The Experts below are selected from a list of 2898 Experts worldwide ranked by ideXlab platform
Yasuo Ariki - One of the best experts on this subject based on the ideXlab platform.
-
individuality preserving voice reconstruction for Articulation Disorders using text to speech synthesis
International Conference on Multimodal Interfaces, 2015Co-Authors: Reina Ueda, Tetsuya Takiguchi, Yasuo ArikiAbstract:This paper presents a speech synthesis method for people with Articulation Disorders. Because the movements of such speakers are limited by their athetoid symptoms, their prosody is often unstable and their speech rate differs from that of a physically unimpaired person, which causes their speech to be less intelligible and, consequently, makes communication with physically unimpaired persons difficult. In order to deal with these problems, this paper describes a Hidden Markov Model(HMM)-based text-to-speech synthesis approach that preserves the individuality of a person with an Articulation Disorder and aids them in their communication. In our method, a duration model of a physically unimpaired person is used for the HMM synthesis system and an F0 model in the system is trained using the F0 patterns of the physically unimpaired person, with the average F0 being converted to the target F0 in advance. In order to preserve the target speaker's individuality, a spectral model is built from target spectra. Through experimental evaluations, we have confirmed that the proposed method successfully synthesizes intelligible speech while maintaining the target speaker's individuality.
-
ICMI - Individuality-Preserving Voice Reconstruction for Articulation Disorders Using Text-to-Speech Synthesis
Proceedings of the 2015 ACM on International Conference on Multimodal Interaction, 2015Co-Authors: Reina Ueda, Tetsuya Takiguchi, Yasuo ArikiAbstract:This paper presents a speech synthesis method for people with Articulation Disorders. Because the movements of such speakers are limited by their athetoid symptoms, their prosody is often unstable and their speech rate differs from that of a physically unimpaired person, which causes their speech to be less intelligible and, consequently, makes communication with physically unimpaired persons difficult. In order to deal with these problems, this paper describes a Hidden Markov Model(HMM)-based text-to-speech synthesis approach that preserves the individuality of a person with an Articulation Disorder and aids them in their communication. In our method, a duration model of a physically unimpaired person is used for the HMM synthesis system and an F0 model in the system is trained using the F0 patterns of the physically unimpaired person, with the average F0 being converted to the target F0 in advance. In order to preserve the target speaker's individuality, a spectral model is built from target spectra. Through experimental evaluations, we have confirmed that the proposed method successfully synthesizes intelligible speech while maintaining the target speaker's individuality.
-
Individuality-Preserving Voice Conversion for Articulation Disorders Using Phoneme-Categorized Exemplars
ACM Transactions on Accessible Computing, 2015Co-Authors: Ryo Aihara, Tetsuya Takiguchi, Yasuo ArikiAbstract:We present a voice conversion (VC) method for a person with an Articulation Disorder resulting from athetoid cerebral palsy. The movements of such speakers are limited by their athetoid symptoms and their consonants are often unstable or unclear, which makes it difficult for them to communicate. Exemplar-based spectral conversion using Nonnegative Matrix Factorization (NMF) is applied to a voice from a speaker with an Articulation Disorder. In our conventional work, we used a combined dictionary that was constructed from the source speaker’s vowels and the consonants from a target speaker without Articulation Disorders in order to preserve the speaker’s individuality. However, this conventional exemplar-based approach needs to use all the training exemplars (frames), and it may cause mismatching of phonemes between input signals and selected exemplars. In order to reduce the mismatching of phoneme alignment, we propose a phoneme-categorized subdictionary and a dictionary selection method using NMF. The effectiveness of this method was confirmed by comparing its effectiveness with that of a conventional Gaussian Mixture Model (GMM)-based and a conventional exemplar-based method.
-
SLPAT@Interspeech - Individuality-Preserving Spectrum Modification for Articulation Disorders Using Phone Selective Synthesis
Proceedings of SLPAT 2015: 6th Workshop on Speech and Language Processing for Assistive Technologies, 2015Co-Authors: Reina Ueda, Tetsuya Takiguchi, Ryo Aihara, Yasuo ArikiAbstract:This paper presents a speech synthesis method for people with Articulation Disorders resulting from athetoid cerebral palsy. For people with Articulation Disorders, there are duration, pitch and spectral problems that cause their speech to be less intelligible and make communication difficult. In order to deal with these problems, this paper describes a Hidden Markov Model (HMM)-based text-to-speech synthesis approach that preserves the voice individuality of those with Articulation Disorders and aids them in their communication. For the unstable pitch problem, we use the F0 patterns of a physically unimpaired person, with the average F0 being converted to the target F0 in advance. Because the spectrum of people with Articulation Disorders is often unstable and unclear, we modify generated spectral parameters from the HMM synthesis system by using a physically unimpaired person’s spectral model while preserving the individuality of the person with an Articulation Disorder. Through experimental evaluations, we have confirmed that the proposed method successfully synthesizes intelligible speech while maintaining the target speaker’s individuality.
-
Dysarthric Speech Recognition Using a Convolutive Bottleneck Network
2014Co-Authors: Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki, Toshiya Yoshioka, Stefan Duffner, Christophe GarciaAbstract:In this paper, we investigate the recognition of speech produced by a person with an Articulation Disorder resulting from athetoid cerebral palsy. The Articulation of the first spoken words tends to become unstable due to strain on speech muscles, and that causes a degradation of traditional speech recognition systems. Therefore, we propose a robust feature extraction method using a convolutive bottleneck network (CBN) instead of the well-known MFCC. The CBN stacks multiple various types of layers, such as a convolution layer, a subsampling layer, and a bottleneck layer, forming a deep network. Applying the CBN to feature extraction for dysarthric speech, we expect that the CBN will reduce the influence of the unstable speaking style caused by the athetoid symptoms. We confirmed its effectiveness through word-recognition experiments, where the CBN-based feature extraction method outperformed the conventional feature extraction method.
Tetsuya Takiguchi - One of the best experts on this subject based on the ideXlab platform.
-
APSIPA - Hybrid Text-to-Speech for Articulation Disorders with a Small Amount of Non-Parallel Data
2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), 2018Co-Authors: Ryuka Nanzaka, Tetsuya TakiguchiAbstract:Conventional approaches to statistical parametric speech synthesis usually require a large amount of speech data. But it is very difficult for persons with Articulation Disorders, in particular, to utter a large amount of speech data, and their utterances are often unstable or unclear so that we cannot understand what they say. In this paper, we propose a hybrid approach for a person with an Articulation Disorder, using two models of a physically unimpaired person and a person with an Articulation Disorder to generate an intelligible voice while preserving the speaker's individuality (with an Articulation Disorder). Our method has two processes - the speech synthesis part and voice conversion part. Speech synthesis is employed for obtaining a speech signal (of a physically unimpaired person), where a large amount of training data of a physically unimpaired person is used. Then, voice conversion (VC) is employed for converting the voice of the physically unimpaired person to that of a person with an Articulation Disorder, where a small amount of speech data of a person with an Articulation Disorder is only used for training VC. Also, a cycle-consistent adversarial network (CycleGAN) that does not require parallel data is employed for VC. An objective evaluation showed that the mel-cepstrum obtained using our method are close to the target in terms of global variance (GV) and modulation spectrum (MS).
-
individuality preserving voice reconstruction for Articulation Disorders using text to speech synthesis
International Conference on Multimodal Interfaces, 2015Co-Authors: Reina Ueda, Tetsuya Takiguchi, Yasuo ArikiAbstract:This paper presents a speech synthesis method for people with Articulation Disorders. Because the movements of such speakers are limited by their athetoid symptoms, their prosody is often unstable and their speech rate differs from that of a physically unimpaired person, which causes their speech to be less intelligible and, consequently, makes communication with physically unimpaired persons difficult. In order to deal with these problems, this paper describes a Hidden Markov Model(HMM)-based text-to-speech synthesis approach that preserves the individuality of a person with an Articulation Disorder and aids them in their communication. In our method, a duration model of a physically unimpaired person is used for the HMM synthesis system and an F0 model in the system is trained using the F0 patterns of the physically unimpaired person, with the average F0 being converted to the target F0 in advance. In order to preserve the target speaker's individuality, a spectral model is built from target spectra. Through experimental evaluations, we have confirmed that the proposed method successfully synthesizes intelligible speech while maintaining the target speaker's individuality.
-
ICMI - Individuality-Preserving Voice Reconstruction for Articulation Disorders Using Text-to-Speech Synthesis
Proceedings of the 2015 ACM on International Conference on Multimodal Interaction, 2015Co-Authors: Reina Ueda, Tetsuya Takiguchi, Yasuo ArikiAbstract:This paper presents a speech synthesis method for people with Articulation Disorders. Because the movements of such speakers are limited by their athetoid symptoms, their prosody is often unstable and their speech rate differs from that of a physically unimpaired person, which causes their speech to be less intelligible and, consequently, makes communication with physically unimpaired persons difficult. In order to deal with these problems, this paper describes a Hidden Markov Model(HMM)-based text-to-speech synthesis approach that preserves the individuality of a person with an Articulation Disorder and aids them in their communication. In our method, a duration model of a physically unimpaired person is used for the HMM synthesis system and an F0 model in the system is trained using the F0 patterns of the physically unimpaired person, with the average F0 being converted to the target F0 in advance. In order to preserve the target speaker's individuality, a spectral model is built from target spectra. Through experimental evaluations, we have confirmed that the proposed method successfully synthesizes intelligible speech while maintaining the target speaker's individuality.
-
Individuality-Preserving Voice Conversion for Articulation Disorders Using Phoneme-Categorized Exemplars
ACM Transactions on Accessible Computing, 2015Co-Authors: Ryo Aihara, Tetsuya Takiguchi, Yasuo ArikiAbstract:We present a voice conversion (VC) method for a person with an Articulation Disorder resulting from athetoid cerebral palsy. The movements of such speakers are limited by their athetoid symptoms and their consonants are often unstable or unclear, which makes it difficult for them to communicate. Exemplar-based spectral conversion using Nonnegative Matrix Factorization (NMF) is applied to a voice from a speaker with an Articulation Disorder. In our conventional work, we used a combined dictionary that was constructed from the source speaker’s vowels and the consonants from a target speaker without Articulation Disorders in order to preserve the speaker’s individuality. However, this conventional exemplar-based approach needs to use all the training exemplars (frames), and it may cause mismatching of phonemes between input signals and selected exemplars. In order to reduce the mismatching of phoneme alignment, we propose a phoneme-categorized subdictionary and a dictionary selection method using NMF. The effectiveness of this method was confirmed by comparing its effectiveness with that of a conventional Gaussian Mixture Model (GMM)-based and a conventional exemplar-based method.
-
SLPAT@Interspeech - Individuality-Preserving Spectrum Modification for Articulation Disorders Using Phone Selective Synthesis
Proceedings of SLPAT 2015: 6th Workshop on Speech and Language Processing for Assistive Technologies, 2015Co-Authors: Reina Ueda, Tetsuya Takiguchi, Ryo Aihara, Yasuo ArikiAbstract:This paper presents a speech synthesis method for people with Articulation Disorders resulting from athetoid cerebral palsy. For people with Articulation Disorders, there are duration, pitch and spectral problems that cause their speech to be less intelligible and make communication difficult. In order to deal with these problems, this paper describes a Hidden Markov Model (HMM)-based text-to-speech synthesis approach that preserves the voice individuality of those with Articulation Disorders and aids them in their communication. For the unstable pitch problem, we use the F0 patterns of a physically unimpaired person, with the average F0 being converted to the target F0 in advance. Because the spectrum of people with Articulation Disorders is often unstable and unclear, we modify generated spectral parameters from the HMM synthesis system by using a physically unimpaired person’s spectral model while preserving the individuality of the person with an Articulation Disorder. Through experimental evaluations, we have confirmed that the proposed method successfully synthesizes intelligible speech while maintaining the target speaker’s individuality.
Reina Ueda - One of the best experts on this subject based on the ideXlab platform.
-
ICMI - Individuality-Preserving Voice Reconstruction for Articulation Disorders Using Text-to-Speech Synthesis
Proceedings of the 2015 ACM on International Conference on Multimodal Interaction, 2015Co-Authors: Reina Ueda, Tetsuya Takiguchi, Yasuo ArikiAbstract:This paper presents a speech synthesis method for people with Articulation Disorders. Because the movements of such speakers are limited by their athetoid symptoms, their prosody is often unstable and their speech rate differs from that of a physically unimpaired person, which causes their speech to be less intelligible and, consequently, makes communication with physically unimpaired persons difficult. In order to deal with these problems, this paper describes a Hidden Markov Model(HMM)-based text-to-speech synthesis approach that preserves the individuality of a person with an Articulation Disorder and aids them in their communication. In our method, a duration model of a physically unimpaired person is used for the HMM synthesis system and an F0 model in the system is trained using the F0 patterns of the physically unimpaired person, with the average F0 being converted to the target F0 in advance. In order to preserve the target speaker's individuality, a spectral model is built from target spectra. Through experimental evaluations, we have confirmed that the proposed method successfully synthesizes intelligible speech while maintaining the target speaker's individuality.
-
individuality preserving voice reconstruction for Articulation Disorders using text to speech synthesis
International Conference on Multimodal Interfaces, 2015Co-Authors: Reina Ueda, Tetsuya Takiguchi, Yasuo ArikiAbstract:This paper presents a speech synthesis method for people with Articulation Disorders. Because the movements of such speakers are limited by their athetoid symptoms, their prosody is often unstable and their speech rate differs from that of a physically unimpaired person, which causes their speech to be less intelligible and, consequently, makes communication with physically unimpaired persons difficult. In order to deal with these problems, this paper describes a Hidden Markov Model(HMM)-based text-to-speech synthesis approach that preserves the individuality of a person with an Articulation Disorder and aids them in their communication. In our method, a duration model of a physically unimpaired person is used for the HMM synthesis system and an F0 model in the system is trained using the F0 patterns of the physically unimpaired person, with the average F0 being converted to the target F0 in advance. In order to preserve the target speaker's individuality, a spectral model is built from target spectra. Through experimental evaluations, we have confirmed that the proposed method successfully synthesizes intelligible speech while maintaining the target speaker's individuality.
-
SLPAT@Interspeech - Individuality-Preserving Spectrum Modification for Articulation Disorders Using Phone Selective Synthesis
Proceedings of SLPAT 2015: 6th Workshop on Speech and Language Processing for Assistive Technologies, 2015Co-Authors: Reina Ueda, Tetsuya Takiguchi, Ryo Aihara, Yasuo ArikiAbstract:This paper presents a speech synthesis method for people with Articulation Disorders resulting from athetoid cerebral palsy. For people with Articulation Disorders, there are duration, pitch and spectral problems that cause their speech to be less intelligible and make communication difficult. In order to deal with these problems, this paper describes a Hidden Markov Model (HMM)-based text-to-speech synthesis approach that preserves the voice individuality of those with Articulation Disorders and aids them in their communication. For the unstable pitch problem, we use the F0 patterns of a physically unimpaired person, with the average F0 being converted to the target F0 in advance. Because the spectrum of people with Articulation Disorders is often unstable and unclear, we modify generated spectral parameters from the HMM synthesis system by using a physically unimpaired person’s spectral model while preserving the individuality of the person with an Articulation Disorder. Through experimental evaluations, we have confirmed that the proposed method successfully synthesizes intelligible speech while maintaining the target speaker’s individuality.
Ryo Aihara - One of the best experts on this subject based on the ideXlab platform.
-
Individuality-Preserving Voice Conversion for Articulation Disorders Using Phoneme-Categorized Exemplars
ACM Transactions on Accessible Computing, 2015Co-Authors: Ryo Aihara, Tetsuya Takiguchi, Yasuo ArikiAbstract:We present a voice conversion (VC) method for a person with an Articulation Disorder resulting from athetoid cerebral palsy. The movements of such speakers are limited by their athetoid symptoms and their consonants are often unstable or unclear, which makes it difficult for them to communicate. Exemplar-based spectral conversion using Nonnegative Matrix Factorization (NMF) is applied to a voice from a speaker with an Articulation Disorder. In our conventional work, we used a combined dictionary that was constructed from the source speaker’s vowels and the consonants from a target speaker without Articulation Disorders in order to preserve the speaker’s individuality. However, this conventional exemplar-based approach needs to use all the training exemplars (frames), and it may cause mismatching of phonemes between input signals and selected exemplars. In order to reduce the mismatching of phoneme alignment, we propose a phoneme-categorized subdictionary and a dictionary selection method using NMF. The effectiveness of this method was confirmed by comparing its effectiveness with that of a conventional Gaussian Mixture Model (GMM)-based and a conventional exemplar-based method.
-
SLPAT@Interspeech - Individuality-Preserving Spectrum Modification for Articulation Disorders Using Phone Selective Synthesis
Proceedings of SLPAT 2015: 6th Workshop on Speech and Language Processing for Assistive Technologies, 2015Co-Authors: Reina Ueda, Tetsuya Takiguchi, Ryo Aihara, Yasuo ArikiAbstract:This paper presents a speech synthesis method for people with Articulation Disorders resulting from athetoid cerebral palsy. For people with Articulation Disorders, there are duration, pitch and spectral problems that cause their speech to be less intelligible and make communication difficult. In order to deal with these problems, this paper describes a Hidden Markov Model (HMM)-based text-to-speech synthesis approach that preserves the voice individuality of those with Articulation Disorders and aids them in their communication. For the unstable pitch problem, we use the F0 patterns of a physically unimpaired person, with the average F0 being converted to the target F0 in advance. Because the spectrum of people with Articulation Disorders is often unstable and unclear, we modify generated spectral parameters from the HMM synthesis system by using a physically unimpaired person’s spectral model while preserving the individuality of the person with an Articulation Disorder. Through experimental evaluations, we have confirmed that the proposed method successfully synthesizes intelligible speech while maintaining the target speaker’s individuality.
-
A preliminary demonstration of exemplar-based voice conversion for Articulation Disorders using an individuality-preserving dictionary
EURASIP Journal on Audio Speech and Music Processing, 2014Co-Authors: Ryo Aihara, Tetsuya Takiguchi, Ryoichi Takashima, Yasuo ArikiAbstract:We present in this paper a voice conversion (VC) method for a person with an Articulation Disorder resulting from athetoid cerebral palsy. The movement of such speakers is limited by their athetoid symptoms, and their consonants are often unstable or unclear, which makes it difficult for them to communicate. In this paper, exemplar-based spectral conversion using nonnegative matrix factorization (NMF) is applied to a voice with an Articulation Disorder. To preserve the speaker’s individuality, we used an individuality-preserving dictionary that is constructed from the source speaker’s vowels and target speaker’s consonants. Using this dictionary, we can create a natural and clear voice preserving their voice’s individuality. Experimental results indicate that the performance of NMF-based VC is considerably better than conventional GMM-based VC.
-
ICASSP - Individuality-preserving voice conversion for Articulation Disorders based on non-negative matrix factorization
2013 IEEE International Conference on Acoustics Speech and Signal Processing, 2013Co-Authors: Ryo Aihara, Tetsuya Takiguchi, Ryoichi Takashima, Yasuo ArikiAbstract:We present in this paper a voice conversion (VC) method for a person with an Articulation Disorder resulting from athetoid cerebral palsy. The movement of such speakers is limited by their athetoid symptoms, and their consonants are often unstable or unclear, which makes it difficult for them to communicate. In this paper, exemplar-based spectral conversion using Non-negative Matrix Factorization (NMF) is applied to a voice with an Articulation Disorder. To preserve the speaker's individuality, we used a combined dictionary that is constructed from the source speaker's vowels and target speaker's consonants. Experimental results indicate that the performance of NMF-based VC is considerably better than conventional GMM-based VC.
-
INTERSPEECH - Exemplar-based Individuality-Preserving Voice Conversion for Articulation Disorders in Noisy Environments
2013Co-Authors: Ryo Aihara, Tetsuya Takiguchi, Ryoichi Takashima, Yasuo ArikiAbstract:We present in this paper a noise robust voice conversion (VC) method for a person with an Articulation Disorder resulting from athetoid cerebral palsy. The movements of such speakers are limited by their athetoid symptoms, and their consonants are often unstable or unclear, which makes it difficult for them to communicate. In this paper, exemplar-based spectral conversion using Non-negative Matrix Factorization (NMF) is applied to a voice with an Articulation Disorder in real noisy environments. In this paper, in order to deal with background noise, an input noisy source signal is decomposed into the clean source exemplars and noise exemplars by NMF. Also, to preserve the speaker’s individuality, we use a combined dictionary that was constructed from the source speaker’s vowels and target speaker’s consonants. The effectiveness of this method was confirmed by comparing its effectiveness with that of a conventional Gaussian Mixture Model (GMM)-based method. Index Terms: Voice Conversion, NMF, Articulation Disorders, Noise Robustness, Assistive Technologies
Kyriaki Ttofari Eecen - One of the best experts on this subject based on the ideXlab platform.
-
validation of dodd s model for differential diagnosis of childhood speech sound Disorders a longitudinal community cohort study
Developmental Medicine & Child Neurology, 2019Co-Authors: Kyriaki Ttofari Eecen, Patricia Eadie, Angela T Morgan, Sheena ReillyAbstract:AIM Dodd's Model for Differential Diagnosis is one of the available clinical diagnostic classification systems of childhood speech sound Disorders. Yet we do not understand the validity of this system beyond clinical samples, precluding its application in epidemiological or population-based research. This study aimed to determine the prevalence of subgroups of speech sound Disorders in a community sample, relative to past clinical samples, in children speaking standard Australian English. METHOD We examined speech development in a community-ascertained sample of children at 4 years (n=1607). Inclusion for speech sound Disorder was a score of less than or equal to 1 standard deviation on a standardized speech test, and/or research assistant concern, and/or three or more speech errors on sounds typically acquired by 4 years. Dodd's model was then applied to 126 children. RESULTS Data revealed proportions of children across Dodd's diagnostic subgroups as follows: suspected atypical speech motor control (10%); inconsistent phonological Disorder (15%); consistent atypical phonological Disorder (20%); phonological delay (55%); and Articulation Disorder alone (0%). The findings are in line with known prevalence of these subgroups in clinical populations. INTERPRETATION Our findings provide additional support for speech-language pathologists to use this system in clinical practice for differential diagnosis and targeted intervention of speech sound Disorders in children. WHAT THIS PAPER ADDS Dodd's Model for Differential Diagnosis is the first classification system of speech sound Disorders to be applicable to both clinical and community cohorts.
