Abstract: A method and apparatus for performing text-to-speech conversion in a client/server environment partitions an otherwise conventional text-to-speech conversion algorithm into two portions: a first “text analysis” portion, which generates from an original input text an intermediate representation thereof and a second “speech synthesis” portion, which synthesizes speech waveforms from the intermediate representation generated by the first portion (i.e., the text analysis portion) The text analysis portion of the algorithm is executed exclusively on a server while the speech synthesis portion is executed exclusively on a client which may be associated therewith. The client may comprise a hand-held device such as, for example, a cell phone, and the intermediate representation of the input text advantageously comprises at least a sequence of phonemes representative of the input text.

Abstract: A method and system for selecting formant trajectories based on input speech and corresponding text data. The input speech is analyzed to obtain formant candidates for the respective time frame. The text data corresponding to the input speech is converted into a sequence of phonemes which are then time aligned such that each phoneme is temporally labeled with a corresponding segment of the input speech. Nominal formant frequencies are assigned to a center timing point of each phoneme and target formant trajectories are generated for each time frame by interpolating the nominal formant frequencies between adjacent phonemes. For each time frame, at least one formant candidate that is closest to the corresponding target formant trajectories is selected according to a minimum cost factor. The selected formant candidates are output for storage or further processing in subsequent speech applications.

Abstract: A method and apparatus for performing text-to-speech conversion in a client/server environment partitions an otherwise conventional text-to-speech conversion algorithm into two portions: a first “text analysis” portion, which generates from an original input text an intermediate representation thereof; and a second “speech synthesis” portion, which synthesizes speech waveforms from the intermediate representation generated by the first portion (i.e., the text analysis portion). The text analysis portion of the algorithm is executed exclusively on a server while the speech synthesis portion is executed exclusively on a client which may be associated therewith. The client may comprise a hand-held device such as, for example, a cell phone, and the intermediate representation of the input text advantageously comprises at least a sequence of phonemes representative of the input text.

Abstract: Multiple, yet plausible, pronunciations of a proper name are generated based on one or more potential language origins of the name, and based further on the context in which the name is being spoken—namely, on characteristics of the population of potential speakers. Conventional techniques may be employed to identify likely candidates for the language origin of the name, and the characteristics of the speaker population on which the generation of the pronunciations is further based may comprise, for example, the national origin of the speakers, the purpose of the speech, the geographical location of the speakers, or the general level of sophistication of the speaker population.

Abstract: A system and method are provided for automatically computing local pitch contours from textual input to produce pitch contours that closely mimic those found in natural speech. The methodology of the invention incorporates parameterized equations whose parameters can be estimated directly from natural speech recordings. That methodology incorporates a model based on the premise that pitch contours instantiating a particular pitch contour class can be described as distortions in the temporal and frequency domains of a single, underlying contour. After the nature of the pitch contour for different pitch contour classes has been established, a pitch contour can be predicted that closely models a natural speech contour for a synthetic speech utterance by adding the individual contours of the different intonational classes and adjusting the boundaries of these to match the boundaries of the adjacent intonation curves.

Abstract: A speech synthesis method employs an acoustic element database that is established from phonetic sequences occurring in an interval of a speech signal. In establishing the database, trajectories are determined for each of the phonetic sequences containing a phonetic segment that corresponds to a particular phoneme. A tolerance region is then identified based on a concentration of trajectories that correspond to different phoneme sequences. The acoustic elements for the database are formed from portions of the phonetic sequences by identifying cut points in the phonetic sequences which correspond to time points along the respective trajectories proximate the tolerance region. In this manner, it is possible to concatenate the acoustic elements having a common junction phonemes such that perceptible discontinuities at the junction phonemes are minimized. Computationally simple and fast methods for determining the tolerance region are also disclosed.

Abstract: A real-time predictive speech synthesizer produces an artificial speech signal from pitch period segmented codes. Responsive to the predictive parameters of the currently occurring pitch period, preceding speech samples, and the adjusted excitation signal of the current pitch period, a prescribed set of current pitch period speech samples are generated in regularly spaced time periods. In the intervals between spaced time periods, prescribed components of the excitation level adjustment signal of the next successive pitch period are formed from the prediction parameters of the next successive pitch period, the preceding speech samples, and the next successive pitch period excitation signal. After the current pitch period final spaced time period, the formed components are combined with the next successive pitch period energy signal to produce the next successive pitch period excitation level adjustment signal.