Using privacy-transformed speech in the automatic speech recognition acoustic model training - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2020

Using privacy-transformed speech in the automatic speech recognition acoustic model training

Askars Salimbajevs
  • Function : Author
  • PersonId : 1068872

Abstract

Automatic Speech Recognition (ASR) requires huge amounts of real user speech data to reach state-of-the-art performance. However, speech data conveys sensitive speaker attributes like identity that can be inferred and exploited for malicious purposes. Therefore, there is a interest in collection of the anonymized speech data that is processed by some voice conversion method. In this paper we evaluate one of voice conversion methods on Latvian speech data and also investigate if privacy-transformed data can be used to improve ASR acoustic models. Results show effectiveness of voice conversion against state-of-the-art speaker verification models on Latvian speech and effectiveness of using privacy-transformed data in ASR training.
Fichier principal
Vignette du fichier
Voice_privacy_transform_ASR.pdf (161.43 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-02907056 , version 1 (27-07-2020)

Identifiers

  • HAL Id : hal-02907056 , version 1

Cite

Askars Salimbajevs. Using privacy-transformed speech in the automatic speech recognition acoustic model training. 9th International Conference on Human Language Technologies - the Baltic Perspective (Baltic HLT 2020), Sep 2020, Kaunas, Lithuania. ⟨hal-02907056⟩
74 View
214 Download

Share

Gmail Mastodon Facebook X LinkedIn More