torchaudio.functional¶
Functions to perform common audio operations.
Utility¶
amplitude_to_DB¶

torchaudio.functional.
amplitude_to_DB
(x: torch.Tensor, multiplier: float, amin: float, db_multiplier: float, top_db: Optional[float] = None) → torch.Tensor[source]¶ Turn a spectrogram from the power/amplitude scale to the decibel scale.
The output of each tensor in a batch depends on the maximum value of that tensor, and so may return different values for an audio clip split into snippets vs. a full clip.
 Parameters
x (Tensor) – Input spectrogram(s) before being converted to decibel scale. Input should take the form (…, freq, time). Batched inputs should include a channel dimension and have the form (batch, channel, freq, time).
multiplier (float) – Use 10. for power and 20. for amplitude
amin (float) – Number to clamp
x
db_multiplier (float) – Log10(max(reference value and amin))
top_db (float or None, optional) – Minimum negative cutoff in decibels. A reasonable number is 80. (Default:
None
)
 Returns
Output tensor in decibel scale
 Return type
Tensor
DB_to_amplitude¶
create_fb_matrix¶

torchaudio.functional.
create_fb_matrix
(n_freqs: int, f_min: float, f_max: float, n_mels: int, sample_rate: int, norm: Optional[str] = None, mel_scale: str = 'htk') → torch.Tensor[source]¶ Create a frequency bin conversion matrix.
 Parameters
n_freqs (int) – Number of frequencies to highlight/apply
f_min (float) – Minimum frequency (Hz)
f_max (float) – Maximum frequency (Hz)
n_mels (int) – Number of mel filterbanks
sample_rate (int) – Sample rate of the audio waveform
norm (Optional[str]) – If ‘slaney’, divide the triangular mel weights by the width of the mel band
normalization). (Default ((area) –
None
)mel_scale (str, optional) – Scale to use:
htk
orslaney
. (Default:htk
)
 Returns
Triangular filter banks (fb matrix) of size (
n_freqs
,n_mels
) meaning number of frequencies to highlight/apply to x the number of filterbanks. Each column is a filterbank so that assuming there is a matrix A of size (…,n_freqs
), the applied result would beA * create_fb_matrix(A.size(1), ...)
. Return type
Tensor
create_dct¶
mask_along_axis¶

torchaudio.functional.
mask_along_axis
(specgram: torch.Tensor, mask_param: int, mask_value: float, axis: int) → torch.Tensor[source]¶ Apply a mask along
axis
. Mask will be applied from indices[v_0, v_0 + v)
, wherev
is sampled fromuniform(0, mask_param)
, andv_0
fromuniform(0, max_v  v)
. All examples will have the same mask interval. Parameters
 Returns
Masked spectrogram of dimensions (channel, freq, time)
 Return type
Tensor
mask_along_axis_iid¶

torchaudio.functional.
mask_along_axis_iid
(specgrams: torch.Tensor, mask_param: int, mask_value: float, axis: int) → torch.Tensor[source]¶ Apply a mask along
axis
. Mask will be applied from indices[v_0, v_0 + v)
, wherev
is sampled fromuniform(0, mask_param)
, andv_0
fromuniform(0, max_v  v)
. Parameters
 Returns
Masked spectrograms of dimensions (batch, channel, freq, time)
 Return type
Tensor
mu_law_encoding¶

torchaudio.functional.
mu_law_encoding
(x: torch.Tensor, quantization_channels: int) → torch.Tensor[source]¶ Encode signal based on mulaw companding. For more info see the Wikipedia Entry
This algorithm assumes the signal has been scaled to between 1 and 1 and returns a signal encoded with values from 0 to quantization_channels  1.
 Parameters
x (Tensor) – Input tensor
quantization_channels (int) – Number of channels
 Returns
Input after mulaw encoding
 Return type
Tensor
mu_law_decoding¶

torchaudio.functional.
mu_law_decoding
(x_mu: torch.Tensor, quantization_channels: int) → torch.Tensor[source]¶ Decode mulaw encoded signal. For more info see the Wikipedia Entry
This expects an input with values between 0 and quantization_channels  1 and returns a signal scaled between 1 and 1.
 Parameters
x_mu (Tensor) – Input tensor
quantization_channels (int) – Number of channels
 Returns
Input after mulaw decoding
 Return type
Tensor
apply_codec¶

torchaudio.functional.
apply_codec
(waveform: torch.Tensor, sample_rate: int, format: str, channels_first: bool = True, compression: Optional[float] = None, encoding: Optional[str] = None, bits_per_sample: Optional[int] = None) → torch.Tensor[source]¶ Apply codecs as a form of augmentation.
 Parameters
waveform (Tensor) – Audio data. Must be 2 dimensional. See also
`channels_first`
.sample_rate (int) – Sample rate of the audio waveform.
format (str) – File format.
channels_first (bool) – When True, both the input and output Tensor have dimension
[channel, time]
. Otherwise, they have dimension[time, channel]
.compression (float) – Used for formats other than WAV. For more details see
torchaudio.backend.sox_io_backend.save()
.encoding (str, optional) – Changes the encoding for the supported formats. For more details see
torchaudio.backend.sox_io_backend.save()
.bits_per_sample (int, optional) – Changes the bit depth for the supported formats. For more details see
torchaudio.backend.sox_io_backend.save()
.
 Returns
Resulting Tensor. If
channels_first=True
, it has[channel, time]
else[time, channel]
. Return type
resample¶

torchaudio.functional.
resample
(waveform: torch.Tensor, orig_freq: float, new_freq: float, lowpass_filter_width: int = 6, rolloff: float = 0.99, resampling_method: str = 'sinc_interpolation', beta: Optional[float] = None) → torch.Tensor[source]¶ Resamples the waveform at the new frequency using bandlimited interpolation.
https://ccrma.stanford.edu/~jos/resample/Theory_Ideal_Bandlimited_Interpolation.html
Note
transforms.Resample
precomputes and reuses the resampling kernel, so using it will result in more efficient computation if resampling multiple waveforms with the same resampling parameters. Parameters
waveform (Tensor) – The input signal of dimension (…, time)
orig_freq (float) – The original frequency of the signal
new_freq (float) – The desired frequency
lowpass_filter_width (int, optional) – Controls the sharpness of the filter, more == sharper but less efficient. (Default:
6
)rolloff (float, optional) – The rolloff frequency of the filter, as a fraction of the Nyquist. Lower values reduce antialiasing, but also reduce some of the highest frequencies. (Default:
0.99
)resampling_method (str, optional) – The resampling method to use. Options: [
sinc_interpolation
,kaiser_window
] (Default:'sinc_interpolation'
)beta (float or None) – The shape parameter used for kaiser window.
 Returns
The waveform at the new frequency of dimension (…, time).
 Return type
Tensor
Complex Utility¶
Utilities for pseudo complex tensor. This is not for the native complex dtype, such as cfloat64, but for tensors with realvalue type and have extra dimension at the end for real and imaginary parts.
angle¶
complex_norm¶

torchaudio.functional.
complex_norm
(complex_tensor: torch.Tensor, power: float = 1.0) → torch.Tensor[source]¶ Compute the norm of complex tensor input.
 Parameters
complex_tensor (Tensor) – Tensor shape of (…, complex=2)
power (float) – Power of the norm. (Default: 1.0).
 Returns
Power of the normed input tensor. Shape of (…, )
 Return type
Tensor
magphase¶

torchaudio.functional.
magphase
(complex_tensor: torch.Tensor, power: float = 1.0) → Tuple[torch.Tensor, torch.Tensor][source]¶ Separate a complexvalued spectrogram with shape (…, 2) into its magnitude and phase.
 Parameters
complex_tensor (Tensor) – Tensor shape of (…, complex=2)
power (float) – Power of the norm. (Default: 1.0)
 Returns
The magnitude and phase of the complex tensor
 Return type
(Tensor, Tensor)
Filtering¶
allpass_biquad¶

torchaudio.functional.
allpass_biquad
(waveform: torch.Tensor, sample_rate: int, central_freq: float, Q: float = 0.707) → torch.Tensor[source]¶ Design twopole allpass filter. Similar to SoX implementation.
 Parameters
waveform (torch.Tensor) – audio waveform of dimension of (…, time)
sample_rate (int) – sampling rate of the waveform, e.g. 44100 (Hz)
central_freq (float or torch.Tensor) – central frequency (in Hz)
Q (float or torch.Tensor, optional) – https://en.wikipedia.org/wiki/Q_factor (Default:
0.707
)
 Returns
Waveform of dimension of (…, time)
 Return type
Tensor
band_biquad¶

torchaudio.functional.
band_biquad
(waveform: torch.Tensor, sample_rate: int, central_freq: float, Q: float = 0.707, noise: bool = False) → torch.Tensor[source]¶ Design twopole band filter. Similar to SoX implementation.
 Parameters
waveform (Tensor) – audio waveform of dimension of (…, time)
sample_rate (int) – sampling rate of the waveform, e.g. 44100 (Hz)
central_freq (float or torch.Tensor) – central frequency (in Hz)
Q (float or torch.Tensor, optional) – https://en.wikipedia.org/wiki/Q_factor (Default:
0.707
).noise (bool, optional) – If
True
, uses the alternate mode for unpitched audio (e.g. percussion). IfFalse
, uses mode oriented to pitched audio, i.e. voice, singing, or instrumental music (Default:False
).
 Returns
Waveform of dimension of (…, time)
 Return type
Tensor
bandpass_biquad¶

torchaudio.functional.
bandpass_biquad
(waveform: torch.Tensor, sample_rate: int, central_freq: float, Q: float = 0.707, const_skirt_gain: bool = False) → torch.Tensor[source]¶ Design twopole bandpass filter. Similar to SoX implementation.
 Parameters
waveform (Tensor) – audio waveform of dimension of (…, time)
sample_rate (int) – sampling rate of the waveform, e.g. 44100 (Hz)
central_freq (float or torch.Tensor) – central frequency (in Hz)
Q (float or torch.Tensor, optional) – https://en.wikipedia.org/wiki/Q_factor (Default:
0.707
)const_skirt_gain (bool, optional) – If
True
, uses a constant skirt gain (peak gain = Q). IfFalse
, uses a constant 0dB peak gain. (Default:False
)
 Returns
Waveform of dimension of (…, time)
 Return type
Tensor
bandreject_biquad¶

torchaudio.functional.
bandreject_biquad
(waveform: torch.Tensor, sample_rate: int, central_freq: float, Q: float = 0.707) → torch.Tensor[source]¶ Design twopole bandreject filter. Similar to SoX implementation.
 Parameters
waveform (Tensor) – audio waveform of dimension of (…, time)
sample_rate (int) – sampling rate of the waveform, e.g. 44100 (Hz)
central_freq (float or torch.Tensor) – central frequency (in Hz)
Q (float or torch.Tensor, optional) – https://en.wikipedia.org/wiki/Q_factor (Default:
0.707
)
 Returns
Waveform of dimension of (…, time)
 Return type
Tensor
bass_biquad¶

torchaudio.functional.
bass_biquad
(waveform: torch.Tensor, sample_rate: int, gain: float, central_freq: float = 100, Q: float = 0.707) → torch.Tensor[source]¶ Design a bass tonecontrol effect. Similar to SoX implementation.
 Parameters
waveform (Tensor) – audio waveform of dimension of (…, time)
sample_rate (int) – sampling rate of the waveform, e.g. 44100 (Hz)
gain (float or torch.Tensor) – desired gain at the boost (or attenuation) in dB.
central_freq (float or torch.Tensor, optional) – central frequency (in Hz). (Default:
100
)Q (float or torch.Tensor, optional) – https://en.wikipedia.org/wiki/Q_factor (Default:
0.707
).
 Returns
Waveform of dimension of (…, time)
 Return type
Tensor
biquad¶

torchaudio.functional.
biquad
(waveform: torch.Tensor, b0: float, b1: float, b2: float, a0: float, a1: float, a2: float) → torch.Tensor[source]¶ Perform a biquad filter of input tensor. Initial conditions set to 0. https://en.wikipedia.org/wiki/Digital_biquad_filter
 Parameters
waveform (Tensor) – audio waveform of dimension of (…, time)
b0 (float or torch.Tensor) – numerator coefficient of current input, x[n]
b1 (float or torch.Tensor) – numerator coefficient of input one time step ago x[n1]
b2 (float or torch.Tensor) – numerator coefficient of input two time steps ago x[n2]
a0 (float or torch.Tensor) – denominator coefficient of current output y[n], typically 1
a1 (float or torch.Tensor) – denominator coefficient of current output y[n1]
a2 (float or torch.Tensor) – denominator coefficient of current output y[n2]
 Returns
Waveform with dimension of (…, time)
 Return type
Tensor
contrast¶

torchaudio.functional.
contrast
(waveform: torch.Tensor, enhancement_amount: float = 75.0) → torch.Tensor[source]¶ Apply contrast effect. Similar to SoX implementation. Comparable with compression, this effect modifies an audio signal to make it sound louder
 Parameters
waveform (Tensor) – audio waveform of dimension of (…, time)
enhancement_amount (float) – controls the amount of the enhancement Allowed range of values for enhancement_amount : 0100 Note that enhancement_amount = 0 still gives a significant contrast enhancement
 Returns
Waveform of dimension of (…, time)
 Return type
Tensor
 Reference:
dcshift¶

torchaudio.functional.
dcshift
(waveform: torch.Tensor, shift: float, limiter_gain: Optional[float] = None) → torch.Tensor[source]¶ Apply a DC shift to the audio. Similar to SoX implementation. This can be useful to remove a DC offset (caused perhaps by a hardware problem in the recording chain) from the audio
 Parameters
 Returns
Waveform of dimension of (…, time)
 Return type
Tensor
 Reference:
deemph_biquad¶

torchaudio.functional.
deemph_biquad
(waveform: torch.Tensor, sample_rate: int) → torch.Tensor[source]¶ Apply ISO 908 CD deemphasis (shelving) IIR filter. Similar to SoX implementation.
 Parameters
waveform (Tensor) – audio waveform of dimension of (…, time)
sample_rate (int) – sampling rate of the waveform, Allowed sample rate
44100
or48000
 Returns
Waveform of dimension of (…, time)
 Return type
Tensor
dither¶

torchaudio.functional.
dither
(waveform: torch.Tensor, density_function: str = 'TPDF', noise_shaping: bool = False) → torch.Tensor[source]¶ Dither increases the perceived dynamic range of audio stored at a particular bitdepth by eliminating nonlinear truncation distortion (i.e. adding minimally perceived noise to mask distortion caused by quantization).
 Parameters
waveform (Tensor) – Tensor of audio of dimension (…, time)
density_function (str, optional) – The density function of a continuous random variable. One of
"TPDF"
(Triangular Probability Density Function),"RPDF"
(Rectangular Probability Density Function) or"GPDF"
(Gaussian Probability Density Function) (Default:"TPDF"
).noise_shaping (bool, optional) – a filtering process that shapes the spectral energy of quantisation error (Default:
False
)
 Returns
waveform dithered
 Return type
Tensor
equalizer_biquad¶

torchaudio.functional.
equalizer_biquad
(waveform: torch.Tensor, sample_rate: int, center_freq: float, gain: float, Q: float = 0.707) → torch.Tensor[source]¶ Design biquad peaking equalizer filter and perform filtering. Similar to SoX implementation.
 Parameters
waveform (Tensor) – audio waveform of dimension of (…, time)
sample_rate (int) – sampling rate of the waveform, e.g. 44100 (Hz)
center_freq (float) – filter’s central frequency
gain (float or torch.Tensor) – desired gain at the boost (or attenuation) in dB
Q (float or torch.Tensor, optional) – https://en.wikipedia.org/wiki/Q_factor (Default:
0.707
)
 Returns
Waveform of dimension of (…, time)
 Return type
Tensor
flanger¶

torchaudio.functional.
flanger
(waveform: torch.Tensor, sample_rate: int, delay: float = 0.0, depth: float = 2.0, regen: float = 0.0, width: float = 71.0, speed: float = 0.5, phase: float = 25.0, modulation: str = 'sinusoidal', interpolation: str = 'linear') → torch.Tensor[source]¶ Apply a flanger effect to the audio. Similar to SoX implementation.
 Parameters
waveform (Tensor) – audio waveform of dimension of (…, channel, time) . Max 4 channels allowed
sample_rate (int) – sampling rate of the waveform, e.g. 44100 (Hz)
delay (float) – desired delay in milliseconds(ms) Allowed range of values are 0 to 30
depth (float) – desired delay depth in milliseconds(ms) Allowed range of values are 0 to 10
regen (float) – desired regen(feedback gain) in dB Allowed range of values are 95 to 95
width (float) – desired width(delay gain) in dB Allowed range of values are 0 to 100
speed (float) – modulation speed in Hz Allowed range of values are 0.1 to 10
phase (float) – percentage phaseshift for multichannel Allowed range of values are 0 to 100
modulation (str) – Use either “sinusoidal” or “triangular” modulation. (Default:
sinusoidal
)interpolation (str) – Use either “linear” or “quadratic” for delayline interpolation. (Default:
linear
)
 Returns
Waveform of dimension of (…, channel, time)
 Return type
Tensor
 Reference:
Scott Lehman, Effects Explained,
gain¶

torchaudio.functional.
gain
(waveform: torch.Tensor, gain_db: float = 1.0) → torch.Tensor[source]¶ Apply amplification or attenuation to the whole waveform.
 Parameters
waveform (Tensor) – Tensor of audio of dimension (…, time).
gain_db (float, optional) Gain adjustment in decibels (dB) –
1.0
).
 Returns
the whole waveform amplified by gain_db.
 Return type
Tensor
highpass_biquad¶

torchaudio.functional.
highpass_biquad
(waveform: torch.Tensor, sample_rate: int, cutoff_freq: float, Q: float = 0.707) → torch.Tensor[source]¶ Design biquad highpass filter and perform filtering. Similar to SoX implementation.
 Parameters
waveform (Tensor) – audio waveform of dimension of (…, time)
sample_rate (int) – sampling rate of the waveform, e.g. 44100 (Hz)
cutoff_freq (float or torch.Tensor) – filter cutoff frequency
Q (float or torch.Tensor, optional) – https://en.wikipedia.org/wiki/Q_factor (Default:
0.707
)
 Returns
Waveform dimension of (…, time)
 Return type
Tensor
lfilter¶

torchaudio.functional.
lfilter
(waveform: torch.Tensor, a_coeffs: torch.Tensor, b_coeffs: torch.Tensor, clamp: bool = True) → torch.Tensor[source]¶ Perform an IIR filter by evaluating difference equation.
Note
To avoid numerical problems, small filter order is preferred. Using double precision could also minimize numerical precision errors.
 Parameters
waveform (Tensor) – audio waveform of dimension of
(..., time)
. Must be normalized to 1 to 1.a_coeffs (Tensor) – denominator coefficients of difference equation of dimension of
(n_order + 1)
. Lower delays coefficients are first, e.g.[a0, a1, a2, ...]
. Must be same size as b_coeffs (pad with 0’s as necessary).b_coeffs (Tensor) – numerator coefficients of difference equation of dimension of
(n_order + 1)
. Lower delays coefficients are first, e.g.[b0, b1, b2, ...]
. Must be same size as a_coeffs (pad with 0’s as necessary).clamp (bool, optional) – If
True
, clamp the output signal to be in the range [1, 1] (Default:True
)
 Returns
Waveform with dimension of
(..., time)
. Return type
Tensor
lowpass_biquad¶

torchaudio.functional.
lowpass_biquad
(waveform: torch.Tensor, sample_rate: int, cutoff_freq: float, Q: float = 0.707) → torch.Tensor[source]¶ Design biquad lowpass filter and perform filtering. Similar to SoX implementation.
 Parameters
waveform (torch.Tensor) – audio waveform of dimension of (…, time)
sample_rate (int) – sampling rate of the waveform, e.g. 44100 (Hz)
cutoff_freq (float or torch.Tensor) – filter cutoff frequency
Q (float or torch.Tensor, optional) – https://en.wikipedia.org/wiki/Q_factor (Default:
0.707
)
 Returns
Waveform of dimension of (…, time)
 Return type
Tensor
overdrive¶

torchaudio.functional.
overdrive
(waveform: torch.Tensor, gain: float = 20, colour: float = 20) → torch.Tensor[source]¶ Apply a overdrive effect to the audio. Similar to SoX implementation. This effect applies a non linear distortion to the audio signal.
 Parameters
 Returns
Waveform of dimension of (…, time)
 Return type
Tensor
 Reference:
phaser¶

torchaudio.functional.
phaser
(waveform: torch.Tensor, sample_rate: int, gain_in: float = 0.4, gain_out: float = 0.74, delay_ms: float = 3.0, decay: float = 0.4, mod_speed: float = 0.5, sinusoidal: bool = True) → torch.Tensor[source]¶ Apply a phasing effect to the audio. Similar to SoX implementation.
 Parameters
waveform (Tensor) – audio waveform of dimension of (…, time)
sample_rate (int) – sampling rate of the waveform, e.g. 44100 (Hz)
gain_in (float) – desired input gain at the boost (or attenuation) in dB Allowed range of values are 0 to 1
gain_out (float) – desired output gain at the boost (or attenuation) in dB Allowed range of values are 0 to 1e9
delay_ms (float) – desired delay in milliseconds Allowed range of values are 0 to 5.0
decay (float) – desired decay relative to gainin Allowed range of values are 0 to 0.99
mod_speed (float) – modulation speed in Hz Allowed range of values are 0.1 to 2
sinusoidal (bool) – If
True
, uses sinusoidal modulation (preferable for multiple instruments) IfFalse
, uses triangular modulation (gives single instruments a sharper phasing effect) (Default:True
)
 Returns
Waveform of dimension of (…, time)
 Return type
Tensor
 Reference:
Scott Lehman, Effects Explained.
riaa_biquad¶

torchaudio.functional.
riaa_biquad
(waveform: torch.Tensor, sample_rate: int) → torch.Tensor[source]¶ Apply RIAA vinyl playback equalization. Similar to SoX implementation.
 Parameters
waveform (Tensor) – audio waveform of dimension of (…, time)
sample_rate (int) – sampling rate of the waveform, e.g. 44100 (Hz). Allowed sample rates in Hz :
44100
,``48000``,``88200``,``96000``
 Returns
Waveform of dimension of (…, time)
 Return type
Tensor
treble_biquad¶

torchaudio.functional.
treble_biquad
(waveform: torch.Tensor, sample_rate: int, gain: float, central_freq: float = 3000, Q: float = 0.707) → torch.Tensor[source]¶ Design a treble tonecontrol effect. Similar to SoX implementation.
 Parameters
waveform (Tensor) – audio waveform of dimension of (…, time)
sample_rate (int) – sampling rate of the waveform, e.g. 44100 (Hz)
gain (float or torch.Tensor) – desired gain at the boost (or attenuation) in dB.
central_freq (float or torch.Tensor, optional) – central frequency (in Hz). (Default:
3000
)Q (float or torch.Tensor, optional) – https://en.wikipedia.org/wiki/Q_factor (Default:
0.707
).
 Returns
Waveform of dimension of (…, time)
 Return type
Tensor
vad¶
Feature Extractions¶

torchaudio.functional.
vad
(waveform: torch.Tensor, sample_rate: int, trigger_level: float = 7.0, trigger_time: float = 0.25, search_time: float = 1.0, allowed_gap: float = 0.25, pre_trigger_time: float = 0.0, boot_time: float = 0.35, noise_up_time: float = 0.1, noise_down_time: float = 0.01, noise_reduction_amount: float = 1.35, measure_freq: float = 20.0, measure_duration: Optional[float] = None, measure_smooth_time: float = 0.4, hp_filter_freq: float = 50.0, lp_filter_freq: float = 6000.0, hp_lifter_freq: float = 150.0, lp_lifter_freq: float = 2000.0) → torch.Tensor[source]¶ Voice Activity Detector. Similar to SoX implementation. Attempts to trim silence and quiet background sounds from the ends of recordings of speech. The algorithm currently uses a simple cepstral power measurement to detect voice, so may be fooled by other things, especially music.
The effect can trim only from the front of the audio, so in order to trim from the back, the reverse effect must also be used.
 Parameters
waveform (Tensor) – Tensor of audio of dimension (channels, time) or (time) Tensor of shape (channels, time) is treated as a multichannel recording of the same event and the resulting output will be trimmed to the earliest voice activity in any channel.
sample_rate (int) – Sample rate of audio signal.
trigger_level (float, optional) – The measurement level used to trigger activity detection. This may need to be cahnged depending on the noise level, signal level, and other characteristics of the input audio. (Default: 7.0)
trigger_time (float, optional) – The time constant (in seconds) used to help ignore short bursts of sound. (Default: 0.25)
search_time (float, optional) – The amount of audio (in seconds) to search for quieter/shorter bursts of audio to include prior to the detected trigger point. (Default: 1.0)
allowed_gap (float, optional) – The allowed gap (in seconds) between quieter/shorter bursts of audio to include prior to the detected trigger point. (Default: 0.25)
pre_trigger_time (float, optional) – The amount of audio (in seconds) to preserve before the trigger point and any found quieter/shorter bursts. (Default: 0.0)
boot_time (float, optional) The algorithm (internally) – estimation/reduction in order to detect the start of the wanted audio. This option sets the time for the initial noise estimate. (Default: 0.35)
noise_up_time (float, optional) – for when the noise level is increasing. (Default: 0.1)
noise_down_time (float, optional) – for when the noise level is decreasing. (Default: 0.01)
noise_reduction_amount (float, optional) – the detection algorithm (e.g. 0, 0.5, …). (Default: 1.35)
measure_freq (float, optional) – processing/measurements. (Default: 20.0)
measure_duration – (float, optional) Measurement duration. (Default: Twice the measurement period; i.e. with overlap.)
measure_smooth_time (float, optional) – spectral measurements. (Default: 0.4)
hp_filter_freq (float, optional) – at the input to the detector algorithm. (Default: 50.0)
lp_filter_freq (float, optional) – at the input to the detector algorithm. (Default: 6000.0)
hp_lifter_freq (float, optional) – in the detector algorithm. (Default: 150.0)
lp_lifter_freq (float, optional) – in the detector algorithm. (Default: 2000.0)
 Returns
Tensor of audio of dimension (…, time).
 Return type
Tensor
 Reference:
spectrogram¶

torchaudio.functional.
spectrogram
(waveform: torch.Tensor, pad: int, window: torch.Tensor, n_fft: int, hop_length: int, win_length: int, power: Optional[float], normalized: bool, center: bool = True, pad_mode: str = 'reflect', onesided: bool = True, return_complex: bool = False) → torch.Tensor[source]¶ Create a spectrogram or a batch of spectrograms from a raw audio signal. The spectrogram can be either magnitudeonly or complex.
 Parameters
waveform (Tensor) – Tensor of audio of dimension (…, time)
pad (int) – Two sided padding of signal
window (Tensor) – Window tensor that is applied/multiplied to each frame/window
n_fft (int) – Size of FFT
hop_length (int) – Length of hop between STFT windows
win_length (int) – Window size
power (float or None) – Exponent for the magnitude spectrogram, (must be > 0) e.g., 1 for energy, 2 for power, etc. If None, then the complex spectrum is returned instead.
normalized (bool) – Whether to normalize by magnitude after stft
center (bool, optional) – whether to pad
waveform
on both sides so that the \(t\)th frame is centered at time \(t \times \text{hop\_length}\). Default:True
pad_mode (string, optional) – controls the padding method used when
center
isTrue
. Default:"reflect"
onesided (bool, optional) – controls whether to return half of results to avoid redundancy. Default:
True
return_complex (bool, optional) – Indicates whether the resulting complexvalued Tensor should be represented with native complex dtype, such as torch.cfloat and torch.cdouble, or real dtype mimicking complex value with an extra dimension for real and imaginary parts. This argument is only effective when
power=None
. See alsotorch.view_as_real
.
 Returns
Dimension (…, freq, time), freq is
n_fft // 2 + 1
andn_fft
is the number of Fourier bins, and time is the number of window hops (n_frame). Return type
Tensor
griffinlim¶

torchaudio.functional.
griffinlim
(specgram: torch.Tensor, window: torch.Tensor, n_fft: int, hop_length: int, win_length: int, power: float, n_iter: int, momentum: float, length: Optional[int], rand_init: bool) → torch.Tensor[source]¶ Compute waveform from a linear scale magnitude spectrogram using the GriffinLim transformation.
Implementation ported from 1, 2 and 3.
 Parameters
specgram (Tensor) – A magnitudeonly STFT spectrogram of dimension (…, freq, frames) where freq is
n_fft // 2 + 1
.window (Tensor) – Window tensor that is applied/multiplied to each frame/window
n_fft (int) – Size of FFT, creates
n_fft // 2 + 1
binshop_length (int) – Length of hop between STFT windows. ( Default:
win_length // 2
)win_length (int) – Window size. (Default:
n_fft
)power (float) – Exponent for the magnitude spectrogram, (must be > 0) e.g., 1 for energy, 2 for power, etc.
n_iter (int) – Number of iteration for phase recovery process.
momentum (float) – The momentum parameter for fast GriffinLim. Setting this to 0 recovers the original GriffinLim method. Values near 1 can lead to faster convergence, but above 1 may not converge.
rand_init (bool) – Initializes phase randomly if True, to zero otherwise.
 Returns
waveform of (…, time), where time equals the
length
parameter if given. Return type
phase_vocoder¶

torchaudio.functional.
phase_vocoder
(complex_specgrams: torch.Tensor, rate: float, phase_advance: torch.Tensor) → torch.Tensor[source]¶ Given a STFT tensor, speed up in time without modifying pitch by a factor of
rate
. Parameters
complex_specgrams (Tensor) – Either a real tensor of dimension of
(..., freq, num_frame, complex=2)
or a tensor of dimension(..., freq, num_frame)
with complex dtype.rate (float) – Speedup factor
phase_advance (Tensor) – Expected phase advance in each bin. Dimension of (freq, 1)
 Returns
Stretched spectrogram. The resulting tensor is of the same dtype as the input spectrogram, but the number of frames is changed to
ceil(num_frame / rate)
. Return type
Tensor
 Example  With Tensor of complex dtype
>>> freq, hop_length = 1025, 512 >>> # (channel, freq, time) >>> complex_specgrams = torch.randn(2, freq, 300, dtype=torch.cfloat) >>> rate = 1.3 # Speed up by 30% >>> phase_advance = torch.linspace( >>> 0, math.pi * hop_length, freq)[..., None] >>> x = phase_vocoder(complex_specgrams, rate, phase_advance) >>> x.shape # with 231 == ceil(300 / 1.3) torch.Size([2, 1025, 231])
 Example  With Tensor of real dtype and extra dimension for complex field
>>> freq, hop_length = 1025, 512 >>> # (channel, freq, time, complex=2) >>> complex_specgrams = torch.randn(2, freq, 300, 2) >>> rate = 1.3 # Speed up by 30% >>> phase_advance = torch.linspace( >>> 0, math.pi * hop_length, freq)[..., None] >>> x = phase_vocoder(complex_specgrams, rate, phase_advance) >>> x.shape # with 231 == ceil(300 / 1.3) torch.Size([2, 1025, 231, 2])
compute_deltas¶

torchaudio.functional.
compute_deltas
(specgram: torch.Tensor, win_length: int = 5, mode: str = 'replicate') → torch.Tensor[source]¶ Compute delta coefficients of a tensor, usually a spectrogram:
\[d_t = \frac{\sum_{n=1}^{\text{N}} n (c_{t+n}  c_{tn})}{2 \sum_{n=1}^{\text{N}} n^2} \]where \(d_t\) is the deltas at time \(t\), \(c_t\) is the spectrogram coeffcients at time \(t\), \(N\) is
(win_length1)//2
. Parameters
 Returns
Tensor of deltas of dimension (…, freq, time)
 Return type
Tensor
 Example
>>> specgram = torch.randn(1, 40, 1000) >>> delta = compute_deltas(specgram) >>> delta2 = compute_deltas(delta)
detect_pitch_frequency¶

torchaudio.functional.
detect_pitch_frequency
(waveform: torch.Tensor, sample_rate: int, frame_time: float = 0.01, win_length: int = 30, freq_low: int = 85, freq_high: int = 3400) → torch.Tensor[source]¶ Detect pitch frequency.
It is implemented using normalized crosscorrelation function and median smoothing.
 Parameters
waveform (Tensor) – Tensor of audio of dimension (…, freq, time)
sample_rate (int) – The sample rate of the waveform (Hz)
frame_time (float, optional) – Duration of a frame (Default:
10 ** (2)
).win_length (int, optional) – The window length for median smoothing (in number of frames) (Default:
30
).freq_low (int, optional) – Lowest frequency that can be detected (Hz) (Default:
85
).freq_high (int, optional) – Highest frequency that can be detected (Hz) (Default:
3400
).
 Returns
Tensor of freq of dimension (…, frame)
 Return type
Tensor
sliding_window_cmn¶

torchaudio.functional.
sliding_window_cmn
(specgram: torch.Tensor, cmn_window: int = 600, min_cmn_window: int = 100, center: bool = False, norm_vars: bool = False) → torch.Tensor[source]¶ Apply slidingwindow cepstral mean (and optionally variance) normalization per utterance.
 Parameters
specgram (Tensor) – Tensor of audio of dimension (…, time, freq)
cmn_window (int, optional) – Window in frames for running average CMN computation (int, default = 600)
min_cmn_window (int, optional) – Minimum CMN window used at start of decoding (adds latency only at start). Only applicable if center == false, ignored if center==true (int, default = 100)
center (bool, optional) – If true, use a window centered on the current frame (to the extent possible, modulo end effects). If false, window is to the left. (bool, default = false)
norm_vars (bool, optional) – If true, normalize variance to one. (bool, default = false)
 Returns
Tensor matching input shape (…, freq, time)
 Return type
Tensor
compute_kaldi_pitch¶

torchaudio.functional.
compute_kaldi_pitch
(waveform: torch.Tensor, sample_rate: float, frame_length: float = 25.0, frame_shift: float = 10.0, min_f0: float = 50, max_f0: float = 400, soft_min_f0: float = 10.0, penalty_factor: float = 0.1, lowpass_cutoff: float = 1000, resample_frequency: float = 4000, delta_pitch: float = 0.005, nccf_ballast: float = 7000, lowpass_filter_width: int = 1, upsample_filter_width: int = 5, max_frames_latency: int = 0, frames_per_chunk: int = 0, simulate_first_pass_online: bool = False, recompute_frame: int = 500, snip_edges: bool = True) → torch.Tensor[source]¶ Extract pitch based on method described in 4.
This function computes the equivalent of computekaldipitchfeats from Kaldi.
 Parameters
waveform (Tensor) – The input waveform of shape (…, time).
sample_rate (float) – Sample rate of waveform.
frame_length (float, optional) – Frame length in milliseconds. (default: 25.0)
frame_shift (float, optional) – Frame shift in milliseconds. (default: 10.0)
min_f0 (float, optional) – Minimum F0 to search for (Hz) (default: 50.0)
max_f0 (float, optional) – Maximum F0 to search for (Hz) (default: 400.0)
soft_min_f0 (float, optional) – Minimum f0, applied in soft way, must not exceed minf0 (default: 10.0)
penalty_factor (float, optional) – Cost factor for FO change. (default: 0.1)
lowpass_cutoff (float, optional) – Cutoff frequency for LowPass filter (Hz) (default: 1000)
resample_frequency (float, optional) – Frequency that we downsample the signal to. Must be more than twice lowpasscutoff. (default: 4000)
delta_pitch (float, optional) – Smallest relative change in pitch that our algorithm measures. (default: 0.005)
nccf_ballast (float, optional) – Increasing this factor reduces NCCF for quiet frames (default: 7000)
lowpass_filter_width (int, optional) – Integer that determines filter width of lowpass filter, more gives sharper filter. (default: 1)
upsample_filter_width (int, optional) – Integer that determines filter width when upsampling NCCF. (default: 5)
max_frames_latency (int, optional) – Maximum number of frames of latency that we allow pitch tracking to introduce into the feature processing (affects output only if
frames_per_chunk > 0
andsimulate_first_pass_online=True
) (default: 0)frames_per_chunk (int, optional) – The number of frames used for energy normalization. (default: 0)
simulate_first_pass_online (bool, optional) – If true, the function will output features that correspond to what an online decoder would see in the first pass of decoding – not the final version of the features, which is the default. (default: False) Relevant if
frames_per_chunk > 0
.recompute_frame (int, optional) – Only relevant for compatibility with online pitch extraction. A noncritical parameter; the frame at which we recompute some of the forward pointers, after revising our estimate of the signal energy. Relevant if
frames_per_chunk > 0
. (default: 500)snip_edges (bool, optional) – If this is set to false, the incomplete frames near the ending edge won’t be snipped, so that the number of frames is the file size divided by the frameshift. This makes different types of features give the same number of frames. (default: True)
 Returns
Pitch feature. Shape:
(batch, frames 2)
where the last dimension corresponds to pitch and NCCF. Return type
Tensor
spectral_centroid¶

torchaudio.functional.
spectral_centroid
(waveform: torch.Tensor, sample_rate: int, pad: int, window: torch.Tensor, n_fft: int, hop_length: int, win_length: int) → torch.Tensor[source]¶ Compute the spectral centroid for each channel along the time axis.
The spectral centroid is defined as the weighted average of the frequency values, weighted by their magnitude.
 Parameters
waveform (Tensor) – Tensor of audio of dimension (…, time)
sample_rate (int) – Sample rate of the audio waveform
pad (int) – Two sided padding of signal
window (Tensor) – Window tensor that is applied/multiplied to each frame/window
n_fft (int) – Size of FFT
hop_length (int) – Length of hop between STFT windows
win_length (int) – Window size
 Returns
Dimension (…, time)
 Return type
Tensor
References¶
 1
Brian McFee, Colin Raffel, Dawen Liang, Daniel P.W. Ellis, Matt McVicar, Eric Battenberg, and Oriol Nieto. Librosa: Audio and Music Signal Analysis in Python. In Kathryn Huff and James Bergstra, editors, Proceedings of the 14th Python in Science Conference, 18 – 24. 2015. doi:10.25080/Majora7b98e3ed003.
 2
Nathanaël Perraudin, Peter Balazs, and Peter L. Søndergaard. A fast griffinlim algorithm. In 2013 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, volume, 1–4. 2013. doi:10.1109/WASPAA.2013.6701851.
 3
D. Griffin and Jae Lim. Signal estimation from modified shorttime fourier transform. In ICASSP ‘83. IEEE International Conference on Acoustics, Speech, and Signal Processing, volume 8, 804–807. 1983. doi:10.1109/ICASSP.1983.1172092.
 4
Pegah Ghahremani, Bagher BabaAli, Daniel Povey, Korbinian Riedhammer, Jan Trmal, and Sanjeev Khudanpur. A pitch extraction algorithm tuned for automatic speech recognition. In 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), volume, 2494–2498. 2014. doi:10.1109/ICASSP.2014.6854049.