Error detection of grapheme-to-phoneme conversion in text-to-speech synthesis using speech signal and lexical context

In unit selection text-to-speech synthesis, voice creation involved a phonemic transcription of read speech. This is produced by an automatic grapheme-to-phoneme conversion of the text read, followed by a manual correction. Although grapheme-to-phoneme conversion makes few errors, the manual correction is time consuming as every generated phoneme should be checked. We propose a method to automatically detect grapheme-to-phoneme conversion errors by comparing contrastives phonemisation hypothesis. A lattice-based forced alignment system is implemented, allowing for signal-dependent phonemisation. We implement also a sequence-to-sequence neural network model to obtain a context-dependent grapheme-to-phoneme conversion. On a French dataset, we show that we can detect to 86.3% of the errors made by a commercial grapheme-to-phoneme system. Moreover, the amount of data annotated as erroneous is kept under 10% of the total evaluation data. The time spent for phoneme manual checking can thus been drastically reduced without decreasing significantly the phonemic transcription quality.