A computational model of intonation for yorùbá text-to-speech synthesis:design and analysis

In this paper we present the design and analysis of an intonation model for text-to-speech (TTS) synthesis applications using a combination of Relational Tree (RT) and Fuzzy Logic (FL) technologies. The model is demonstrated using the Standard Yorùbá (SY) language. In the proposed intonation model, phonological information extracted from text is converted into an RT. RT is a sophisticated data structure that represents the peaks and valleys as well as the spatial structure of a waveform symbolically in the form of trees. An initial approximation to the RT, called Skeletal Tree (ST), is first generated algorithmically. The exact numerical values of the peaks and valleys on the ST is then computed using FL. Quantitative analysis of the result gives RMSE of 0.56 and 0.71 for peak and valley respectively. Mean Opinion Scores (MOS) of 9.5 and 6.8, on a scale of 1 - -10, was obtained for intelligibility and naturalness respectively.

The effects of word prediction and text-to-speech technologies on the narrative writing skills of students with specific learning disabilities

This study investigated the effects of word prediction and text-to-speech on the narrative composition writing skills of 6, fifth-grade Hispanic boys with specific learning disabilities (SLD). A multiple baseline design across subjects was used to explore the efficacy of word prediction and text-to-speech alone and in combination on four dependent variables: writing fluency (words per minute), syntax (T-units), spelling accuracy, and overall organization (holistic scoring rubric). Data were collected and analyzed during baseline, assistive technology interventions, and at 2-, 4-, and 6-week maintenance probes. ^ Participants were equally divided into Cohorts A and B, and two separate but related studies were conducted. Throughout all phases of the study, participants wrote narrative compositions for 15-minute sessions. During baseline, participants used word processing only. During the assistive technology intervention condition, Cohort A participants used word prediction followed by word prediction with text-to-speech. Concurrently, Cohort B participants used text-to-speech followed by text-to-speech with word prediction. ^ The results of this study indicate that word prediction alone or in combination with text-to-speech has a positive effect on the narrative writing compositions of students with SLD. Overall, participants in Cohorts A and B wrote more words, more T-units, and spelled more words correctly. A sign test indicated that these perceived effects were not likely due to chance. Additionally, the quality of writing improved as measured by holistic rubric scores. When participants in Cohort B used text-to-speech alone, with the exception of spelling accuracy, inconsequential results were observed on all dependent variables. ^ This study demonstrated that word prediction alone or in combination assists students with SLD to write longer, improved-quality, narrative compositions. These results suggest that word prediction or word prediction with text-to-speech be considered as a writing support to facilitate the production of a first draft of a narrative composition. However, caution should be given to the use of text-to-speech alone as its effectiveness has not been established. Recommendations for future research include investigating the use of these technologies in other phases of the writing process, with other student populations, and with other writing styles. Further, these technologies should be investigated while integrated into classroom composition instruction. ^

Evaluating parts-of-speech taggers for use in a text-to-scene conversion system

This paper presents parts-of-speech tagging as a first step towards an autonomous text-to-scene conversion system. It categorizes some freely available taggers, according to the techniques used by each in order to automatically identify word-classes. In addition, the performance of each identified tagger is verified experimentally. The SUSANNE corpus is used for testing and reveals the complexity of working with different tagsets, resulting in substantially lower accuracies in our tests than in those reported by the developers of each tagger. The taggers are then grouped to form a voting system to attempt to raise accuracies, but in no cases do the combined results improve upon the individual accuracies. Additionally a new metric, agreement, is tentatively proposed as an indication of confidence in the output of a group of taggers where such output cannot be validated.

The acoustic approach to speech correction

This paper reviews a study to determine if an auditory approach to speech correction can be of beneift to hearing impaired children who have become visually oriented.

Automatic prediction of emotions from text in Spanish for expressive speech synthesis in the chat domain

This paper describes a module for the prediction of emotions in text chats in Spanish, oriented to its use in specific-domain text-to-speech systems. A general overview of the system is given, and the results of some evaluations carried out with two corpora of real chat messages are described. These results seem to indicate that this system offers a performance similar to other systems described in the literature, for a more complex task than other systems (identification of emotions and emotional intensity in the chat domain).

A modular holistic approach to prosody modelling for Standard Yorùbá speech synthesis

This paper presents a novel prosody model in the context of computer text-to-speech synthesis applications for tone languages. We have demonstrated its applicability using the Standard Yorùbá (SY) language. Our approach is motivated by the theory that abstract and realised forms of various prosody dimensions should be modelled within a modular and unified framework [Coleman, J.S., 1994. Polysyllabic words in the YorkTalk synthesis system. In: Keating, P.A. (Ed.), Phonological Structure and Forms: Papers in Laboratory Phonology III, Cambridge University Press, Cambridge, pp. 293–324]. We have implemented this framework using the Relational Tree (R-Tree) technique. R-Tree is a sophisticated data structure for representing a multi-dimensional waveform in the form of a tree. The underlying assumption of this research is that it is possible to develop a practical prosody model by using appropriate computational tools and techniques which combine acoustic data with an encoding of the phonological and phonetic knowledge provided by experts. To implement the intonation dimension, fuzzy logic based rules were developed using speech data from native speakers of Yorùbá. The Fuzzy Decision Tree (FDT) and the Classification and Regression Tree (CART) techniques were tested in modelling the duration dimension. For practical reasons, we have selected the FDT for implementing the duration dimension of our prosody model. To establish the effectiveness of our prosody model, we have also developed a Stem-ML prosody model for SY. We have performed both quantitative and qualitative evaluations on our implemented prosody models. The results suggest that, although the R-Tree model does not predict the numerical speech prosody data as accurately as the Stem-ML model, it produces synthetic speech prosody with better intelligibility and naturalness. The R-Tree model is particularly suitable for speech prosody modelling for languages with limited language resources and expertise, e.g. African languages. Furthermore, the R-Tree model is easy to implement, interpret and analyse.

Medical free-text to concept mapping as an information retrieval problem

Concept mapping involves determining relevant concepts from a free-text input, where concepts are defined in an external reference ontology. This is an important process that underpins many applications for clinical information reporting, derivation of phenotypic descriptions, and a number of state-of-the-art medical information retrieval methods. Concept mapping can be cast into an information retrieval (IR) problem: free-text mentions are treated as queries and concepts from a reference ontology as the documents to be indexed and retrieved. This paper presents an empirical investigation applying general-purpose IR techniques for concept mapping in the medical domain. A dataset used for evaluating medical information extraction is adapted to measure the effectiveness of the considered IR approaches. Standard IR approaches used here are contrasted with the effectiveness of two established benchmark methods specifically developed for medical concept mapping. The empirical findings show that the IR approaches are comparable with one benchmark method but well below the best benchmark.

GMM based Bayesian approach to speech enhancement in signal transform domain

Considering a general linear model of signal degradation, by modeling the probability density function (PDF) of the clean signal using a Gaussian mixture model (GMM) and additive noise by a Gaussian PDF, we derive the minimum mean square error (MMSE) estimator. The derived MMSE estimator is non-linear and the linear MMSE estimator is shown to be a special case. For speech signal corrupted by independent additive noise, by modeling the joint PDF of time-domain speech samples of a speech frame using a GMM, we propose a speech enhancement method based on the derived MMSE estimator. We also show that the same estimator can be used for transform-domain speech enhancement.

GMM basedbayesian approach to speech enhancement in signal/transform domain

Considering a general linear model of signal degradation, by modeling the probability density function (PDF) of the clean signal using a Gaussian mixture model (GMM) and additive noise by a Gaussian PDF, we derive the minimum mean square error (MMSE) estimator.The derived MMSE estimator is non-linear and the linear MMSE estimator is shown to be a special case. For speech signal corrupted by independent additive noise, by modeling the joint PDF of time-domain speech samples of a speech frame using a GMM, we propose a speech enhancement method based on the derived MMSE estimator. We also show that the same estimator can be used for transform-domain speech enhancement.

A generalized Stein's estimation approach to speech enhancement based on perceptual criteria

We address the problem of speech enhancement using a risk- estimation approach. In particular, we propose the use the Stein’s unbiased risk estimator (SURE) for solving the problem. The need for a suitable finite-sample risk estimator arises because the actual risks invariably depend on the unknown ground truth. We consider the popular mean-squared error (MSE) criterion first, and then compare it against the perceptually-motivated Itakura-Saito (IS) distortion, by deriving unbiased estimators of the corresponding risks. We use a generalized SURE (GSURE) development, recently proposed by Eldar for MSE. We consider dependent observation models from the exponential family with an additive noise model,and derive an unbiased estimator for the risk corresponding to the IS distortion, which is non-quadratic. This serves to address the speech enhancement problem in a more general setting. Experimental results illustrate that the IS metric is efficient in suppressing musical noise, which affects the MSE-enhanced speech. However, in terms of global signal-to-noise ratio (SNR), the minimum MSE solution gives better results.

An efficient and robust pitch marking algorithm on the speech waveform for TD-PSOLA

In a Text-to-Speech system based on time-domain techniques that employ pitch-synchronous manipulation of the speech waveforms, one of the most important issues that affect the output quality is the way the analysis points of the speech signal are estimated and the actual points, i.e. the analysis pitchmarks. In this paper we present our methodology for calculating the pitchmarks of a speech waveform, a pitchmark detection algorithm, which after thorough experimentation and in comparison with other algorithms, proves to behave better with our TD-PSOLA-based Text-to-Speech synthesizer (Time- Domain Pitch-Synchronous Overlap Add Text to Speech System).

Corpus design for a unit selection TtS system with application to Bulgarian

In this paper we present the process of designing an efficient speech corpus for the first unit selection speech synthesis system for Bulgarian, along with some significant preliminary results regarding the quality of the resulted system. As the initial corpus is a crucial factor for the quality delivered by the Text-to-Speech system, special effort has been given in designing a complete and efficient corpus for use in a unit selection TTS system. The targeted domain of the TTS system and hence that of the corpus is the news reports, and although it is a restricted one, it is characterized by an unlimited vocabulary. The paper focuses on issues regarding the design of an optimal corpus for such a framework and the ideas on which our approach was based on. A novel multi-stage approach is presented, with special attention given to language and speaker dependent issues, as they affect the entire process. The paper concludes with the presentation of our results and the evaluation experiments, which provide clear evidence of the quality level achieved. © 2011 Springer-Verlag.