This thesis concerns the problem of unknown or out-of-vocabulary (00V) words in continuous speech recognition. Most of today's state-of-the-art speech recognition systems can recognize only words that belong to some predefined finite word vocabulary. When encountering an OOV word, a speech recognizer erroneously substitutes the OOV word with a similarly sounding word from its vocabulary. Furthermore, a recognition error due to an OOV word tends to spread errors into neighboring words; dramatically degrading overall recognition performance.

Abstract not found

Generic recognition systems contain language models which are representative of a broad corpus. In actual practice, however, recognition is usually on a coherent text covering a single topic, suggesting that knowledge of the topic at hand can be used to advantage. A base model can be augmented with information from a small sample of domain-specific language data to significantly improve recognition performance. Good performance may be obtained by merging in only those n-grams that include words that are out of vocabulary with respect to the base model. 1. Introduction Current language modeling practice requires access to a substantial amount of text from a target domain in order to create a reliable language model. For the North American Business (CSR NAB) domain, 227M words were available. Of necessity models based on large corpora cover a diversity of material and are fairly general in nature. In practice, a given sequence of input utterances (say a dictation) will stick to a parti...

In developing telephone-based conversational systems, we foresee future systems capable of supporting multiple domains and flexible vocabulary. Users can pursue several topics of interest within a single telephone call, and the system is able to switch transparently among domains within a single dialog. This system is able to detect the presence of any out-of-vocabulary (OOV) words, and automatically hypothesizes each of their pronunciation, spelling and meaning. These can be confirmed with the user and the new words are subsequently incorporated into the recognizer lexicon for future use. This thesis

This thesis deals with the problem of Out-Of-Vocabulary words in speech recognition. The standard response of speech recognition systems whenever they encounter such OOV words is to (silently) misrecognize them without issuing any warning to the user. In order to avoid this undesired behaviour, two different strategies are proposed. The first strategy consists in preventing the problem, i.e. the occurrence of OOV words, and this thesis presents two ways of doing that. First, the system vocabulary is optimized using information extracted from other corpora and application domains, such that the number of expected OOV words be minimized. Using this method, the vocabulary coverage was significantly improved, especially for small vocabularies. The second method of reducing the number of OOV words consists of redefining the concept of "word" based on morphological considerations. In particular, compound words are decomposed into their constituent parts, which are used as the lexical recogni...

A speech recognizer is a device that translates speech into text. Many current speech recognizers contain two components, an acoustic model and a statistical language model. The acoustic model indicates how likely it is that a certain word corresponds to a part of the acoustic signal (e.g. the speech). The statistical language model indicates how likely it is that a certain word will be spoken next, given the words recognized so far. Even though the acoustic model might for example not be able to decide between the acoustically similar words "peach" and "teach", the statistical language model can indicate that the word "peach" is more likely if the previously recognized words are "He ate the". Current speech recognizers perform well on constrained tasks, but the goal of continuous, speaker independent speech recognition in potentially noisy environments with a very large vocabulary has not been reached so far. How can statistical language models be improved so that more complex tasks c...

Data-driven techniques, although commonly used for many natural language processing tasks, require large amounts of data to perform well. Even with significant amounts of data there is always a long tail of infrequent linguistic events, which results in poor statistical estimation. To lessen the effect of these unreliable estimates, we propose augmenting corpus statistics with linguistic knowledge encoded in existing resources. This paper evaluates the use-fulness of the information encoded in WordNet for two tasks: improving perplexity of a bigram lan-guage model trained on very little data, and finding longer-distance correlations in text. Word similar-ities derived from WordNet are evaluated by com-paring them to association statistics derived from large amounts of data. Although we see the trends we were hoping for, the overall effect is small. We have found that WordNet does not currently have the breadth or quantity of relations necessary to make substantial improvements over purely data-driven approaches for these two tasks. 1

Word clustering methods and, in general, categorization techniques have been successfully used to reduce the number of parameters to be estimated in language and translation models.