On semi-supervised LF-MMI training of acoustic models with limited data - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2020

On semi-supervised LF-MMI training of acoustic models with limited data

Abstract

This work investigates semi-supervised training of acoustic models (AM) with the lattice-free maximum mutual information (LF-MMI) objective in practically relevant scenarios with a limited amount of labeled in-domain data. An error detection driven semi-supervised AM training approach is proposed, in which an error detector controls the hypothesized transcriptions or lattices used as LF-MMI training targets on additional unlabeled data. Under this approach, our first method uses a single error-tagged hypothesis whereas our second method uses a modified supervision lattice. These methods are evaluated and compared with existing semi-supervised AM training methods in three different matched or mismatched, limited data setups. Word error recovery rates of 28 to 89% are reported.
Fichier principal
Vignette du fichier
is20_wsl_310720.pdf (165.03 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-02907924 , version 1 (31-07-2020)

Identifiers

  • HAL Id : hal-02907924 , version 1

Cite

Imran Sheikh, Emmanuel Vincent, Irina Illina. On semi-supervised LF-MMI training of acoustic models with limited data. INTERSPEECH 2020, Oct 2020, Shanghai, China. ⟨hal-02907924⟩
238 View
625 Download

Share

Gmail Mastodon Facebook X LinkedIn More