A method and system are provided for text-to-speech synthesis with personalized voice. The method includes receiving an incidental audio input ( 403 ) of speech in the form of an audio communication from an input speaker ( 401 ) and generating a voice dataset ( 404 ) for the input speaker ( 401 ). The method includes receiving a text input ( 411 ) at the same device as the audio input ( 403 ) and synthesizing ( 312 ) the text from the text input ( 411 ) to synthesized speech including using the voice dataset ( 404 ) to personalize the synthesized speech to sound like the input speaker ( 401 ). In addition, the method includes analyzing ( 316 ) the text for expression and adding the expression ( 315 ) to the synthesized speech. The audio communication may be part of a video communication ( 453 ) and the audio input ( 403 ) may have an associated visual input ( 455 ) of an image of the input speaker. The synthesis from text may include providing a synthesized image personalized to look like the image of the input speaker with expressions added from the visual input ( 455 ).

Method and system for text-to-speech synthesis with personalized voice

A system and method for porting of existing speech recognition solutions in a source language to a target language has been disclosed. The system envisaged by the present invention enables porting of a working speech recognition solution in the source language to a working system in the target language, thus minimising the development process and reusing existing speech recognition solution components to recognise multiple languages.

System and method for rapid prototyping of existing speech recognition solutions in different languages

Recognition of proper nouns by an automated speech recognition system is improved by augmenting the pronunciation of each proper noun or name in the natural language of the speech recognition system with at least one “native” pronunciation in another natural language. To maximize recognition, preferably the pronunciations are predicted based on information not available to the speech recognition system. Prediction of pronunciation may be based on a location derived from a telephone number or postal address associated with the name and the language or dialect spoken in the country or region of that location. The “native” pronunciation(s) may be added to a dictionary of the speech recognition system or directly to the grammar used for recognizing speech.

Recognition of proper nouns using native-language pronunciation

A system and method for generating synthetic speech, which operates in a computer implemented Text-To-Speech system. The system comprises at least a speaker database that has been previously created from user recordings, a Front-End system to receive an input text and a Text-To-Speech engine. The Front-End system generates multiple phonetic transcriptions for each word of the input text, and the TTS engine uses a cost function to select which phonetic transcription is the more appropriate for searching the speech segments within the speaker database to be concatenated and synthesized.

Systems and methods for selecting from multiple phonectic transcriptions for text-to-speech synthesis

The invention relates to pre-processing of a pronunciation dictionary for compression in a data processing device, the pronunciation dictionary comprising at least one entry, the entry comprising a sequence of character units and a sequence of phoneme units. According to one aspect of the invention the sequence of character units and the sequence of phoneme units are aligned using a statistical algorithm. The aligned sequence of character units and aligned sequence of phoneme units are interleaved by inserting each phoneme unit at a predetermined location relative to the corresponding character unit.

Method for compressing dictionary data

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

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

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

A databank produced according to the inventive method can be used to train a neural network to synthesize or recognise speeches. The trained neural network can be used to convert graphemes or letters of text into corresponding phonemes.

Horst-Udo Hain

Papers

Individualization of voice output by matching synthesized voice target voice

Assignment of phonemes to the graphemes producing them

Method for conditioning a database for automatic speech processing

Method for speech synthesis

Method of preparing database for automatic speech processing enables very simple generation of database contg. grapheme-phoneme association