aTENNuate: Optimized Real-time Speech Enhancement with Deep SSMs on RawAudio
By Yan Ru Pei, Ritik Shrivastava, FNU Sidharth (BrainChip)
Abstract
We present aTENNuate, a simple deep state-space autoencoder configured for efficient online raw speech enhancement in an end-to-end fashion. The network’s performance is primarily evaluated on raw speech denoising, with additional assessments on tasks such as super-resolution and de-quantization. We benchmark aTENNuate on the VoiceBank + DEMAND and the Microsoft DNS1 synthetic test sets. The network outperforms previous real-time denoising models in terms of PESQ score, parameter count, MACs, and latency. Even as a raw waveform processing model, the model maintains high fidelity to the clean signal with minimal audible artifacts. In addition, the model remains performant even when the noisy input is compressed down to 4000Hz and 4 bits, suggesting general speech enhancement capabilities in low-resource environments.
keywords: state-space models, autoencoder, denoising, super-resolution, de-quantization
To read the full article, click here
Related Semiconductor IP
Related Articles
- VLSI Based On Two-Dimensional Reconfigurable Array Of Processor Elements And Theirs Implementation For Numerical Algorithms In Real-Time Systems
- ASIC Implementation of a Speech Detector IP-Core for Real-Time Speaker Verification
- A Realtime 1080P30 H.264 Encoder System on a Zynq Device
- Delivering High Quality Analog Video Signals With Optimized Video DACs
Latest Articles
- A 14ns-Latency 9Gb/s 0.44mm² 62pJ/b Short-Blocklength LDPC Decoder ASIC in 22FDX
- Pipeline Stage Resolved Timing Characterization of FPGA and ASIC Implementations of a RISC V Processor
- Lyra: A Hardware-Accelerated RISC-V Verification Framework with Generative Model-Based Processor Fuzzing
- Leveraging FPGAs for Homomorphic Matrix-Vector Multiplication in Oblivious Message Retrieval
- Extending and Accelerating Inner Product Masking with Fault Detection via Instruction Set Extension