One of the challenges of processing real-world spoken content, such as automatic speech recognition, is the potential presence of different languages and dialects. Language and Dialect identification can be a useful capability to identify which language is being spoken during a recording.

In our research, we explore both acoustic and natural language processing techniques to develop language and dialect identification system from speech. We basically focused on the acoustic signal using deep learning technology to learn similarity and dis-similarity between languages and dialects.

Dialect identification can be regarded as a special case of language recognition, requiring an ability to discriminate between different members within the same language family, as opposed to across language families (i.e., for language identification). In contrast to the language identification scenario, dialects typically share a common phonetic inventory and written language. Thus, we also focused on linguistic features (i.e words, characters and phonemes) that could be utilized by automatic speech recognition.

Research Areas