In this paper, three different voicing features are studied as additional acoustic features for continuous speech recognition. The harmonic product spectrum based feature is extracted in frequency domain while the aut...
详细信息
In this paper, three different voicing features are studied as additional acoustic features for continuous speech recognition. The harmonic product spectrum based feature is extracted in frequency domain while the autocorrelation and the average magnitude difference based methods work in time domain. The algorithms produce a measure of voicing for each time frame. The voicing measure was combined with the standard Mel Frequency Cepstral Coefficients (MFCC) using linear discriminant analysis to choose the most relevant features. Experiments have been performed on small and large vocabulary tasks. The three different voicing measures combined with MFCCs resulted in similar improvements in word error rate: improvements of up to 14% on the small-vocabulary task and improvements of up to 6% on the large-vocabulary task relative to using MFCC alone with the same overall number of parameters in the system.
During the last few years, the statistical approach has found widespread use in machine translation, in particular for spoken language. In many comparative evaluations of automatic speech translation, the statistical ...
详细信息
During the last few years, the statistical approach has found widespread use in machine translation, in particular for spoken language. In many comparative evaluations of automatic speech translation, the statistical approach was found to be significantly superior to the existing conventional approaches. The paper will present the main components of a statistical machine translation system (such as alignment and lexicon models, training procedure, generation of the target sentence) and summarize the progress made so far. We will conclude with a roadmap for future research on spoken language translation.
This paper is based on the work carried out in the framework of the Verbmobil project, which is a limited-domain speech translation task (German-English). In the final evaluation, the statistical approach was found to...
详细信息
暂无评论