Siemens Aktiengesellschaft

Svox Ag

Horst-Udo Hain

Klaus Lukas

The voice of a synthesized voice output is individualized and matched to a user voice, the voice of a communication partner or the voice of a famous personality. In this way mobile terminals in particular can be originally individualized and text messages can be read out using a specific voice.

Individualization of voice output by matching synthesized voice target voice

A neural network can be trained for synthesizing or recognizing speech with the aid of a database produced by automatically matching graphemes and phonemes. First, graphemes and phonemes are matched for words which have the same number of graphemes and phonemes. Next, graphemes and phonemes are matched for words that have more graphemes than phonemes in a series of steps that combine graphemes with preceding phonemes. Then, graphemes and phonemes are matched for words that have fewer graphemes than phonemes. After each step, infrequent and unsuccessful matches made in the preceding step are are erased. After this process is completed, the database can be used to train the neural network and graphemes, or letters of a text can be converted into the corresponding phonemes with the aid of the trained neural network.

Method for conditioning a database for automatic speech processing

A method, an arrangement and a computer program synthesize speech by grapheme/phoneme conversion. In this case, a search is made for subwords of a given word in a database which contains phonetic transcriptions of words. If at least one subword of the given word is found in the database, a phonetic transcription registered in the database is selected for the subword found. In addition to the subword found, the given word has at least one further constituent, which is not registered in the database. This further constituent is phonetically transcribed with the aid of an OOV treatment, and the phonetic transcription of the subword found and the phonetic transcription of the further constituent are combined.

Method for speech synthesis

The assignment of phonemes to graphemes producing them in a lexicon having words (grapheme sequences) and their associated phonetic transcription (phoneme sequences) for the preparation of patterns for training neural networks for the purpose of grapheme-phoneme conversion is carried out with the aid of a variant of dynamic programming which is known as dynamic time warping (DTW).

Assignment of phonemes to the graphemes producing them

In a method for grapheme-phoneme conversion of a word which is not contained as a whole in a pronunciation lexicon, the word is firstly decomposed into subwords. The subwords are transcribed and chained. As a result, interfaces are formed between the transcriptions of the subwords. The phonemes at the interfaces must be changed frequently. Consequently, they are subjected to recalculation.

Growing community of inventors

Munich, Germany

Horst-Udo Hain