Part Number: TMS320C5545
Hello,
I'm wondering if someone can help me with the selection of an appropriate DSP for my application.
My application requires far-field voice technology. I am using 4 analog MEMS microphone in a circular array (the mics are Vesper's VM1010 piezo MEMS with 'wake-on-sound'). For this microphone array I wish to use a DSP to do the appropriate signal pre-processing (specifically: beamforming, echo cancellation, de-reverb, filtering, etc). I am particularly interested in a low-power DSP that can do the job.
I found this : TMS320C5545.
Is it good enough for the task? If not, why not, and can you make recommendations.
I should also mention that I intend to use the DSP, if possible, for wake-word detection (wake word engine is from SNIPS.ai). All ASR (automatic speech recognition), NLU (natural language understanding) and STT (speech-to-text) will be performed on cloud servers.
Any input would be very much appreciated.
Thanks
Sam