A text processing system for processing multi-lingual text for a speech synthesizer includes a first language dependent module for performing at least one of text and prosody analysis on a portion of input text comprising a first language. A second language dependent module performs at least one of text and prosody analysis on a second portion of input text comprising a second language. A third module is adapted to receive outputs from the first and second dependent module and performs prosodic and phonetic context abstraction over the outputs based on multi-lingual text.

Front-end architecture for a multi-lingual text-to-speech system

A speech synthesizer is provided that concatenates stored samples of speech units without modifying the prosody of the samples. The present invention is able to achieve a high level of naturalness in synthesized speech with a carefully designed training speech corpus by storing samples based on the prosodic and phonetic context in which they occur. In particular, some embodiments of the present invention limit the training text to those sentences that will produce the most frequent sets of prosodic contexts for each speech unit. Further embodiments of the present invention also provide a multi-tier selection mechanism for selecting a set of samples that will produce the most natural sounding speech.

Method and apparatus for speech synthesis without prosody modification

Automatic generation of synthesis units and prosodic information for Chinese concatenative synthesis

This paper examines how people communicate with computers using speech. Automatic speech recognition (ASR) transforms speech into text, while automatic speech synthesis [or text-to-speech (TTS)] performs the reverse task. ASR has been largely developed based on speech coding theory, while simulating certain spectral analyses performed by the ear. Typically, a Fourier transform is employed, but following the auditory Bark scale and simplifying the spectral representation with a decorrelation into cepstral coefficients. Current ASR provides good accuracy and performance on limited practical tasks, but exploits only the most rudimentary knowledge about human production and perception phenomena. The popular mathematical model called the hidden Markov model (HMM) is examined; first-order HMMs are efficient but ignore long-range correlations in actual speech. Common language models use a time window of three successive words in their syntactic-semantic analysis. Speech synthesis is the automatic generation of a speech waveform, typically from an input text. As with ASR, TTS starts from a database of information previously established by analysis of much training data, both speech and text. Previously analyzed speech is stored in small units in the database, for concatenation in the proper sequence at runtime. TTS systems first perform text processing, including "letter-to-sound" conversion, to generate the phonetic transcription. Intonation must be properly specified to approximate the naturalness of human speech. Modern synthesizers using large databases of stored spectral patterns or waveforms output highly intelligible synthetic speech, but naturalness remains to be improved.

Interacting with computers by voice: automatic speech recognition and synthesis

We present an effective generic communicating rational agent, ARTIMIS, and its application to cooperative spoken dialogue. ARTIMIS ' kernel is the implementation of a formal theory of interaction. This theory involves a set of generic axioms which models, in a homogeneous logical framework, principles of rational behaviour, communication, and cooperation. The theory is interpreted by a specifically designed reasoning engine. When applied to the context of natural dialogue, ARTIMIS includes specialised components for speech and natural language processing.

/pdf/artimis-natural-dialogue-meets-rational-agency-kqxaqf8k65.pdf

ARTIMIS: natural dialogue meets rational agency

Work done at CNET on developing multilingual concatenation-based PSOLA TTS (text-to-speech) systems well adapted to their use in interactive voice services is reviewed. A new system architecture SYC (synthesis control) has been specifically designed for assuring real-time, multichannel, and interactive operation. The data control and transfer methods within the system are now fully independent of the content of the modules, allowing for an easy adaptation of the system to multilingual operation. A complete version has been developed for German, and mixed systems have been elaborated for Italian and English in collaboration with other laboratories, using the same PSOLA synthesizer as for French. The overall quality of the French version has been improved both in naturalness (optimization of the linguistico-prosodic processings) and in articulation accuracy (use of longer units to be concatenated). An automatic segmentation procedure has been developed for the rapid building of new repertories of speech from recordings by new speakers, i.e., for the creation of new synthetic voices. >

O. Boeffard

Papers

Multilingual PSOLA text-to-speech system