Abstract: Text may be converted to audible signals, such as speech, by first training a neural network 106 using recorded audio messages 204. To begin the training, the recorded audio messages are converted into a series of audio frames 205 having a fixed duration 213. Then, each audio frame is assigned a phonetic representation 203 and a target acoustic representation 208, where the phonetic representation 203 is a binary word that represents the phone and articulation characteristics of the audio frame, while the target acoustic representation 208 is a vector of audio information such as pitch and energy. After training, the neural network 106 is used in conversion of text into speech. First, text that is to be convened is translated to a series of phonetic frames 401 of the same form as the phonetic representations 208 and having the fixed duration 213. Then the neural network produces acoustic representations in response to context descriptions 207 that include some of the phonetic frames 401.

Abstract: In a speech coder (100), excitation source gain information (802) is transmitted along with a coding mode indicator. The coding mode indicator indicates how the gain information is to be interpreted. In one embodiment, the coding mode indicator can also be utilized to control which of a plurality of excitation sources (202, 206-208) are utilized when synthesizing the speech. The coding mode itself is selected as a function of the periodicity of an input speech signal.

Abstract: A method for protecting information bits wherein input data bits, at least some of which are to be protected, are sorted based upon information determined from a subset of the input data bits. An error control coding technique is applied to at least some of the sorted bits. In the preferred embodiment, an input data stream of voice coder bits is separated into arrays of bits. A first array (302) comprises voice coder bits needing error protection, with the bits arranged in order of importance determined by voicing mode. The second array (303) comprises bits that will not be error protected. The bits from the first array are provided to the input of an encoder (304), then the encoded bits are combined (305) with the bits from the second array (303) to form a bit stream.