From real-world voice input to recognition and dialogue

mpAEC

Cancels echo produced by the device's own speaker

mpAEC is a multi-channel acoustic echo cancellation technology that reduces sound played by the product — TV audio, car audio, robot responses, kiosk prompts — from re-entering the microphone.

It is designed for environments where the user's voice and the product's output are present at the same time, and its output can feed beamforming or your existing ASR.

Official material presents stable processing with near-end speech present, no double-talk detection required, no far-end signal decorrelation required, and fast convergence as mpAEC's characteristics.

mpBeamforming

Reduces ambient noise and strengthens the target voice with multiple microphones

mpBeamforming uses the spatial information across multiple microphones to reduce the impact of ambient noise and deliver the target voice more clearly.

mpWAV optimizes from the actual input signals rather than fixed microphone position data, reducing the repeated tuning burden when microphone configurations change between products.

Official material describes automatic optimization from input signals, no separate tuning when microphone configurations change, and minimal target-voice distortion as its core characteristics.

mpAB

Integrates echo cancellation and beamforming into one real-time pipeline

mpAB combines mpAEC and mpBeamforming to process input where product speaker echo and environmental noise are present together.

Multi-channel microphones, the speaker reference, FPGA·DSP·AP platforms, and your existing ASR can be connected into a single product architecture.

Official material presents mpAB as the integration of mpAEC and mpBeamforming, with real-time FPGA implementation and MCU+DSP / AP porting structures.

mpNC

Single-microphone noise control for products that cannot add mics

mpNC is a voice enhancement technology that reduces the impact of ambient noise from a single microphone input.

It provides the technical foundation for improving voice input in earbuds, mobile accessories, small smart devices, and constrained hardware where a microphone array is not an option.

mpWWD

Detects the wake word and starts the voice interface

mpWWD detects a predefined wake word so the product can start listening for voice commands.

It connects to robots, smart home devices, vehicles, and edge devices that must decide the moment of activation on-device rather than streaming audio to a server at all times.

mpS

Prepares multi-party voice input for downstream processing

mpS processes audio from environments where multiple voices exist or overlap — meetings and voice chat — into a form suitable for downstream analysis and recognition.

Combined with mpDiarization and mpASR, it forms the input pipeline for multi-party meeting records and voice chat.

mpLocalization

Estimates where the voice is coming from

mpLocalization uses multi-microphone input to estimate the direction or position of the user's voice.

It powers interfaces where a robot turns toward the user, a vehicle distinguishes speech by seat, or a multi-directional smart device responds toward the speaker.

mpDiarization

Tells who spoke when

mpDiarization separates the speech segments of each speaker in multi-party audio.

It organizes per-speaker utterances in meeting minutes, consultation records, and voice chat, and attaches speaker identity to the text produced by mpASR.

mpASR

Noise-robust, on-device end-to-end ASR

mpASR is mpWAV's speech recognition technology, designed to run on servers, PCs, smart devices, and IoT/edge environments.

It supports domain fine-tuning for your product's terminology, menu names, and command set, and combines with mpWAV's speech enhancement front end.

mpLLM

An on-device language model that understands dialogue inside the product

mpLLM is a conversational language model that connects user intent, dialogue context, and product functions on top of the text produced by mpASR.

Built on a 1B-class on-device model direction, it implements product-specific dialogue flows — such as kiosk voice ordering — while reducing network dependence.