device having memory, the method comprising:

• (a) receiving the input text into the computing device memory;
• (b) applying a set of the lexical parsing rules to parse said text into a plurality of components;
• (c) associating pronunciation and meaning information with said components;
• (d) applying a set of phrase parsing rules to generate marked up text;
• (e) phonetically parsing said marked up text using phonetic parsing rules and parsing said marked up text using Lessac expressive parsing rules;
• (f) applying artificial intelligence to recognize the meaning of the text and to identify the emotional nature of the message to be communicated;
• (g) employing a grapheme-to-phoneme database to instruct the computing device in appropriate pronunciation to reflect the identified emotion;
• (g) storing a plurality of sounds in memory each of said sounds being associated with said pronunciation information;
• and
• (h) recalling the sounds associated with said text to generate a raw speech signal from said marked up text after said parsing using phonetic and expressive parsing rules.