One of the main problems in developing a text-to-speech (TTS) synthesizer for French lies in grapheme-to-phoneme conversion. Automatic converters produce still too many errors in their phoneme sequences, to be helpful for people learning French as a foreign language. The prediction of the phonetic realizations of word-final consonants (WFCs) in general, and liaison in particular (les haricots v...

The feed-forward multi-layer neural networks have significant importance in speech recognition. A new parallel-training tool TNet was designed and optimized for multiprocessor computers. The training acceleration rates are reported on a phoneme-state classification task.

This thesis is about improving machine lip-reading, that is, the classification of speech from only visual cues of a speaker. Machine lip-reading is a niche research problem in both areas of speech processing and computer vision. Current challenges for machine lip-reading fall into two groups: the content of the video, such as the rate at which a person is speaking or; the parameters of the vid...

We present a training approach for recurrent neural networks by combing evolutionary and gradient descent learning. We train the weights of the network using genetic algorithms. We then apply gradient descent learning on the knowledge acquired by genetic training to further refine the knowledge. We also use genetic neural learning and gradient descent learning for training on the same network t...

In this paper, we propose the use of a novel feature set, i.e., modulation spectrogram for fricative classification. Modulation spectrogram gives 2-dimensional (i.e., 2-D) feature vector for each phoneme. Higher Order Singular Value Decomposition (HOSVD) is used to reduce the size of large dimensional feature vector obtained by modulation spectrogram. These features are then used to classify th...

Grapheme-to-Phoneme (G2P) conversion is the task of predicting the pronunciation of a word given its graphemic or written form. It is a highly important part of both automatic speech recognition (ASR) and text-to-speech (TTS) systems. In this paper, we evaluate seven G2P conversion approaches: Adaptive Regularization of Weight Vectors (AROW) based structured learning (S-AROW), Conditional Rando...

In this paper, we present an approach for phoneme detection and phonetic classification that can be used as a basis for different speech processes, such as phoneme boundary detection, acoustic-phonetic decoding or word-graph construction with acoustic confidence scores. The phonetic classifier that has been developed is based on a phase of acoustic vector clustering in the space of acoustic cha...

English speech based on accent dependent parallel phoneme recognition (PPR) has been developed. The classifier is designed to process continuous speech and to discriminate between native Australian English (AuE) speakers and two migrant speaker groups with foreign accents, whose first languages are Lebanese Arabic (LA) and South Vietnamese (SV). The training of the system can be automated and i...