kean chin - Academia.edu (original) (raw)
Uploads
Papers by kean chin
Conference of the International Speech Communication Association, 2015
Recently, it was shown that the performance of supervised time-frequency masking based robust aut... more Recently, it was shown that the performance of supervised time-frequency masking based robust automatic speech recognition techniques can be improved by training them jointly with the acoustic model [1]. The system in [1], termed deep neural network based joint adaptive training, used fully-connected feed-forward deep neural networks for estimating time-frequency masks and for acoustic modeling; stacked log mel spectra was used as features and training minimized cross entropy loss. In this work, we extend such jointly trained systems in several ways. First, we use recurrent neural networks based on long short-term memory (LSTM) units-this allows the use of un-stacked features, simplifying joint optimization. Next, we use a sequence discriminative training criterion for optimizing parameters. Finally, we conduct experiments on large scale data and show that joint adaptive training can provide gains over a strong baseline. Systematic evaluations on noisy voice-search data show relativ...
New Era for Robust Speech Recognition, 2017
2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018
2009 IEEE Workshop on Automatic Speech Recognition & Understanding, 2009
2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2011
The Journal of the Acoustical Society of America, 2008
IEEE Transactions on Audio, Speech, and Language Processing, 2011
ABSTRACT
Master's thesis, Engineering Department, Cambridge …
Support Vector Machines (SVM) is a new approach to pattern classification. It promises to give go... more Support Vector Machines (SVM) is a new approach to pattern classification. It promises to give good generalisation and has been applied to various tasks. In this project, pattern recognition using SVMs is evaluated. Specifically, SVMs will be used to classify speech patterns. ...
2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2011
Interspeech 2012
ABSTRACT This paper presents a novel approach to factorize and control different speech factors i... more ABSTRACT This paper presents a novel approach to factorize and control different speech factors in HMM-based TTS systems. In this paper cluster adaptive training (CAT) is used to factorize speaker identity and expressiveness (i.e. emotion). Within a CAT framework, each speech factor can be modelled by a different set of clusters. Users can control speaker identity and expressiveness independently by modifying the weights associated with each set. These weights are defined in a continuous space, so variations of speaker and emotion are also continuous. Additionally, given a speaker which has only neutral-style training data, the approach is able to synthesise speech with that speaker’s voice and different expressions. Lastly, the paper discusses how generalization of the basic factorization concept could allow the production of expressive speech from neutral voices for other HMM-TTS systems not based on CAT.
Conference of the International Speech Communication Association, 2015
Recently, it was shown that the performance of supervised time-frequency masking based robust aut... more Recently, it was shown that the performance of supervised time-frequency masking based robust automatic speech recognition techniques can be improved by training them jointly with the acoustic model [1]. The system in [1], termed deep neural network based joint adaptive training, used fully-connected feed-forward deep neural networks for estimating time-frequency masks and for acoustic modeling; stacked log mel spectra was used as features and training minimized cross entropy loss. In this work, we extend such jointly trained systems in several ways. First, we use recurrent neural networks based on long short-term memory (LSTM) units-this allows the use of un-stacked features, simplifying joint optimization. Next, we use a sequence discriminative training criterion for optimizing parameters. Finally, we conduct experiments on large scale data and show that joint adaptive training can provide gains over a strong baseline. Systematic evaluations on noisy voice-search data show relativ...
New Era for Robust Speech Recognition, 2017
2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018
2009 IEEE Workshop on Automatic Speech Recognition & Understanding, 2009
2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2011
The Journal of the Acoustical Society of America, 2008
IEEE Transactions on Audio, Speech, and Language Processing, 2011
ABSTRACT
Master's thesis, Engineering Department, Cambridge …
Support Vector Machines (SVM) is a new approach to pattern classification. It promises to give go... more Support Vector Machines (SVM) is a new approach to pattern classification. It promises to give good generalisation and has been applied to various tasks. In this project, pattern recognition using SVMs is evaluated. Specifically, SVMs will be used to classify speech patterns. ...
2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2011
Interspeech 2012
ABSTRACT This paper presents a novel approach to factorize and control different speech factors i... more ABSTRACT This paper presents a novel approach to factorize and control different speech factors in HMM-based TTS systems. In this paper cluster adaptive training (CAT) is used to factorize speaker identity and expressiveness (i.e. emotion). Within a CAT framework, each speech factor can be modelled by a different set of clusters. Users can control speaker identity and expressiveness independently by modifying the weights associated with each set. These weights are defined in a continuous space, so variations of speaker and emotion are also continuous. Additionally, given a speaker which has only neutral-style training data, the approach is able to synthesise speech with that speaker’s voice and different expressions. Lastly, the paper discusses how generalization of the basic factorization concept could allow the production of expressive speech from neutral voices for other HMM-TTS systems not based on CAT.