Mozilla RNNoise Noise Suppression Benchmark

Prerequisites

• Ubuntu 20.04 (x86_64)
• FFmpeg
• Git
• Python 3
• PIP
• Picovoice Console Account

Usage

1. Clone the repository:

git clone https://github.com/Picovoice/noise-suppression-benchmark.git
cd noise-suppression-benchmark

2. Install the dependencies:

pip3 install -r requirements.txt

3. Follow the instructions in README.md to obtain the Interspeech2020 dataset for the benchmark.

4. Clone and build the RNNoise repository from https://gitlab.xiph.org/xiph/rnnoise:

git clone [email protected]:xiph/rnnoise.git
cd rnnoise
./autogen.sh
./configure
make

5. From the root folder of the benchmark repository, run the benchmark script:

python3 benchmark.py \
--engine mozilla_rnnoise \
--dataset Interspeech2020 \
--data-folder ${PATH_TO_DNS_CHALLENGE_FOLDER}/datasets/test_set/synthetic/no_reverb \
--rnnoise-demo-path ${PATH_TO_RNNOISE}/examples/rnnoise_demo

Replace ${PATH_TO_DNS_CHALLENGE_FOLDER} with the path to the main folder of the DNS Challenge repository that you cloned to obtain the data, and ${PATH_TO_RNNOISE} with the main folder of the RNNoise repository.

By default, the command uses the original mix of clean speech and noise as given by the dataset. To evaluate the performance at a specific noise level, the benchmark can also re-mix the data at a custom signal-to-noise ratio (SNR). Simply repeat the command above with an additional argument --remix-snr-db ${SNR_DB}, where ${SNR_DB} is replaced with the SNR in decibels (dB).