German-Arabic Speech-to-Speech Translation for Psychiatric Diagnosis
Juan Hussain, Moritz Behr, Mohamed Amine Chéragui, Sebastian Stüker, Waibel, Alex, Mohammed Mediani · KITopen · 2020
In this paper we present the Arabic related natural language processing components of our German–Arabic speech-to-speech translation system which is being deployed in the context of interpretation during psychiatric, diagnostic interviews. For this purpose we have built a pipelined speech-to-speech translation system consisting of automatic speech recognition, machine translation, text post-processing, and speech synthesis systems. We have implemented two pipelines, from German to Arabic and vice versa, to conduct interpreted two-way dialogues between psychiatrists and potential patients. All systems in our pipeline have been realized as all-neural end-to-end systems, using different architectures suitable for the different components. The speech recognition systems use an encoder/decoder + attention architecture, the machine translation system is based on the Transformer architecture, the post-processing for Arabic employs a sequence-tagger for diacritization, and for the speech synthesis systems we use Tacotron 2 for generating spectrograms and WaveGlow as a vocoder. The speech translation is deployed in a server-based speech translation application that implements a turn-based translation between a German-speaking psychiatrist administrating the Mini-International Neuropsychiatric Interview (M.I.N.I.) and an Arabic speaking person answering the interview. As this is a very specific domain, in addition to the linguistic challenges posed by translating between Arabic and German, we also focus in this paper on the methods we implemented for adapting our speech to speech translation system to the domain of this psychiatric interview.