2015 · 13 citations · 6 references
PhonologySpeech RecognitionSpeech CodingPhoneticsRobust Speech RecognitionVoice RecognitionLanguage StudiesHealth SciencesSpeech SynthesisSpeech OutputDeep LearningText-to-speechVietnamese WordSpeech CommunicationSpeech TechnologyBottleneck FeatureSpeech ProcessingVietnamese LvcsrSpeech InputSpeech PerceptionTonal PhonemeLinguistics
This paper proposes an algorithm that is first known as a grapheme-to-phoneme method to transform any Vietnamese word to a tonal phoneme-based pronunciation. The tonal phoneme set produced by this algorithm is further used to develop some acoustic models which integrated tone information and tonal feature. The processes using the Kaldi toolkit to develop a LVCSR system and extract a bottleneck feature which is calculated from a trained deep neural network for Vietnamese are also presented. The results showed that the use of tonal phoneme improved by 1.54% of word error rate (WER) compared to the system using the nontonal phoneme, the use of tonal feature information improved by 4.65% of WER, and of the bottleneck feature gave the best WER with about 10% improvement.
6
Stochastic Gradient Learning in Neural Networks
Léon Bottou · 1991 · 565 citations
Extracting deep bottleneck features using stacked auto-encoders
Jonas Gehring, Yajie Miao, Florian Metze et al. · 2013 · 278 citations · Full text
Convolutional Neural Network, Engineering, Machine Learning +20
Improved feature processing for deep neural networks
Shakti P. Rath, Daniel Povey, Karel Veselý et al. · 2013 · 188 citations
Convolutional Neural Network, Engineering, Machine Learning +16
Models of tone for tonal and non-tonal languages
Florian Metze, Zaid Sheikh, Alex Waibel et al. · 2013 · 38 citations · Full text