Module: tfio.audio

View source on GitHub

tensorflow_io.audio

Classes

class AudioIODataset: AudioIODataset

class AudioIOTensor: AudioIOTensor

Functions

dbscale(...): Turn spectrogram into db scale

decode_aac(...): Decode MP4 (AAC) audio from input string.

decode_flac(...): Decode Flac audio from input string.

decode_mp3(...): Decode MP3 audio from input string.

decode_vorbis(...): Decode Ogg(Vorbis) audio from input string.

decode_wav(...): Decode WAV audio from input string.

encode_aac(...): Encode MP4(AAC) audio into string.

encode_flac(...): Encode Flac audio into string.

encode_mp3(...): Encode MP3 audio into string.

encode_vorbis(...): Encode Ogg(Vorbis) audio into string.

encode_wav(...): Encode WAV audio into string.

fade(...): Apply fade in/out to audio.

freq_mask(...): Apply masking to a spectrogram in the freq domain.

inverse_spectrogram(...): Generate audio waveform from spectrogram using Griffin-Lim algorithm.

melscale(...): Turn spectrogram into mel scale spectrogram

remix(...): Remix the audio from segments indices.

resample(...): Resample audio.

spectrogram(...): Create spectrogram from audio.

split(...): Split the audio by removing the noise smaller than epsilon.

time_mask(...): Apply masking to a spectrogram in the time domain.

trim(...): Trim the noise from beginning and end of the audio.