noisyspeech_synthesizer.cfg

# Configuration for generating Noisy Speech Dataset

# - sampling_rate: Specify the sampling rate. Default is 16 kHz
# - audioformat: default is .wav
# - audio_length: Minimum Length of each audio clip (noisy and clean speech) in seconds that will be generated by augmenting utterances. 
# - silence_length: Duration of silence introduced between clean speech utterances.
# - total_hours: Total number of hours of data required. Units are in hours. 
# - snr_lower: Lower bound for SNR required (default: 0 dB)
# - snr_upper: Upper bound for SNR required (default: 40 dB)
# - total_snrlevels: Number of SNR levels required (default: 5, which means there are 5 levels between snr_lower and snr_upper)
# - noise_dir: Default is None. But specify the noise directory path if noise files are not in the source directory
# - Speech_dir: Default is None. But specify the speech directory path if speech files are not in the source directory
# - noise_types_excluded: Noise files starting with the following tags to be excluded in the noise list. Example: noise_types_excluded: Babble, AirConditioner
#                         Specify 'None' if no noise files to be excluded.

[noisy_speech_train]

sampling_rate: 16000
audioformat: *.wav
audio_length: 10
silence_lower: 0.2
silence_upper: 3.0
total_hours: 10
snr_lower: 0
snr_upper: 40
total_snrlevels: 5

output_dir: noisy_speech_train
noise_dir: None
speech_dir: None
noise_types_excluded: None

[noisy_speech_test]

sampling_rate: 16000
audioformat: *.wav
audio_length: 10
silence_lower: 0.2
silence_upper: 3.0
total_hours: 2
snr_lower: 0
snr_upper: 40
total_snrlevels: 5

output_dir: noisy_speech_test
noise_dir: noise_test
speech_dir: clean_test
noise_types_excluded: None