Today, the vocabulary size for language models in large vocabulary speech recognition is typically several hundreds of thousands of words. While this is already sufficient in some applications, the out-of-vocabulary words are still limiting the usability in others. In agglutinative languages the vocabulary for conversational speech should include millions of word forms to cover the spelling variations due to colloquial pronunciations, in addition to the word compounding and inflections. Very large vocabularies are also needed, for example, when the recognition of rare proper names is important.Peer reviewe
A regular automatic speech recognizer works with a so-called recognition lexicon. This lexicon conta...
In state-of-the-art large vocabulary automatic recognition systems, a large statistical language mod...
The use of variable-width features (prosodics, broad structural information etc.) in large vocabular...
We study class-based n-gram and neural network language models for very large vocabulary speech reco...
Speech technology applications for major languages are becoming widely available, but for many other...
We study continuous speech recognition based on sub-word units found in an unsupervised fashion. For...
One particular problem in large vocabulary continuous speech recognition for low-resourced languages...
It is practically impossible to build a word-based lexicon for speech recognition in agglutinative l...
Automatic speech recognition systems are devices or computer programs that convert human speech into...
In this paper we report on our activities in multilingual, speakerindependent, large vocabulary cont...
Automatic speech recognition systems are devices or computer programs that convert human speech into...
Automatic speech recognition will soon be a part of everyday life. Even today many people use the sp...
In the automatic speech recognition of agglutinative and morphologically rich languages, the recogni...
This paper presents results for large vocabulary continuous speech recognition (LVCSR) in Swedish. W...
In the speech recognition of highly inflecting or compounding languages, the traditional word-based ...
A regular automatic speech recognizer works with a so-called recognition lexicon. This lexicon conta...
In state-of-the-art large vocabulary automatic recognition systems, a large statistical language mod...
The use of variable-width features (prosodics, broad structural information etc.) in large vocabular...
We study class-based n-gram and neural network language models for very large vocabulary speech reco...
Speech technology applications for major languages are becoming widely available, but for many other...
We study continuous speech recognition based on sub-word units found in an unsupervised fashion. For...
One particular problem in large vocabulary continuous speech recognition for low-resourced languages...
It is practically impossible to build a word-based lexicon for speech recognition in agglutinative l...
Automatic speech recognition systems are devices or computer programs that convert human speech into...
In this paper we report on our activities in multilingual, speakerindependent, large vocabulary cont...
Automatic speech recognition systems are devices or computer programs that convert human speech into...
Automatic speech recognition will soon be a part of everyday life. Even today many people use the sp...
In the automatic speech recognition of agglutinative and morphologically rich languages, the recogni...
This paper presents results for large vocabulary continuous speech recognition (LVCSR) in Swedish. W...
In the speech recognition of highly inflecting or compounding languages, the traditional word-based ...
A regular automatic speech recognizer works with a so-called recognition lexicon. This lexicon conta...
In state-of-the-art large vocabulary automatic recognition systems, a large statistical language mod...
The use of variable-width features (prosodics, broad structural information etc.) in large vocabular...