Interpretation services lend an ear with language app
Appropriately for an international event, Waverly Labs is showcasing its Ambassador Interpreter over-the-ear device and app at MWC21. The ear unit fits over the ear and its far-field microphone array captures speech with “astounding levels of clarity”. The speech signals are seamlessly compressed and transmitted to cloud-based neural network engines to recognise, translate, and synthesise the speech into a fast, fluid translation.
The Ambassador Interpreter kits is designed for multiple interpretation scenarios. Users simply pair the Ambassador Interpreter device to the accompanying iOS or Android app and enable one of three modes: listen, lecture or converse.
In listen mode, Ambassador Interpreter actively listens for someone speaking near the wearer, up to a distance of 2.5m or 8ft, and translates their speech in a chosen language. Lecture mode is intended for groups and conferences. The Ambassador Interpreter can be set to translate everything the wearer says, and streams it through the smartphone’s loudspeaker or a paired audio system for an audience.
The third mode, converse, allows the user to share one of the Ambassador Interpreter units with a guest so you can both understand and communicate in their native languages. Ambassador Interpreter supports pairing up to four units directly through a smartphone.
The over-the-ear unit is hygienic when sharing and is also designed for uncompromised signal strength, says Waverly Labs. It is available in black or red. In addition to two Ambassador Interpreter ear units, the package also includes dual micro-USB charging cables, user manual and a carrying bag. The Ambassador Interpreter interprets 20 languages and 42 dialects (English, French, German, Italian, Portuguese, Spanish, Arabic, Greek, Russian, Hindi, Turkish, Polish, Chinese Mandarin, Japanese, Korean, Cantonese, Thai, Vietnamese, Dutch and Hebrew)
Battery life is up to six hours.
Ambassador Interpreter is engineered for professional-grade translation using speech recognition, machine translation, and speech synthesis.