Etude pour l'amélioration de la parole codée par transformation en paquets de framelette serrée (Study for improving the coded speech by tight framelet packet transform) [in French]
نویسندگان
چکیده
Study for improving the coded speech by tight framelet packet transform In this paper we propose to study the performance of a new time-frequency representation called the tight framelet packets transform in speech coding. For this, we performed a comparative study with the wavelet packets transform. Performance evaluation was done using various objective criteria : the coding gain, the normalized root mean square error, the peak signal to noise ratio, the segmental signal to noise ratio, the frequency weighted segmental signal to noise ratio and PESQ. The obtained results show that the speech coding by framelet packets transform provides a higher quality than that using wavelet packet transform. MOTS-CLÉS : Codage de la parole, frame d’ondelette, transformation en paquets de framelette, transformation en paquets d’ondelette.
منابع مشابه
A low-delay transform domain approach to trellis coded quantization
In this paper we propose a new transform domain coding technique called transform trellis coded quantization (TTCQ) that is based on the trellis coded quantization technique recently proposed where Ungerboeck’s amplitude modulation trellises and set partitioning ideas are used for source coding. We combine the proposed technique with a transform domain formulation for small frame sizes obtainin...
متن کاملSatellite Image Deconvolution Using Complex Wavelet Packets
The deconvolution of blurred and noisy satellite images is an ill-posed inverse problem. The direct inversion leads to unacceptable noise amplification. Usually, either the problem is regularized during the inversion process, or the noise is filtered after deconvolution and decomposition in the wavelet transform domain. Herein, we have developed the second solution, by thresholding the coeffici...
متن کاملPronunciation variants across system configuration, language and speaking style
This contribution aims at evaluating the use of pronunciation variants for di erent recognition system con gurations, languages and speaking styles. This study is limited to the use of variants during speech alignment, given an orthographic transcription of the utterance and a phonemically represented lexicon, and is thus focused on the modeling capabilities of the acoustic word models. To meas...
متن کاملContribution à l'étude de la variabilité de la voix des personnes âgées en reconnaissance automatique de la parole (Contribution to the study of elderly people's voice variability in automatic speech recognition) [in French]
RÉSUMÉ L’utilisation de la reconnaissance vocale pour l’assistance à la vie autonome se heurte à la difficulté d’utilisation des systèmes de RAP qui ne sont pas prévus à la base pour la voix âgée. Pour caractériser les différences de comportement d’un système de reconnaissance entre les personnes âgées et non-âgées, nous avons étudié quels sont les phonèmes les moins bien reconnus en nous basan...
متن کاملImportance of Prosody in Swiss French Accent for Speech Synthesis
En français, l’accent standard et l’accent suisse sont proches. Les pronciations observées sont effectivement similaires à quelques exceptions près. En revanche, la prosodie suisse a un effet important sur la façon dont les accents sont perçus. Nous étudions l’effet de la prosodie sur la perception de l’accent suisse sur de la parole synthétique par des locuteurs français natifs. Nous utilisons...
متن کامل