Developing Acoustic Models for Automatic Speech Recognition in Swedish

TL;DR

This study develops and evaluates Swedish acoustic models for speech recognition using hidden Markov models, phonetic modeling, and bigram language models, demonstrating significant performance improvements across diverse speaker groups.

Contribution

Introduces new acoustic models for Swedish speech recognition employing phonetic-level modeling and extensive experimentation with context models and language models.

Findings

Significant performance improvements over previous studies

Effective modeling across diverse speaker demographics

Enhanced system tuning with bigram language models

Abstract

This paper is concerned with automatic continuous speech recognition using trainable systems. The aim of this work is to build acoustic models for spoken Swedish. This is done employing hidden Markov models and using the SpeechDat database to train their parameters. Acoustic modeling has been worked out at a phonetic level, allowing general speech recognition applications, even though a simplified task (digits and natural number recognition) has been considered for model evaluation. Different kinds of phone models have been tested, including context independent models and two variations of context dependent models. Furthermore many experiments have been done with bigram language models to tune some of the system parameters. System performance over various speaker subsets with different sex, age and dialect has also been examined. Results are compared to previous similar studies showing a remarkable improvement.