A High Quality Text-To-Speech System Composed of Multiple Neural Networks

While neural networks have been employed to handle several different text-to-speech tasks, ours is the first system to use neural networks throughout, for both linguistic and acoustic processing. We divide the text-to-speech task into three subtasks, a linguistic module mapping from text to a linguistic representation, an acoustic module mapping from the linguistic representation to speech, and a video module mapping from the linguistic representation to animated images. The linguistic module employs a letter-to-sound neural network and a postlexical neural network. The acoustic module employs a duration neural network and a phonetic neural network. The visual neural network is employed in parallel to the acoustic module to drive a talking head. The use of neural networks that can be retrained on the characteristics of different voices and languages affords our system a degree of adaptability and naturalness heretofore unavailable.

Text-To-Speech Conversion with Neural Networks: A Recurrent TDNN Approach

This paper describes the design of a neural network that performs the phonetic-to-acoustic mapping in a speech synthesis system. The use of a time-domain neural network architecture limits discontinuities that occur at phone boundaries. Recurrent data input also helps smooth the output parameter tracks. Independent testing has demonstrated that the voice quality produced by this system compares favorably with speech from existing commercial text-to-speech systems.

Generating Segment Durations in a Text-To-Speech System: A Hybrid Rule-Based/Neural Network Approach

A combination of a neural network with rule firing information from a rule-based system is used to generate segment durations for a text-to-speech system. The system shows a slight improvement in performance over a neural network system without the rule firing information. Synthesized speech using segment durations was accepted by listeners as having about the same quality as speech generated using segment durations extracted from natural speech.

Variation and Synthetic Speech

We describe the approach to linguistic variation taken by the Motorola speech synthesizer. A pan-dialectal pronunciation dictionary is described, which serves as the training data for a neural network based letter-to-sound converter. Subsequent to dictionary retrieval or letter-to-sound generation, pronunciations are submitted a neural network based postlexical module. The postlexical module has been trained on aligned dictionary pronunciations and hand-labeled narrow phonetic transcriptions. This architecture permits the learning of individual postlexical variation, and can be retrained for each speaker whose voice is being modeled for synthesis. Learning variation in this way can result in greater naturalness for the synthetic speech that is produced by the system.