Language Identification of Individual Words with Joint Sequence Models

1042 Words Feb 17th, 2018 4 Pages
This is of particular importance for ASR systems required to deal with code-switched speech or proper names of foreign origin. For words that occur in the language model, but do not occur in the pronunciation lexicon, text-based language identification (T-LID) of a single word in isolation may be required. This is a challenging task, especially for short words.
We motivate for the importance of accurate T-LID in speech processing systems and introduce a novel way of applying Joint Sequence Models to the T-LID task.
We obtain competitive results on a real-world 4-language task: for our best JSM system, an F1 value of 97.2% is obtained, compared to a F1 value of 95.2% obtained with a state-of-the-art Support Vector Machine (SVM).

Words, phrases and names are often used across language boundaries in multilingual settings. Especially for minority languages, such {\it code-switching} with a dominant language can become an intrinsic part of the language itself~\cite{modipaimplications}.

Automatic speech recognition (ASR) systems are required to deal with various types of words of foreign origin. For example: automated call routing systems or voice-driven navigation systems often process proper names and foreign words that tend to have pronunciations that are difficult to predict~\cite{reveil2010improving}. These…