Skip to Main content Skip to Navigation
Conference papers

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

Imran Sheikh 1 Emmanuel Vincent 1 Irina Illina 1
1 MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication
Inria Nancy - Grand Est, LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
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.
Complete list of metadatas

Cited literature [27 references]  Display  Hide  Download

https://hal.inria.fr/hal-02907924
Contributor : Emmanuel Vincent <>
Submitted on : Friday, July 31, 2020 - 3:19:23 PM
Last modification on : Monday, August 3, 2020 - 9:35:27 AM

File

is20_wsl_310720.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02907924, version 1

Collections

Citation

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⟩

Share

Metrics

Record views

61

Files downloads

41