Language Identification Using Deep Convolutional Recurrent Neural Networks
This addresses the problem of accurate language detection for spoken language processing tasks like ASR, though it appears incremental as it adapts existing methods to a new domain.
The paper tackles language identification from audio by proposing a system that operates on spectrogram images using a hybrid Convolutional Recurrent Neural Network, achieving maintained classification accuracy across noisy scenarios and easy extension to new languages.
Language Identification (LID) systems are used to classify the spoken language from a given audio sample and are typically the first step for many spoken language processing tasks, such as Automatic Speech Recognition (ASR) systems. Without automatic language detection, speech utterances cannot be parsed correctly and grammar rules cannot be applied, causing subsequent speech recognition steps to fail. We propose a LID system that solves the problem in the image domain, rather than the audio domain. We use a hybrid Convolutional Recurrent Neural Network (CRNN) that operates on spectrogram images of the provided audio snippets. In extensive experiments we show, that our model is applicable to a range of noisy scenarios and can easily be extended to previously unknown languages, while maintaining its classification accuracy. We release our code and a large scale training set for LID systems to the community.