Online discriminative training for grapheme-to-phoneme conversion
نویسندگان
چکیده
We present an online discriminative training approach to grapheme-to-phoneme (g2p) conversion. We employ a manyto-many alignment between graphemes and phonemes, which overcomes the limitations of widely used one-to-one alignments. The discriminative structure-prediction model incorporates input segmentation, phoneme prediction, and sequence modeling in a unified dynamic programming framework. The learning model is able to capture both local context features in inputs, as well as non-local dependency features in sequence outputs. Experimental results show that our system surpasses the state-of-the-art on several data sets.
منابع مشابه
Structured Adaptive Regularization of Weight Vectors for a Robust Grapheme-to-Phoneme Conversion Model
Grapheme-to-phoneme (g2p) conversion, used to estimate the pronunciations of out-of-vocabulary (OOV) words, is a highly important part of recognition systems, as well as text-to-speech systems. The current state-of-the-art approach in g2p conversion is structured learning based on the Margin Infused Relaxed Algorithm (MIRA), which is an online discriminative training method for multiclass class...
متن کاملGrapheme-to-phoneme conversion based on adaptive regularization of weight vectors
The current state-of-the-art approach in grapheme-to-phoneme (g2p) conversion is structured learning based on the Margin Infused Relaxed Algorithm (MIRA), which is an online discriminative training method for multiclass classification. However, it is known that the aggressive weight update method of MIRA is prone to overfitting, even if the current example is an outlier or noisy. Adaptive Regul...
متن کاملStructured soft margin confidence weighted learning for grapheme-to-phoneme conversion
In recent years, structured online discriminative learning methods using second order statistics have been shown to outperform conventional generative and discriminative models in the grapheme-to-phoneme (g2p) conversion task. However, these methods update the parameters by sequentially using N -best hypotheses predicted with the current parameters. Thus, the parameters appearing in early hypot...
متن کاملTraining grapheme to phoneme conversion in patients with oral reading and naming deficits: A model-based approach
A model-based treatment focused on improving grapheme to phoneme conversion as well as phoneme to grapheme conversion was implemented to train oral reading skills in two patients with severe oral reading and naming deficits. Initial assessment based on current cognitive neuropsychological models of naming indicated a deficit in the phonological output lexicon and in grapheme to phoneme conversi...
متن کاملImproving LVCSR with hidden conditional random fields for grapheme-to-phoneme conversion
In virtually every state-of-the-art large vocabulary continuous speech recognition (LVCSR) system, grapheme-to-phoneme (G2P) conversion is applied to generalize beyond a fixed set of words given by a background lexicon. The overall performance of the G2P system has a strong effect on the recognition quality. Typically, generative models based on joint-n-grams are used, although some discriminat...
متن کامل