Error detection of grapheme-to-phoneme conversion in text-to-speech synthesis using speech signal and lexical context - Archive ouverte HAL Access content directly
Conference Papers Year : 2017

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

(1, 2) , (1) , (2)
1
2

Abstract

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.
Fichier principal
Vignette du fichier
kv_asru17.pdf (124.8 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01585770 , version 1 (12-09-2017)

Identifiers

Cite

Kévin Vythelingum, Yannick Estève, Olivier Rosec. Error detection of grapheme-to-phoneme conversion in text-to-speech synthesis using speech signal and lexical context. 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), Dec 2017, Okinawa, Japan. ⟨10.1109/ASRU.2017.8269004⟩. ⟨hal-01585770⟩
429 View
694 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More