Translating Dislocations or Parentheticals: Investigating the Role of Prosodic Boundaries for Spoken Language Translation from French into English - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Translating Dislocations or Parentheticals: Investigating the Role of Prosodic Boundaries for Spoken Language Translation from French into English

Résumé

This paper examines some of the effects of prosodic boundaries on ASR outputs and Spoken Language Translations into English for two competing French structures ("c'est" dislocation vs. "c'est" parentheticals). One native speaker of French read 104 test sentences that were then submitted to two systems. We compared the outputs of two toolkits, SYSTRAN Pure Neural Server (SPNS9) (Crego et al., 2016) and Whisper. For SPNS9, we compared the translation of the text file used for the reading with the translation of the transcription generated through Vocapia ASR. We also tested the transcription engine for speech recognition uploading an MP3 file and used the same procedure for AI Whisper's Web-scale Supervised Pretraining for Speech Recognition system (Radford et al., 2022). We reported WER for the transcription tasks and the BLEU scores for the different models. We evidenced the variability of the punctuation in the ASR outputs and discussed it in relation to the duration of the utterance. We discussed the effects of the prosodic boundaries. We described the status of the boundary in the speech-to-text systems, discussing the consequence for the neural machine translation of the rendering of the prosodic boundary by a comma, a full stop, or any other punctuation symbol. We used the reference transcript of the reading phase to compute the edit distance between the reference transcript and the ASR output. We also used textometric analyses with iTrameur (Fleury and Zimina, 2014) for insights into the errors that can be attributed to ASR or to Neural Machine translation.
Fichier principal
Vignette du fichier
2023.mtsummit-users.11.pdf (815.47 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Licence : CC BY - Paternité

Dates et versions

hal-04298775 , version 1 (23-11-2023)

Licence

Paternité

Identifiants

  • HAL Id : hal-04298775 , version 1

Citer

Nicolas Ballier, Behnoosh Namdarzadeh, Maria Zimina, Jean-Baptiste Yunès. Translating Dislocations or Parentheticals: Investigating the Role of Prosodic Boundaries for Spoken Language Translation from French into English. Machine Translation Summit 2023, NLP2CT Lab, University of Macau; University of Macau; AAMT; MACETS, Sep 2023, Macau SAR, China, France. pp.119-131. ⟨hal-04298775⟩
34 Consultations
14 Téléchargements

Partager

Gmail Facebook X LinkedIn More