Suresh Kumar Thakur* et al. / (IJAEST) INTERNATIONAL JOURNAL OF ADVANCED ENGINEERING SCIENCES AND TECHNOLOGIES Vol No.

8, Issue No. 2, 301 - 305

Study of Various kinds of Speech Synthesizer Technologies and Expression For Expressive Text To Speech Conversion System
Computer Science Engineering Rungta College Of Engineering & Technology Bhilai , India Sur25011986@gmail.com
Abstract This paper surveys various types of text to speech conversion methods. It discusses speech synthesis techniques and expression with various parameters, with the goal of identifying techniques most suitable to design and implementation of expressive Text to speech Conversion system. In this manuscript we define the techniques to generate the speech as output by taking the input as text. Text to Speech synthesis we can, in theory, mean any kind of method to generate of speech. Each of the synthesizers received the text and the necessary pronunciation corrections as input and had to generate speech output. All options of each synthesizer were set to their default values, to the settings recommended by the manufacturers. This was done for the following parameters pitch level, pitch dynamics, aspiration, rate, and volume.

Suresh Kumar Thakur

Information Technology Rungta College Of Engineering & Technology Bhilai , India kjsatao@rediffmail.com operating systems have included speech synthesizers since the early 1980s. Text to Speech synthesis we can, in theory, mean any kind of synthesizers f speech. For example, it can be the process in which a speech decoder generates the speech signal based on the parameters it has received through the transmission line, or it can be a procedure performed by a computer to estimate some kind of a presentation of the speech signal given a text input. Text-to-speech synthesis is a research field that has received a lot of attention and resources during the last couple of decades for excellent reasons. One of the most interesting ideas is the fact that a workable Text To Speech system, combined with a workable speech recognition device, would actually be an extremely efficient method for speech coding. It would provide incomparable compression ratio and flexible possibilities to choose the type of speech, the fundamental frequency along with its range, the rhythm of speech, and several other effects. Furthermore, if the content of a message needs to be changed, it is much easier to retype the text than to record the signal again. Of course there are also numerous speech synthesis applications that are closer to being available. For instance, a telephone inquiry system where the information is frequently updated can use Text to speech to deliver answers to the customers. Speech synthesizers are also important to the visually impaired and to those who have lost their ability to speak. Several other examples can be found in everyday life, such as listening to the messages and news instead of reading them, and using hands-free functions through a voice interface in a car, and so on. The most commonly used criteria for high-quality speech are intelligibility, naturalness and pleasantness. Since these are multidimensional factors that depend on each other, the comprehensive high quality is formed by the interaction of numerous details. Thus, the elimination of background noise, musical noise, mumbling, and the various pops and cracks, does not result in the ultimate quality, but the speech should also be made rich in nuances and it should carry information about the personality of the speaker. Moreover, it would be advisable to include in the speech some features that describe the emotional state of the speaker because this improves the naturalness and makes the speech more lively. The quality of

K.J. Satao

Keywords-survey; expressive; parameter; speech ; synthesizer (key words)

Synthesized speech can be created by concatenating pieces of recorded speech that are stored in a database. Systems differ in the size of the stored speech units; a system that stores phones or diphones provides the largest output range, but may lack clarity. For specific usage domains, the storage of entire words or sentences allows for high-quality output. Alternatively, a synthesizer can incorporate a model of the vocal tract and other human voice characteristics to create a completely synthetic voice output. The quality of a speech synthesizer is judged by its similarity to the human voice and by its ability to be understood. An intelligible text-to-speech program allows people with visual impairments or reading disabilities to listen to written works on a home computer. Many computer

IJ A
ISSN: 2230-7818

I. INTRODUCTION Speech synthesis is the artificial production of human speech. A computer system used for this purpose is called a speech synthesizer, and can be implemented in software or hardware. A text-to-speech (TTS) system converts normal language text into speech; other systems render symbolic linguistic representations like phonetic transcriptions into speech

@ 2011 http://www.ijaest.iserp.org. All rights Reserved.

ES

Page 301

Suresh Kumar Thakur* et al. / (IJAEST) INTERNATIONAL JOURNAL OF ADVANCED ENGINEERING SCIENCES AND TECHNOLOGIES Vol No. 8, Issue No. 2, 301 - 305

speech synthesizers can also be examined apart from speech quality as such, in which case we are interested in, for instance, the following facts: How much the operation of the synthesizer depends on the surrounding software or the operating system? How good is the performance of the synthesizer in the particular application for which it has been designed? How much memory does it require? Given the continuously increasing processing capacity, more and more complicated speech synthesizers can be used even on personal computers.

weaknesses, and the intended uses of a synthesis system will typically determine which approach is used. A. Concatenative synthesis Concatenative synthesis is based on the contaminative (or stringing together) of segments of recorded speech. Generally, concatenative synthesis produces the most natural-sounding synthesized speech. However, differences between natural variations in speech and the nature of the automated techniques for segmenting the waveforms sometimes result in audible glitches in the output. There are three main sub-types of concatenative synthesis Concatenative synthesis is a technique for synthesizing sounds by concatenating short samples of recorded sound (called units). The duration of the units is not strictly defined and may vary according to the implementation, roughly in the range of 10 milliseconds up to 1 second. It is used in speech synthesis and music sound synthesis to generate user-specified sequences of sound from a database built from recordings of other sequences. Concatenative text-to-speech systems can, in theory, produce very naturally sounding synthetic speech, since they simply join pre-recorded segments or units to form any sentence. In practice, several factors contribute for less perfect speech output quality. For instance, the choice of the best set of pre-recorded speech units that can be used as building blocks is a difficult task. Moreover, the concatenation of units recorded using different intonation or phonetic contexts may produce suboptimal results even if the set is reasonably complete and if some prosodic transformations are performed during the concatenation phase. [1] B. Unit selection synthesis

Fig. 1 Text to speech Conversion process

The most important qualities of a speech synthesis system are naturalness and intelligibility. Naturalness describes how closely the output sounds like human speech, while intelligibility is the ease with which the output is understood. The ideal speech synthesizer is both natural and intelligible. Speech synthesis systems usually try to maximize both characteristics. The two primary technologies for generating synthetic speech waveforms are concatenative synthesis and formant synthesis. Each technology has strengths and

IJ A
II. TEXT TO SPEECH SYNTHESIZER TECHNOLOGIES
ISSN: 2230-7818

The overall goal of the speech synthesis research community is to create natural sounding synthetic speech. To increase naturalness, researchers have been interested in synthesizing emotional speech for a long time. One way synthesized speech benefits from emotions is by delivering certain content in the right emotion (e.g. good news are delivered in a happy voice), therefore making the speech and the content more believable. Emotions can make the interaction with the computer more natural because the system reacts in ways that the user expects. Emotional speech synthesis is a step in this direction The implementation of emotions seems straightforward at first but a closer look reveals many difficulties in studying and implementing emotions. The difficulties start with the definition of emotions. Researchers agree that emotions are not as often thought of, just a subjective experience or feeling.

@ 2011 http://www.ijaest.iserp.org. All rights Reserved.

ES

Unit selection synthesis uses large databases of recorded speech. During database creation, each recorded utterance is segmented into some or all of the following: individual phones, diaphones, half-phones, syllables, morphemes, words, phrases, and sentences. Typically, the division into segments is done using a specially modified speech recognizer set to a "forced alignment" mode with some manual correction afterward, using visual representations such as the waveform and spectrogram. An index of the units in the speech database is then created based on the segmentation and acoustic parameters like the fundamental frequency (pitch), duration, position in the syllable, and neighboring phones. At runtime, the desired target utterance is created by determining the best chain of candidate units from the database (unit selection). This process is typically achieved using a specially weighted decision tree. Unit selection provides the greatest naturalness, because it applies only a small amount of digital signals processing (DSP) to the recorded speech. DSP often makes recorded speech sound less natural, although some systems use a small amount of signal processing at the point of concatenation to smooth the waveform. The output from the best unit-selection systems is often indistinguishable from real human voices, especially in Contexts for which the TTS system has been tuned. However,

Page 302

Suresh Kumar Thakur* et al. / (IJAEST) INTERNATIONAL JOURNAL OF ADVANCED ENGINEERING SCIENCES AND TECHNOLOGIES Vol No. 8, Issue No. 2, 301 - 305

maximum naturalness typically require unit-selection speech databases to be very large, in some systems ranging into the gigabytes of recorded data, representing dozens of hours of speech. Also, unit selection algorithms have been known to select segments from a place that results in less than ideal synthesis (e.g. minor words become unclear) even when a better choice exists in the database . The goal of unit selection is to provide a mechanism whereby segments of prerecorded speech are selected for synthesis. These segments are provided from a database. They may be parameterized in some form (LPC, HNM) or other or may be digitized speech samples.[2] C. Diphone synthesis Diphone synthesis uses a minimal speech database containing all the diphones (sound-to-sound transitions) occurring in a language. The number of diphones depends on the phonotactics of the language: for example, Spanish has about 800 diphones and German about 2500. In diphone synthesis, only one example of each diphone is contained in the speech database. At runtime, the target prosody of a sentence is superimposed on these minimal units by means of digital signal processing techniques such as linear predictive coding, PSOLA[4] or MBROLA[5]. The quality of the resulting speech is generally worse than that of unit-selection systems, but more natural-sounding than the output of formant synthesizers. Diphone synthesis suffers from the sonic glitches of concatenative synthesis and the robotic-sounding nature of formant synthesis, and has few of the advantages of either approach other than small size. As such, its use in commercial applications is declining, although it continues to be used in research because there are a number of freely available software implementations.

linguistic representation of the sentence to be spoken, e.g. appropriate word stress. In CTS, the situation is very different. There is no prior input text as such; rather a natural language generation (NLG) system generates some text from scratch. The level of naturalness of these systems can be very high because the variety of sentence types is limited, and they closely match the prosody and intonation of the original recordings. Because these systems are limited by the words and phrases in their databases, they are not general purpose and can only synthesize the combinations of words and phrases with which they have been pre programmed. The blending of words within naturally spoken language however can still cause problems unless the many variations are taken into account. For example, in non-chaotic dialects of English the "r" in words like "clear" /kli/ is usually only pronounced when the following word has a vowel as its first letter (e.g. "clear out" is realized as /kli t/). Likewise in French, many final consonants become no longer silent if followed by a word that begins with a vowel, an effect called liaison. This alternation cannot be reproduced by a simple word concatenation system, which would require additional complexity to be contextsensitive. E. Formant synthesis Synthesis does not use human speech samples at runtime. Instead, the synthesized speech output is created using additive synthesis and an acoustic model (physical modeling synthesis)[7]. Parameters such as fundamental frequency, voicing, and noise levels are varied over time to create a waveform of artificial speech. This method is sometimes called rules-based synthesis; however, many concatenative systems also have rules-based components. Many systems based on formant synthesis technology generate artificial, robotic sounding speech that would never be mistaken for human speech. However, maximum naturalness is not always the goal of a speech synthesis system, and formant synthesis systems have advantages over concatenative systems. Formant synthesized speech can be reliably intelligible, even at very high speeds, avoiding the acoustic glitches that commonly plague concatenative systems. High-speed synthesized speech is used by the visually impaired to quickly navigate computers using a screen reader. Formant synthesizers are usually smaller programs than concatenative systems because they do not have a database of speech samples. They can therefore be used in embedded systems, where memory and microprocessor power are especially limited. Because formant-based systems have complete control of all aspects of the output speech, a wide variety of prosodies and intonations can be output, conveying not just questions and statements, but a variety of emotions and tones of voice. In formant synthesis, the basic assumption is that the vocal tract transfer function can be satisfactorily modeled by simulating formant frequencies and formant amplitudes. The synthesis thus consists of the artificial reconstruction of the formant characteristics to be produced. This is done by exciting a set of resonators by a voicing source or noise generator to achieve the desired speech spectrum, and by controlling the excitation source to simulate both voicing and voice lessons.

Domain-specific synthesis concatenates pre-recorded words and phrases to create complete utterances. It is used in applications where the variety of texts the system will output is limited to a particular domain, like transit schedule announcements or weather reports.[6] The technology is very simple to implement, and has been in commercial use for a long time, in devices like talking clocks and calculators. The term text-to-speech (TTS) synthesis is used to describe the process of converting given raw text into synthetic speech. Concept-to-speech (CTS) is a term often used for speech synthesis where the input is not text, but rather a machine generated message. We can think of a TTS system as comprising two main components: text analysis and speech generation. The text analysis component has to resolve the ambiguities inherent in written text and produce a clean

IJ A
D. Domain-specific synthesis
ISSN: 2230-7818

Diphone-based speech synthesis has been researched for many years. Some of the most successful diphone systems have been concatenative [6]. Such systems can produce very intelligible synthetic speech, but tend not to sound completely natural. This lack of naturalness can be attributed, at least in part, to the limited set of units from which speech is chosen (typically ~2000 diphones), coupled with the need to prosodic ally modify the speech signal of each diphone.[3]

@ 2011 http://www.ijaest.iserp.org. All rights Reserved.

ES

Page 303

Suresh Kumar Thakur* et al. / (IJAEST) INTERNATIONAL JOURNAL OF ADVANCED ENGINEERING SCIENCES AND TECHNOLOGIES Vol No. 8, Issue No. 2, 301 - 305

The addition of a set of anti-resonators furthermore allows the simulation of nasal tract effects, fricatives and plosives.[4] The specification of about 20 or more such parameters can lead to a satisfactory restitution of the speech signal. The advantage of this technique is that its parameters are highly correlated with the production and propagation of sound in the oral tract. The main current drawback of this approach is that automatic techniques of specifying formant parameters are still largely unsatisfactory, and that consequently, the majority of parameters must still be manually optimized.[4] F. Articulatory synthesis Articulatory synthesis refers to computational techniques for synthesizing speech based on models of the human vocal tract and the articulation processes occurring there. The first articulatory synthesizer regularly used for laboratory experiments was developed at Haskins Laboratories in the mid1970s by Philip Rubin, Tom Baer, and Paul Mermelstein. This synthesizer, known as ASY, was based on vocal tract models developed at Bell Laboratories in the 1960s and 1970s by Paul Mermelstein, Cecil Coker, and colleagues. Until recently, articulatory synthesis models have not been incorporated into commercial speech synthesis systems. A notable exception is the NeXT-based system originally developed and marketed by Trillium Sound Research, a spinoff company of the University of Calgary, where much of the original research was conducted. Following the demise of the various incarnations of NeXT (started by Steve Jobs in the late 1980s and merged with Apple Computer in 1997), the Trillium software was published under the GNU General Public License, with work continuing as gnu speech. The system, first marketed in 1994, provides full articulatory-based text-to speech conversion using a waveguide or transmission-line analog of the human oral and nasal tracts controlled by Carr's "distinctive region model". In this note one aspect of articulatory synthesis will be considered-that of solving the differential equation describing acoustic (small amplitude), one-dimensional propagation of a pressure disturbance through a lossless tube with spatially varying cross section.

B.

IJ A
III.
ISSN: 2230-7818

Joy, happiness, humour Generally researchers have focused on more extreme forms of happiness, but still, here the findings reported are quite consistent between researchers. However, Stibbard points out that concerning voice quality the findings are contradictory. In detail Skinner (, emotions induced with music, subjects vocalised emotions through "ah", new subjects recognised the emotions), Cowan , acted speech, subjective enelysis and ster & Risberg , report that happiness gives an increase in pitch and pitch range. ster and Risberg noted a slow tempo, while Fnagy & Magdics, conversations, acted speech, music, subjective analysis, Hungarian) described it as lively. Davitz , subjects rated stimuli with 14 emotive adjectives) reported an increase in speech rate along with an increase in intensity, this intensity also being noted by Skinner . C.

EXPRESSION FOR DEVELOPING EXPRESSIVE TEXT TO SPEECH CONVERSION SYSTEM According to this project we try to implement text to speech system by integrating following basic emotions which is to be explained as below: A. Anger This is the emotional category where findings from both spontaneous and elicited material consistently report features such as high mean, wide pitch range, high energy and fast tempo. In detail Fairbanks and Provonost (neutral phrase, acted speech, subjects recognized emotions, English) report that anger generally is characterized by high pitch and a wide pitch range. Fnagy & Magdics ( recordings of spoken Hungarian, subjective analyzing,) reports that anger is characterized by mid pitch and a straight rigid melody. ster and Risberg (conversation, perception experiment with

@ 2011 http://www.ijaest.iserp.org. All rights Reserved.

ES
D.

Sadness The equations are an exception to the prescribed specifications of this template. General findings describe sadness as exhibiting normal or lower pitch, narrow pitch range and slow tempo , Davitz, Fnagy , Murray and Arnott describe the material as being "a wide range of analysis and experimental techniques", ster and Risberg, However, there are contradictory findings concerning voice quality Fear/Anxiety Generally reported features are increased mean F0, increased F0 range, increased F0 Fairbanks and Pronovost (1939, neutral phrase spoken with different emotive expression by non-actors, subjects recognised emotions) reported the relatively highest pitch and the widest pitch range and the highest pitch median. Fairbanks and Hoaglin (, neutral phrase spoken with different emotive expression by non-actors, subjects recognised emotions) noted high speech rate. Williams

hearing impaired subjects, Swedish) reports high tempo, normal pitch range and normal pitch level. Anger is an emotion related to one's psychological interpretation of having been offended, wronged or denied and a tendency to undo that by retaliation. Videbeck [7] describes anger as a normal emotion that involves a strong uncomfortable and emotional response to a perceived provocation. R. Novaco recognized three modalities of anger: cognitive (appraisals), somatic-affective (tension and agitations) and behavioral (withdrawal and antagonism). De Foore. W 2004 describes anger as a pressure cooker; we can only apply pressure against our anger for a certain amount of time until it explodes. Anger may have physical correlates such as increased heart rate, blood pressure, and levels of adrenaline and nor adrenaline[8]. Some view anger as part of the fight or flight brain response to the perceived threat of harm [8] Anger becomes the predominant feeling behaviorally, cognitively, and physiologically when a person makes the conscious choice to take action to immediately stop the threatening behavior of another outside force[9] The English term originally comes from the term anger of Old Norse language[10]. Anger can have many physical and mental consequences

Page 304

Suresh Kumar Thakur* et al. / (IJAEST) INTERNATIONAL JOURNAL OF ADVANCED ENGINEERING SCIENCES AND TECHNOLOGIES Vol No. 8, Issue No. 2, 301 - 305

and Steven , acted speech, emotions induced by content in specially written play with control clusters) reported low F0, but with occasional F0 peaks, low speech rate. E. Disgust For the category disgust induced data and acted data has shown directly contradictory results Studies using induced data reports an increase in mean F0, while studies using acted data found a decrease . F. Hatred/contempt/scorn Fairbanks & Pronovost noted low pitch median, wide pitch range and very wide downward inflections at phrase endings. Fairbanks & Hoaglin noted lowest observed speech rate, caused by prolonged speech rate and increased pause length. Fnagy & Magdics noted that scorn is reflected by a descending melodic line, intoned to a very low level. However, Stibbard points out, that the only parameter analysed in studies more than one is tempo, why it is difficult to evaluate the findings. IV. CONCLUSION AND DISCUSSION Using current methods such as those outlined in this paper, it is possible to produce speech output that is of high intelligibility and reasonable naturalness, given unrestricted input text. However, there is still much work to be done in all areas of the problem, including: improving voice quality, and allowing for greater user control over aspects of voice quality; producing better models of intonation to allow for more natural-sounding contours; and improving linguistic analysis so that more accurate information on contextually appropriate word pronunciation, accenting, and phrasing can be computed automatically. This latter are linguistic analysis is particularly crucial: most high-quality TTS systems allow for user control of the output speech by means of various escape sequences, which can be inserted into the input text. By use of such escape sequences, it is possible to produce highly appropriate and natural sounding output. What are still lacking in many cases are natural-language analysis techniques that can mimic what a human annotator is able to do.

proposed system that convert inputted text data or information in form of speech or sound data. The actual experiment took place on a computer where subjects had to rate the synthesized sentences. The rating was done using a continues scale represented by a slider bar that was labeled angry on the left side, happy on the right side and neutral in the centre. The program recorded the input on a scale from 0 to 100 where 50 meant neutral, 0 meant angry, and 100 meant happy. It is not correct to say that happy and angry are opposite of each other but for the purpose of this experiment it should not had any effect on the outcome. This type of rating scale had the advantage that it is forced choice with a continuos response. A continuos response was needed because the strength of a given emotion was part of the assessment. REFERENCES
[1] [2] [3] Marc Schroder and Martine Grice "Expressing vocal effort in concatenative synthesis" 15th ICPhS Barcelona pp 2589-2592. Alistair Conkie "ROBUST UNIT SELECTION SYSTEM FOR SPEECH SYNTHESIS". Thomas Styger and Eric Keller "Formant Synthesis" Styger, T., & Keller, E. (1994). Formant synthesis.In E. Keller (ed.), Fundamentals of Speech Synthesis and Speech Recognition: Basic Concepts, State of the Art, and Future Challenges (pp. 109-128).. David hlin and Rolf Carlson "Data-driven formant synthesis" Proceedings, FONETIK 2004, Dept. of Linguistics, Stockholm University. P A TAYLOR "Concept-to-Speech Synthesis by Phonological Structure Matching". Videbeck, Sheila L. (2006.). Psychiatric Mental Health Nursing (3rd ed.). Lippincott Williams & Wilkins. "Anger definition". Medicine.net. Retrieved 2008-04-05. Harris, W., Schoenfeld, C. D., Gwynne, P. W., Weissler, A. M.,Circulatory and humoral responses to fear and anger, The Physiologist, 1964, 7, 155. Raymond DiGiuseppe, Raymond Chip Tafrate, Understanding Anger Disorders, Oxford University Press, 2006, pp.133-159. Anger,The American Heritage Dictionary of the English Language, Fourth Edition, 2000, Houghton Mifflin Company. Michael Kent, Anger, The Oxford Dictionary of Sports Science & Medicine, Oxford University Press, ISBN 0-19-262845-3 Primate Ethology, 1967, Desmond Morris (Ed.). Weidenfeld & Nicolson Publishers: London, p.55 i Raymond W. Novaco, Anger, Encyclopedia of Psychology, Oxford University Press, 2000 C.P.Browman and L.M.Goldstein. Towards an articulatory phonology. W.N.Campbell and S.D.Isard.Segment durations in a syllable fra

IJ A
ISSN: 2230-7818

This paper explore the different type of method to generate text to speech conversion in computer technology , or the purpose of developing expressive text to speech conversion system we need to add the various emotion which is explained above in this paper. To generate emotion for adding in to the proposed system we try to control the parameter such as pitch, rate and volume. This is the basic parameter for generating

@ 2011 http://www.ijaest.iserp.org. All rights Reserved.

ES
[5] [6] [7] [8] [9] [10] [11] [12] [13] [14] [15]

[4]

Page 305