We describe the design of IBM's Attila speech recognition toolkit. We show how the
combination of a highly modular and efficient library of low-level C++ classes with simple …

With increasing globalization, communication across language and cultural boundaries is
becoming an essential requirement of doing business, delivering education, and providing …

Occurrences of one or more keywords in audio data are identified using a speech
recognizer employing a language model to derive a transcript of the keywords. The …

Non-verbalized tokens, such as punctuation, are automatically predicted and inserted into a
transcription of speech in which the tokens were not explicitly verbalized. Token prediction …

It is well known that the performance of automatic speech recognition degrades in noisy
conditions. To address this, typically the noise is removed from the features or the models …

Abstract The Bag-Of-Word (BOW) model uses a fixed length vector of word counts to
represent text. Although the model disregards word sequence information, it has been …

Performance of statistical n-gram language models depends heavily on the amount of
training text material and the degree to which the training text matches the domain of …

Speech endpoint detection (EPD) benefits from the decoder state features (DSFs) of online
automatic speech recognition (ASR) system. However, the DSFs are obtained via the ASR …

This article describes a new automatic transcription system in the Japanese Parliament
which deploys our automatic speech recognition (ASR) technology. To achieve high …

We propose a novel approach based on a statistical transformation framework for language
and pronunciation modeling of spontaneous speech. Since it is not practical to train a …