Javascript must be enabled to continue!
A study of prosodic features for Indonesian speech recognition
View through CrossRef
Utterance-type information has been used been used in spoken dialogue system, speech recognition system and translation machine. In a typical spoken dialogue system, a user can ask question or give information to the system. In another side, the spoken dialogue system should be capable of recognizing its user intention to give the correct response to him/her. In this dissertation, the automatic utterance-type recognizer is proposed to distinguish declarative questions from statements in Indonesian speech. Since utterances in these two types have the same words with the same order and differ only in their intonations, their classification requires not only a word recognizer, but also an intonation recognizer. At first, the utterance-type recognizer is designed based on Fujisaki model. The utterance-type recognizer uses a combination of the Fujisaki-model-parameters as the features to recognizt the two utterance type. The best performance of the Fujisaki model based utterance-type recognizer is achieved using a combination of a fraction value of F[subscript b] : F[subscript b]/100 the amplitude of last accent command, and the magnitude of last phrase command as the input of the neural neetworks. However, the Fujisaki parameters extractor is too complicated to be implemented in an automatic recognition system. Therefore, the utterance-type recognizer is developed using the polynomial coefficients of the pitch contours of the sentence's final word. The automatic utterance-type recognizer using polynomial expansion consists of a pitch contour extractor, normalizer, feature extractor, classifier, and an automatic utterance segmentation module. The pitch contour of each utterance type i analyzed to investigate the final word of the two utterance type. To create the automatic utterance segmentation module, an Indonesian acoustic model is designed. The evaluation confirms that the method using the final word and polynomial expansion is effective to distinguish declarative questions and statements in Indonesian speech.
Title: A study of prosodic features for Indonesian speech recognition
Description:
Utterance-type information has been used been used in spoken dialogue system, speech recognition system and translation machine.
In a typical spoken dialogue system, a user can ask question or give information to the system.
In another side, the spoken dialogue system should be capable of recognizing its user intention to give the correct response to him/her.
In this dissertation, the automatic utterance-type recognizer is proposed to distinguish declarative questions from statements in Indonesian speech.
Since utterances in these two types have the same words with the same order and differ only in their intonations, their classification requires not only a word recognizer, but also an intonation recognizer.
At first, the utterance-type recognizer is designed based on Fujisaki model.
The utterance-type recognizer uses a combination of the Fujisaki-model-parameters as the features to recognizt the two utterance type.
The best performance of the Fujisaki model based utterance-type recognizer is achieved using a combination of a fraction value of F[subscript b] : F[subscript b]/100 the amplitude of last accent command, and the magnitude of last phrase command as the input of the neural neetworks.
However, the Fujisaki parameters extractor is too complicated to be implemented in an automatic recognition system.
Therefore, the utterance-type recognizer is developed using the polynomial coefficients of the pitch contours of the sentence's final word.
The automatic utterance-type recognizer using polynomial expansion consists of a pitch contour extractor, normalizer, feature extractor, classifier, and an automatic utterance segmentation module.
The pitch contour of each utterance type i analyzed to investigate the final word of the two utterance type.
To create the automatic utterance segmentation module, an Indonesian acoustic model is designed.
The evaluation confirms that the method using the final word and polynomial expansion is effective to distinguish declarative questions and statements in Indonesian speech.
Related Results
Pola Komunikasi Interpersonal Terapis Wicara pada Anak Telambat Bicara (Speech Delay)
Pola Komunikasi Interpersonal Terapis Wicara pada Anak Telambat Bicara (Speech Delay)
Abstract. The tittle of this study is Interpersonal Communication Patterns of Speech Therapists in Children with Speech Delay. Children with speech delay disorders are also social ...
Multimodal Emotion Recognition and Human Computer Interaction for AI-Driven Mental Health Support (Preprint)
Multimodal Emotion Recognition and Human Computer Interaction for AI-Driven Mental Health Support (Preprint)
BACKGROUND
Mental health has become one of the most urgent global health issues of the twenty-first century. The World Health Organization (WHO) reports tha...
Tindak Tutur pada Tradisi Mappettuada Suku Bugis
Tindak Tutur pada Tradisi Mappettuada Suku Bugis
This study aims to The purpose of this study is to understand and describe locutionary, illocutionary, and perlocutionary speech acts in the Mappettuada tradition of the Bugis-Maka...
Studying some elicited verbal prosodic patterns in Egyptian children
Studying some elicited verbal prosodic patterns in Egyptian children
EnAbstract
Background
Despite the large number of native Arabic speakers, Arabic prosodic skills have not been studied thoroughly.
...
Prosodic assessment in Egyptian children with specific language impairment
Prosodic assessment in Egyptian children with specific language impairment
EnAbstract
Background
Prosody is the aspect of language that conveys emotion by changes in tone, rhythm, and emphasis during speech. Prosody include...
Discontinuous noun phrases in Vietnamese
Discontinuous noun phrases in Vietnamese
Since Vietnamese is an isolating language, word order plays an important role in identifying the function of a particular word. Yet in some contexts word order may be flexible espe...
PECULIARITIES OF SPEECH BEHAVIOR OF SEAFARERS FROM INDIA AND CHINA
PECULIARITIES OF SPEECH BEHAVIOR OF SEAFARERS FROM INDIA AND CHINA
The article is devoted to the investigation of peculiarities of speech behavior of Indian and Chinese seafarers. Language, being the most important communicative tool as a general ...
Natural Infant-Directed Speech Facilitates Neural Tracking of Prosody
Natural Infant-Directed Speech Facilitates Neural Tracking of Prosody
Infants prefer to be addressed with infant-directed speech (IDS). IDS benefits language acquisition through amplified low-frequency amplitude modulations. It has been reported that...

