Textual Data Selection for Language Modelling in the Scope of Automatic Speech Recognition

Freha Mezzoudj 1 David Langlois 2, * Denis Jouvet 3 Abdelkader Benyettou 1
* Corresponding author
2 SMarT - Statistical Machine Translation and Speech Modelization and Text
LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
3 MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication
Inria Nancy - Grand Est, LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : The language model is an important module in many applications that produce natural language text, in particular speech recognition. Training of language models requires large amounts of textual data that matches with the target domain. Selection of target domain (or in-domain) data has been investigated in the past. For example [1] has proposed a criterion based on the difference of cross-entropy between models representing in-domain and non-domain-specific data. However evaluations were conducted using only two sources of data, one corresponding to the in-domain, and another one to generic data from which sentences are selected. In the scope of broadcast news and TV shows transcription systems, language models are built by interpolating several language models estimated from various data sources. This paper investigates the data selection process in this context of building interpolated language models for speech transcription. Results show that, in the selection process, the choice of the language models for representing in-domain and non-domain-specific data is critical. Moreover, it is better to apply the data selection only on some selected data sources. This way, the selection process leads to an improvement of 8.3 in terms of perplexity and 0.2% in terms of word-error rate on the French broadcast transcription task.
Document type :
Conference papers
Complete list of metadatas

Cited literature [28 references]  Display  Hide  Download

https://hal.inria.fr/hal-01184192
Contributor : Denis Jouvet <>
Submitted on : Thursday, August 13, 2015 - 11:17:06 AM
Last modification on : Tuesday, December 18, 2018 - 4:38:02 PM
Long-term archiving on: Saturday, November 14, 2015 - 10:15:07 AM

File

ICNLSP15-V8-final-aug2015.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01184192, version 1

Collections

Citation

Freha Mezzoudj, David Langlois, Denis Jouvet, Abdelkader Benyettou. Textual Data Selection for Language Modelling in the Scope of Automatic Speech Recognition. International Conference on Natural Language and Speech Processing, Oct 2015, Alger, Algeria. ⟨hal-01184192⟩

Share

Metrics

Record views

440

Files downloads

464