Journal ArticleDOI
Vocal tract normalization equals linear transformation in cepstral space
Michael Pitz,Hermann Ney +1 more
Reads0
Chats0
TLDR
In this paper, the Jacobian determinant of the transformation matrix is computed analytically for three typical warping functions and it is shown that the matrices are diagonal dominant and thus can be approximated by quindiagonal matrices.Abstract:
Vocal tract normalization (VTN) is a widely used speaker normalization technique which reduces the effect of different lengths of the human vocal tract and results in an improved recognition accuracy of automatic speech recognition systems. We show that VTN results in a linear transformation in the cepstral domain, which so far have been considered as independent approaches of speaker normalization. We are now able to compute the Jacobian determinant of the transformation matrix, which allows the normalization of the probability distributions used in speaker-normalization for automatic speech recognition. We show that VTN can be viewed as a special case of Maximum Likelihood Linear Regression (MLLR). Consequently, we can explain previous experimental results that improvements obtained by VTN and subsequent MLLR are not additive in some cases. For three typical warping functions the transformation matrix is calculated analytically and we show that the matrices are diagonal dominant and thus can be approximated by quindiagonal matrices.read more
Citations
More filters
Proceedings ArticleDOI
Cross-lingual frame selection method for polyglot speech synthesis
TL;DR: Evaluation results show that good performance regarding similarity (speaker identity) and naturalness (speech quality) can be achieved with the proposed method.
Proceedings ArticleDOI
Para-Linguistic Information Represented as Distortion of the Acoustic Universal Structure In Speech
TL;DR: Results showed that the structural size can be interpreted as magnitude of articulatory efforts made in speech production.
Acoustic model and language model adaptation for a mobile dictation service
TL;DR: In this work, performance of the TKK speech recognition system has been evaluated on law-related speech recorded on a mobile phone with the Mobi-Dic client application and language model adaptation was not able to significantly improve performance.
Dissertation
Estudio y modelización acústica del habla espontanea en diálogos hombre/máquina y entre personas
Rodríguez Fuentes,Luis Javier +1 more
TL;DR: In this article, a nuevo esquema de anotacion de fenomenos de habla espontanea, asi como su aplicacion a two bases of data, one ligada a una tarea and formada by dialogos hombre-maquina, and the other completamente generica and formado by dialogueos naturales entre personas.
Journal ArticleDOI
Speaker adaptation techniques for speech recognition using probabilistic models
TL;DR: A survey of previous research into speaker adaptation techniques focusing particularly on maximum a posteriori (MAP) parameter estimation, maximum likelihood linear regression (MLLR), and eigenvoices is presented.
References
More filters
Journal ArticleDOI
Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences
S. Davis,Paul Mermelstein +1 more
TL;DR: In this article, several parametric representations of the acoustic signal were compared with regard to word recognition performance in a syllable-oriented continuous speech recognition system, and the emphasis was on the ability to retain phonetically significant acoustic information in the face of syntactic and duration variations.
Journal ArticleDOI
Perceptual linear predictive (PLP) analysis of speech
TL;DR: A new technique for the analysis of speech, the perceptual linear predictive (PLP) technique, which uses three concepts from the psychophysics of hearing to derive an estimate of the auditory spectrum, and yields a low-dimensional representation of speech.
Journal ArticleDOI
Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models
TL;DR: An important feature of the method is that arbitrary adaptation data can be used—no special enrolment sentences are needed and that as more data is used the adaptation performance improves.
Journal ArticleDOI
Maximum likelihood linear transformations for HMM-based speech recognition
TL;DR: The paper compares the two possible forms of model-based transforms: unconstrained, where any combination of mean and variance transform may be used, and constrained, which requires the variance transform to have the same form as the mean transform.
BookDOI
Acoustical and environmental robustness in automatic speech recognition
TL;DR: This dissertation describes a number of algorithms developed to increase the robustness of automatic speech recognition systems with respect to changes in the environment, including the SNR-Dependent Cepstral Normalization, (SDCN) and the Codeword-Dependent Cep stral normalization (CDCN).