Add to ORKGA method for data-driven lexical adaptation on the basis of a limited number of acoustic training tokens is discussed. The method is closely related to pronunciation modeling techniques. A set of pronunciation variants is generated by forced alignment, followed by a step to select promising pronunciation candidates by using a ranking function. The method has been validated on a database consisting of short utterances (proper names) spoken by native and non-native speakers. In the case of 5 training tokens per word, an improvement of 10-30 percent relative could be obtained compared to the baseline. A number of possible improvements of this method are discussed as well. 1
While many studies have been focused on pronunciation modeling for improving word recognition, limit...
In this paper we describe a method for improving the performance of a continuous speech recognizer b...
Put in the most general terms, this dissertation addresses the problem of automatic recognition of n...
Contains fulltext : 76383.pdf (author's version ) (Open Access)Workshop, 14 septem...
To achieve a robust system the variation seen for different speaking styles must be handled. An inve...
This paper describes a method to improve speech recog-nition for non-native speech in a spoken dialo...
Due to pronunciation variation, many insertions and deletions of phones occur in spontaneous speech....
In this paper we present an approach to modelling pronuncia-tion variation, particularly for non-nat...
The general goal of this thesis is to improve the performance of state-of-the-art statistical automa...
International audienceText-to-Speech (TTS) systems rely on a grapheme-to-phoneme converter which is ...
This dissertation proposes to investigate the area of pronunciation modeling in speech synthesis. By...
In this paper, three different approaches to pronunciation modeling are investigated. Two existing p...
Where human beings can easily learn and adopt pronunciation variations, machines need training befor...
One of the challenges in automatic speech recognition is how to handle pronunciation variation. The ...
In many ways, the lexicon remains the Achilles heel of modern automatic speech recogniz-ers (ASRs). ...
While many studies have been focused on pronunciation modeling for improving word recognition, limit...
In this paper we describe a method for improving the performance of a continuous speech recognizer b...
Put in the most general terms, this dissertation addresses the problem of automatic recognition of n...
Contains fulltext : 76383.pdf (author's version ) (Open Access)Workshop, 14 septem...
To achieve a robust system the variation seen for different speaking styles must be handled. An inve...
This paper describes a method to improve speech recog-nition for non-native speech in a spoken dialo...
Due to pronunciation variation, many insertions and deletions of phones occur in spontaneous speech....
In this paper we present an approach to modelling pronuncia-tion variation, particularly for non-nat...
The general goal of this thesis is to improve the performance of state-of-the-art statistical automa...
International audienceText-to-Speech (TTS) systems rely on a grapheme-to-phoneme converter which is ...
This dissertation proposes to investigate the area of pronunciation modeling in speech synthesis. By...
In this paper, three different approaches to pronunciation modeling are investigated. Two existing p...
Where human beings can easily learn and adopt pronunciation variations, machines need training befor...
One of the challenges in automatic speech recognition is how to handle pronunciation variation. The ...
In many ways, the lexicon remains the Achilles heel of modern automatic speech recogniz-ers (ASRs). ...
While many studies have been focused on pronunciation modeling for improving word recognition, limit...
In this paper we describe a method for improving the performance of a continuous speech recognizer b...
Put in the most general terms, this dissertation addresses the problem of automatic recognition of n...