L.M. Arslan, Speaker transformation algorithm using segmental codebooks (STASC), Speech Communication, 1999, 28:211-226.  Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
A new Multi-Speaker Formant Synthesizer that applies.. - Conversion Techniques.. (2001) (Correct)
....variability problem. 1. Introduction One of the lacks of current synthesizers is that they are commonly judged as monotonous and boring. Recent researches try to improve prosodic models and to add variability to the voices. This variability includes emotions [1] 2] and speaker conversion [3] [4]. Speaker variability is important when the synthesizer is used in a talker machine or as a reader because users can choose the voice they like. In information retrieval systems, it has been proved that a change of the speaker is more effective when transmitting the message, if the information to ....
L.M. Arslan. "Speaker Transformation Algorithm using Segmental Codebooks (STASC)" Speech Communication, vol.28, pp 211-226. 1999
Design And Evaluation Of A Voice Conversion Algorithm Based On.. - Kain, Macon (2001) (Correct)
....to the naturalness of speech and may also contain vital speaker information, apparent in the test results in Section 3 for the set of male speakers. To address this, several authors proposed ways of improving VC beyond changing the LPC spectral envelope by also changing the LPC residual. In [11], the authors formulated a codebook based transformation of the source excitation characteristics by using a weighted combination of codeword filters, which were derived from the average source and target codeword excitation spectra. In [12] the excitation is modeled by a long delay neural net ....
Levent M. Arslan, "Speaker transformation algorithm using segmental codebooks (STASC)," Speech Communication, vol. 28, no. 3, pp. 211--226, 1999.
Subjective Assessment Of Frequency Bands - For Perception Of (2002) Self-citation (Arslan) (Correct)
....range. Our research is focused on voice conversion which can be defined as the task of transforming the characteristics of a speech signal to make it sound as if it had been uttered by another speaker [1] Codebook mapping using different acoustical features such as line spectral frequencies [1,2], formant frequencies [3] and harmonic plus noise model parameters [4] is a common method for voice conversion. Voice conversion has many applications in speech synthesis and speaker adaptation especially in dubbing, looping, Karaoke, email and screen reading. For speech synthesis, generation ....
....Karaoke, email and screen reading. For speech synthesis, generation of speech by multiple speakers is necessary but the cost of employing more speakers is high. One algorithm used for high quality voice conversion is Speaker Transformation Algorithm using Segmental Codebooks (STASC) proposed in [2]. Basically this algorithm consists of two steps: training and transformation. These steps have been modified and improved using subband based techniques as explained in detail in [1] The results of the experiments presented in this paper will be used in further improvement of subband based ....
Arslan, L.M., "Speaker Transformation Algorithm using Segmental Codebooks (STASC)", Speech Communication 28 (1999).
Subband Based Voice Conversion - Levent (2002) Self-citation (Arslan) (Correct)
....without the need to generate and process a separate TTS database for each speaker. Codebook mapping is a general strategy for obtaining oneto one correspondence between the source and the target acoustical space. Previous research on voice conversion employing codebook based methods include [1], 2] and [3] The acoustic spaces of the source and target speaker are represented using acoustical features such as formant frequencies [4] LPC cepstrum coefficients, Line Spectral Frequencies (LSFs) 5] and harmonic plus noise model parameters [6] In this study, we investigate the use of ....
.... cepstrum coefficients, Line Spectral Frequencies (LSFs) 5] and harmonic plus noise model parameters [6] In this study, we investigate the use of Discrete Wavelet Transform (DWT) and subband processing as a modification to the Speaker Transformation Algorithm Using Segmental Codebooks (STASC) [1] as well as implementing a VCS system using both STASC and the proposed method. In STASC, voice conversion is performed in two steps: Training and Transformation. The training data consist of the same sentences uttered by both source and target speakers. The sentences must be phonetically balanced ....
Arslan, L.M., "Speaker Transformation Algorithm using Segmental Codebooks (STASC)", Speech Communication 28 (1999), pp. 211-226.
Voice Morphing Using the Generative Topographic Mapping - Orphanidou, Moroz, Roberts (Correct)
No context found.
L.M. Arslan, Speaker transformation algorithm using segmental codebooks (STASC), Speech Communication, 1999, 28:211-226.
A Phonetic Vocoder For Finnish - Kivimäki, Lahti, Koppinen (Correct)
No context found.
L.M. Arslan, \Speaker transformation algorithm using segmental codebook (STASC)", Speech Communication Journal, No. 28, February 1999.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC