Recognition errors caused by out-of-vocabulary (OOV) words lead critical problems when developing spoken language understanding systems based on automatic speech recognition technology. And automatic vocabulary adaptation is an essential technique to solve these problems. In this paper, we propose a novel and effective automatic vocabulary adaptation method. Our method selects OOV words from relevant documents using combined scores of semantic and acoustic similarities. Using this combined score that reflects both semantic and acoustic aspects, only necessary OOV words can be selected without registering redundant words. In addition, our method estimates probabilities of OOV words using semantic similarity and a class-based N-gram language model. These probabilities will be appropriate since they are estimated by considering both frequencies of OOV words in target speech data and the stable class N-gram probabilities. Experimental results show that our method improves OOV selection accuracy and recognition accuracy of newly registered words in comparison with conventional methods.

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 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 Regularization of Weight Vectors (AROW) has been proposed to resolve this problem for binary classification. In addition, AROW's update rule is simpler and more efficient than that of MIRA, allowing for more efficient training. Although AROW has these advantages, it has not been applied to g2p conversion yet. In this paper, we first apply AROW on g2p conversion task which is structured learning problem. In an evaluation that employed a dataset generated from the collective knowledge on the Web, our proposed approach achieves a 6.8% error reduction rate compared to MIRA in terms of phoneme error rate. Also the learning time of our proposed approach was shorter than that of MIRA in almost datasets.

Out-of-vocabulary (OOV) words create serious problems for automatic speech recognition (ASR) systems. Not only are they miss-recognized as in-vocabulary (IV) words with similar phonetics, but the error also causes further errors in nearby words. Language models (LMs) for most open vocabulary ASR systems treat OOV words as a single entity, ignoring the linguistic information. In this paper we present a class-based n-gram LM that is able to deal with OOV words by treating each of them individually without retraining all the LM parameters. OOV words are assigned to IV classes consisting of similar semantic meanings for IV words. The World Wide Web is used to acquire additional data for finding the relation between the OOV and IV words. An evaluation based on adjusted perplexity and word-error-rate was carried out on the Wall Street Journal corpus. The result suggests the preference of the use of multiple classes for OOV words, instead of one unknown class.

This paper proposes a method for handling out-of-vocabulary (OOV) words that cannot be translated using conventional phrase-based statistical machine translation (SMT) systems. For a given OOV word, lexical approximation techniques are utilized to identify spelling and inflectional word variants that occur in the training data. All OOV words in the source sentence are then replaced with appropriate word variants found in the training corpus, thus reducing the number of OOV words in the input. Moreover, in order to increase the coverage of such word translations, the SMT translation model is extended by adding new phrase translations for all source language words that do not have a single-word entry in the original phrase-table but only appear in the context of larger phrases. The effectiveness of the proposed methods is investigated for the translation of Hindi to English, Chinese, and Japanese.

In this paper, we address the task of incremental language modeling for automatic transcription of broadcast news speech. Daily broadcast news naturally contains new words that are not in the lexicon of the speech recognition system but are important for downstream applications such as information retrieval or machine translation. To recognize those new words, the lexicon and the language model of the speech recognition system need to be updated periodically. We propose a method of estimating a list of words to be added to the lexicon based on some time-series text data. The experimental results on the RT04 Broadcast News data and other TV audio data showed that this method provided an impressive and stable reduction in both out-of-vocabulary rates and speech recognition word error rates.