Work

Interdependence of Language Models and Discriminative Training

Year: 2007

Type: conference-paper

Abstract: In this paper, the interdependence of language models and discriminative training for large vocabulary speech recognition is investigated. In addition, a constrained recognition approach using word graphs is presented for the efficient determination of alternative word sequences for discriminative training. Experiments have been carried out on the ARPA Wall Street Journal corpus. The recognition results for MMI training show a significant dependence on the context length of the language model used for training. Best results were obtained using a unigram language model for MMI training. No significant correlation has been observed between the language model choice for training and recognition. 1.

Source: RWTH Publications (RWTH Aachen)

Authors: Ralf Schlüter, Boris Müller, Frank Wessel, Hermann Ney

Institution: RWTH Aachen University

Language: English

Topic: Speech Recognition and Synthesis

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: Siemens, Advanced Research Projects Agency

OpenAlex ID: W1495239264

FWCI: 1.735

Cites: 11

Cited by: 31

Related to: 20