Abstract: A method (300), device (408), and system (400) provide part-of-speech disambiguation for words based on hybrid neural-network and stochastic processing. The method disambiguates the part-of-speech tags of text tokens by obtaining a set of probabilistically annotated tags for each text token, determining a locally predicted tag for each text token based on the local context of the text token, determining an alternative tag for each text token based on the expanded context of the text token, and choosing between the locally predicted tag and the alternative tag when the locally predicted tag and the alternative tag are different.

Abstract: A method (900), device (200) and system (100) provide, in response to text/linguistic input, one of a set of pre-determined meanings which is the most likely intended meaning of that input. A trained meaning discriminator is generated from an annotated training corpus and a meaning discriminator trainer. The trained meaning discriminator generates a meaning vector from an input utterance. The intended meaning encoder analyzes the meaning vector to determine the most likely intended meaning and confidence measures.

Abstract: A method (2000), device (2200) and article of manufacture (2300) provide, in response to lexical pronunciation information, efficient generation of postlexical pronunciation information. A method is presented for providing, in response to a lexical pronunciation, efficient generation of a postlexical pronunciation, including the steps of: determining lexical phones, lexical features, and boundary information for a predetermined portion of text; and utilizing a pretrained neural network that was pretrained using lexical phones, postlexical phones, lexical features, and boundary information to generate a neural network hypothesis for a postlexical pronunciation of the predetermined portion of text.

Abstract: The present invention teaches a method (400), device and system (300) utilizing at least one of: mapping a sequence of phones to a sequence of articulatory features and utilizing prominence and boundary information, in addition to a predetermined set of rules for type, phonetic context, syntactic and prosodic context for phones to provide provide a system that generates segment durations efficiently with a small training set.

Abstract: A method (2000), device (2200) and article of manufacture (2300) provide, in response to orthographic information, efficient generation of a phonetic representation. The method provides for, in response to orthographic information, efficient generation of a phonetic representation, using the steps of: inputting an orthography of a word and a predetermined set of input letter features; utilizing a neural network that has been trained using automatic letter phone alignment and predetermined letter features to provide a neural network hypothesis of a word pronunciation.

Abstract: A method (400, 900, 1000, 1100), device (1205, 1306) and system (1207, 1308) provide memory-efficient encoding of the random-access lexicon for a text-to-speech synthesis system. The method generates word pronunciations based on efficient retrieval of stored pronunciation information and disambiguation information for an input word, by dividing the input word into a stem and a maximal suffix having a maximal suffix code and then generating at least one word pronunciation based on the stem and the maximal suffix.

Abstract: A method (400), device and system (300) provide, in response to linguistic information, efficient generation of a parametric representation of speech using a neural network.

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: A receiver (100) capable of synchronizing to a received signal (302) samples the received signals (302) at a plurality of sample points, and stores all occurrences of zero-crossings corresponding to the plurality of sample points. A processor (212) synchronizes the receiver (100) to the received signal (302) in response to the number of zero-crossings.