§ 00 — Applied Language Technology · Live Demonstrations

Where the latent manifold meets the user.

The lab's quantitative methods become things people can hold and speak to. Two systems run live in your browser, rendered frame by frame from code: an immersive language tutor that moves through 3D scenes, and a multilingual interpreter that turns speech into speech across languages.

The stack at a glance
WebGLThree.jsSpatial Audio ASRNeural MTTTS TransformerSeq2SeqCanvas 2D

rendered live · no recordings · no servers

§ 01 Immersive learning · VR + AI tutor
§ 01
Demonstration one

VR + AI language learning

A learner walks through three rendered worlds with an AI tutor at their side. Café, airport, meeting room. Each scene sets a task, surfaces the vocabulary, and gives feedback in real time.

WebXR

Head-tracked scenes place the learner inside the language, not in front of it.

3D Spatial Audio

Voices come from where the speaker stands, so listening trains direction and distance too.

AI Tutor NLU

The tutor parses each utterance, scores pronunciation, and adapts the next prompt.

§ 02 Speech to speech · multilingual interpreter
§ 02
Demonstration two

Multilingual live interpreter

One device, many tongues. Speech enters on the left, runs through the recognition and translation pipeline, and leaves as a new voice on the right. Watch it relay across English, Chinese, and Japanese.

Voice Activity Detection

segment speech from silence

Speech Recognition

ASR · acoustic + language model

Neural Machine Translation

encoder · decoder · attention

Speech Synthesis

TTS · neural vocoder

§ 03 Under the hood · rendering & models
§ 03
Toolchain

Rendered in the open

Every frame on this page is computed live in the browser. Nothing here is a recording.

WebGL · Three.jsCanvas 2DWeb Audio requestAnimationFrameGLSL shadersASR TransformerSeq2Seq attentionNeural TTS WebXR-readyzero backendzero recordings