Posit AI Weblog: Audio classification with torch

0
37
Posit AI Weblog: Audio classification with torch


Variations on a theme

Easy audio classification with Keras, Audio classification with Keras: Wanting nearer on the non-deep studying components, Easy audio classification with torch: No, this isn’t the primary publish on this weblog that introduces speech classification utilizing deep studying. With two of these posts (the “utilized” ones) it shares the final setup, the kind of deep-learning structure employed, and the dataset used. With the third, it has in widespread the curiosity within the concepts and ideas concerned. Every of those posts has a unique focus – do you have to learn this one?

Effectively, after all I can’t say “no” – all of the extra so as a result of, right here, you may have an abbreviated and condensed model of the chapter on this matter within the forthcoming e book from CRC Press, Deep Studying and Scientific Computing with R torch. By means of comparability with the earlier publish that used torch, written by the creator and maintainer of torchaudio, Athos Damiani, important developments have taken place within the torch ecosystem, the top end result being that the code bought lots simpler (particularly within the mannequin coaching half). That stated, let’s finish the preamble already, and plunge into the subject!

Inspecting the info

We use the speech instructions dataset (Warden (2018)) that comes with torchaudio. The dataset holds recordings of thirty completely different one- or two-syllable phrases, uttered by completely different audio system. There are about 65,000 audio recordsdata total. Our job will probably be to foretell, from the audio solely, which of thirty potential phrases was pronounced.

library(torch)
library(torchaudio)
library(luz)

ds <- speechcommand_dataset(
  root = "~/.torch-datasets", 
  url = "speech_commands_v0.01",
  obtain = TRUE
)

We begin by inspecting the info.

[1]  "mattress"    "chicken"   "cat"    "canine"    "down"   "eight"
[7]  "5"   "4"   "go"     "completely satisfied"  "home"  "left"
[32] " marvin" "9"   "no"     "off"    "on"     "one"
[19] "proper"  "seven" "sheila" "six"    "cease"   "three"
[25]  "tree"   "two"    "up"     "wow"    "sure"    "zero" 

Choosing a pattern at random, we see that the data we’ll want is contained in 4 properties: waveform, sample_rate, label_index, and label.

The primary, waveform, will probably be our predictor.

pattern <- ds[2000]
dim(pattern$waveform)
[1]     1 16000

Particular person tensor values are centered at zero, and vary between -1 and 1. There are 16,000 of them, reflecting the truth that the recording lasted for one second, and was registered at (or has been transformed to, by the dataset creators) a charge of 16,000 samples per second. The latter info is saved in pattern$sample_rate:

[1] 16000

All recordings have been sampled on the identical charge. Their size nearly at all times equals one second; the – very – few sounds which can be minimally longer we will safely truncate.

Lastly, the goal is saved, in integer kind, in pattern$label_index, the corresponding phrase being out there from pattern$label:

pattern$label
pattern$label_index
[1] "chicken"
torch_tensor
2
[ CPULongType{} ]

How does this audio sign “look?”

library(ggplot2)

df <- knowledge.body(
  x = 1:size(pattern$waveform[1]),
  y = as.numeric(pattern$waveform[1])
  )

ggplot(df, aes(x = x, y = y)) +
  geom_line(dimension = 0.3) +
  ggtitle(
    paste0(
      "The spoken phrase "", pattern$label, "": Sound wave"
    )
  ) +
  xlab("time") +
  ylab("amplitude") +
  theme_minimal()
The spoken word “bird,” in time-domain representation.

What we see is a sequence of amplitudes, reflecting the sound wave produced by somebody saying “chicken.” Put otherwise, we’ve right here a time collection of “loudness values.” Even for specialists, guessing which phrase resulted in these amplitudes is an unattainable job. That is the place area data is available in. The skilled might not be capable of make a lot of the sign on this illustration; however they could know a option to extra meaningfully characterize it.

Two equal representations

Think about that as an alternative of as a sequence of amplitudes over time, the above wave have been represented in a means that had no details about time in any respect. Subsequent, think about we took that illustration and tried to get better the unique sign. For that to be potential, the brand new illustration would someway must include “simply as a lot” info because the wave we began from. That “simply as a lot” is obtained from the Fourier Remodel, and it consists of the magnitudes and part shifts of the completely different frequencies that make up the sign.

How, then, does the Fourier-transformed model of the “chicken” sound wave look? We acquire it by calling torch_fft_fft() (the place fft stands for Quick Fourier Remodel):

dft <- torch_fft_fft(pattern$waveform)
dim(dft)
[1]     1 16000

The size of this tensor is similar; nevertheless, its values usually are not in chronological order. As a substitute, they characterize the Fourier coefficients, equivalent to the frequencies contained within the sign. The upper their magnitude, the extra they contribute to the sign:

magazine <- torch_abs(dft[1, ])

df <- knowledge.body(
  x = 1:(size(pattern$waveform[1]) / 2),
  y = as.numeric(magazine[1:8000])
)

ggplot(df, aes(x = x, y = y)) +
  geom_line(dimension = 0.3) +
  ggtitle(
    paste0(
      "The spoken phrase "",
      pattern$label,
      "": Discrete Fourier Remodel"
    )
  ) +
  xlab("frequency") +
  ylab("magnitude") +
  theme_minimal()
The spoken word “bird,” in frequency-domain representation.

From this alternate illustration, we might return to the unique sound wave by taking the frequencies current within the sign, weighting them in line with their coefficients, and including them up. However in sound classification, timing info should absolutely matter; we don’t actually need to throw it away.

Combining representations: The spectrogram

In reality, what actually would assist us is a synthesis of each representations; some type of “have your cake and eat it, too.” What if we might divide the sign into small chunks, and run the Fourier Remodel on every of them? As you’ll have guessed from this lead-up, this certainly is one thing we will do; and the illustration it creates is known as the spectrogram.

With a spectrogram, we nonetheless preserve some time-domain info – some, since there’s an unavoidable loss in granularity. However, for every of the time segments, we find out about their spectral composition. There’s an essential level to be made, although. The resolutions we get in time versus in frequency, respectively, are inversely associated. If we cut up up the indicators into many chunks (referred to as “home windows”), the frequency illustration per window won’t be very fine-grained. Conversely, if we need to get higher decision within the frequency area, we’ve to decide on longer home windows, thus dropping details about how spectral composition varies over time. What seems like a giant drawback – and in lots of circumstances, will probably be – gained’t be one for us, although, as you’ll see very quickly.

First, although, let’s create and examine such a spectrogram for our instance sign. Within the following code snippet, the dimensions of the – overlapping – home windows is chosen in order to permit for cheap granularity in each the time and the frequency area. We’re left with sixty-three home windows, and, for every window, acquire 200 fifty-seven coefficients:

fft_size <- 512
window_size <- 512
energy <- 0.5

spectrogram <- transform_spectrogram(
  n_fft = fft_size,
  win_length = window_size,
  normalized = TRUE,
  energy = energy
)

spec <- spectrogram(pattern$waveform)$squeeze()
dim(spec)
[1]   257 63

We are able to show the spectrogram visually:

bins <- 1:dim(spec)[1]
freqs <- bins / (fft_size / 2 + 1) * pattern$sample_rate 
log_freqs <- log10(freqs)

frames <- 1:(dim(spec)[2])
seconds <- (frames / dim(spec)[2]) *
  (dim(pattern$waveform$squeeze())[1] / pattern$sample_rate)

picture(x = as.numeric(seconds),
      y = log_freqs,
      z = t(as.matrix(spec)),
      ylab = 'log frequency [Hz]',
      xlab = 'time [s]',
      col = hcl.colours(12, palette = "viridis")
)
major <- paste0("Spectrogram, window dimension = ", window_size)
sub <- "Magnitude (sq. root)"
mtext(aspect = 3, line = 2, at = 0, adj = 0, cex = 1.3, major)
mtext(aspect = 3, line = 1, at = 0, adj = 0, cex = 1, sub)
The spoken word “bird”: Spectrogram.

We all know that we’ve misplaced some decision in each time and frequency. By displaying the sq. root of the coefficients’ magnitudes, although – and thus, enhancing sensitivity – we have been nonetheless in a position to acquire an affordable end result. (With the viridis colour scheme, long-wave shades point out higher-valued coefficients; short-wave ones, the other.)

Lastly, let’s get again to the essential query. If this illustration, by necessity, is a compromise – why, then, would we need to make use of it? That is the place we take the deep-learning perspective. The spectrogram is a two-dimensional illustration: a picture. With pictures, we’ve entry to a wealthy reservoir of strategies and architectures: Amongst all areas deep studying has been profitable in, picture recognition nonetheless stands out. Quickly, you’ll see that for this job, fancy architectures usually are not even wanted; a simple convnet will do an excellent job.

Coaching a neural community on spectrograms

We begin by making a torch::dataset() that, ranging from the unique speechcommand_dataset(), computes a spectrogram for each pattern.

spectrogram_dataset <- dataset(
  inherit = speechcommand_dataset,
  initialize = operate(...,
                        pad_to = 16000,
                        sampling_rate = 16000,
                        n_fft = 512,
                        window_size_seconds = 0.03,
                        window_stride_seconds = 0.01,
                        energy = 2) {
    self$pad_to <- pad_to
    self$window_size_samples <- sampling_rate *
      window_size_seconds
    self$window_stride_samples <- sampling_rate *
      window_stride_seconds
    self$energy <- energy
    self$spectrogram <- transform_spectrogram(
        n_fft = n_fft,
        win_length = self$window_size_samples,
        hop_length = self$window_stride_samples,
        normalized = TRUE,
        energy = self$energy
      )
    tremendous$initialize(...)
  },
  .getitem = operate(i) {
    merchandise <- tremendous$.getitem(i)

    x <- merchandise$waveform
    # make sure that all samples have the identical size (57)
    # shorter ones will probably be padded,
    # longer ones will probably be truncated
    x <- nnf_pad(x, pad = c(0, self$pad_to - dim(x)[2]))
    x <- x %>% self$spectrogram()

    if (is.null(self$energy)) {
      # on this case, there's an extra dimension, in place 4,
      # that we need to seem in entrance
      # (as a second channel)
      x <- x$squeeze()$permute(c(3, 1, 2))
    }

    y <- merchandise$label_index
    listing(x = x, y = y)
  }
)

Within the parameter listing to spectrogram_dataset(), be aware energy, with a default worth of two. That is the worth that, except instructed in any other case, torch’s transform_spectrogram() will assume that energy ought to have. Beneath these circumstances, the values that make up the spectrogram are the squared magnitudes of the Fourier coefficients. Utilizing energy, you may change the default, and specify, for instance, that’d you’d like absolute values (energy = 1), another constructive worth (akin to 0.5, the one we used above to show a concrete instance) – or each the actual and imaginary components of the coefficients (energy = NULL).

Show-wise, after all, the complete complicated illustration is inconvenient; the spectrogram plot would wish an extra dimension. However we might properly wonder if a neural community might revenue from the extra info contained within the “complete” complicated quantity. In any case, when lowering to magnitudes we lose the part shifts for the person coefficients, which could include usable info. In reality, my checks confirmed that it did; use of the complicated values resulted in enhanced classification accuracy.

Let’s see what we get from spectrogram_dataset():

ds <- spectrogram_dataset(
  root = "~/.torch-datasets",
  url = "speech_commands_v0.01",
  obtain = TRUE,
  energy = NULL
)

dim(ds[1]$x)
[1]   2 257 101

Now we have 257 coefficients for 101 home windows; and every coefficient is represented by each its actual and imaginary components.

Subsequent, we cut up up the info, and instantiate the dataset() and dataloader() objects.

train_ids <- pattern(
  1:size(ds),
  dimension = 0.6 * size(ds)
)
valid_ids <- pattern(
  setdiff(
    1:size(ds),
    train_ids
  ),
  dimension = 0.2 * size(ds)
)
test_ids <- setdiff(
  1:size(ds),
  union(train_ids, valid_ids)
)

batch_size <- 128

train_ds <- dataset_subset(ds, indices = train_ids)
train_dl <- dataloader(
  train_ds,
  batch_size = batch_size, shuffle = TRUE
)

valid_ds <- dataset_subset(ds, indices = valid_ids)
valid_dl <- dataloader(
  valid_ds,
  batch_size = batch_size
)

test_ds <- dataset_subset(ds, indices = test_ids)
test_dl <- dataloader(test_ds, batch_size = 64)

b <- train_dl %>%
  dataloader_make_iter() %>%
  dataloader_next()

dim(b$x)
[1] 128   2 257 101

The mannequin is a simple convnet, with dropout and batch normalization. The true and imaginary components of the Fourier coefficients are handed to the mannequin’s preliminary nn_conv2d() as two separate channels.

mannequin <- nn_module(
  initialize = operate() {
    self$options <- nn_sequential(
      nn_conv2d(2, 32, kernel_size = 3),
      nn_batch_norm2d(32),
      nn_relu(),
      nn_max_pool2d(kernel_size = 2),
      nn_dropout2d(p = 0.2),
      nn_conv2d(32, 64, kernel_size = 3),
      nn_batch_norm2d(64),
      nn_relu(),
      nn_max_pool2d(kernel_size = 2),
      nn_dropout2d(p = 0.2),
      nn_conv2d(64, 128, kernel_size = 3),
      nn_batch_norm2d(128),
      nn_relu(),
      nn_max_pool2d(kernel_size = 2),
      nn_dropout2d(p = 0.2),
      nn_conv2d(128, 256, kernel_size = 3),
      nn_batch_norm2d(256),
      nn_relu(),
      nn_max_pool2d(kernel_size = 2),
      nn_dropout2d(p = 0.2),
      nn_conv2d(256, 512, kernel_size = 3),
      nn_batch_norm2d(512),
      nn_relu(),
      nn_adaptive_avg_pool2d(c(1, 1)),
      nn_dropout2d(p = 0.2)
    )

    self$classifier <- nn_sequential(
      nn_linear(512, 512),
      nn_batch_norm1d(512),
      nn_relu(),
      nn_dropout(p = 0.5),
      nn_linear(512, 30)
    )
  },
  ahead = operate(x) {
    x <- self$options(x)$squeeze()
    x <- self$classifier(x)
    x
  }
)

We subsequent decide an acceptable studying charge:

mannequin <- mannequin %>%
  setup(
    loss = nn_cross_entropy_loss(),
    optimizer = optim_adam,
    metrics = listing(luz_metric_accuracy())
  )

rates_and_losses <- mannequin %>%
  lr_finder(train_dl)
rates_and_losses %>% plot()
Learning rate finder, run on the complex-spectrogram model.

Primarily based on the plot, I made a decision to make use of 0.01 as a maximal studying charge. Coaching went on for forty epochs.

fitted <- mannequin %>%
  match(train_dl,
    epochs = 50, valid_data = valid_dl,
    callbacks = listing(
      luz_callback_early_stopping(persistence = 3),
      luz_callback_lr_scheduler(
        lr_one_cycle,
        max_lr = 1e-2,
        epochs = 50,
        steps_per_epoch = size(train_dl),
        call_on = "on_batch_end"
      ),
      luz_callback_model_checkpoint(path = "models_complex/"),
      luz_callback_csv_logger("logs_complex.csv")
    ),
    verbose = TRUE
  )

plot(fitted)
Fitting the complex-spectrogram model.

Let’s verify precise accuracies.

"epoch","set","loss","acc"
1,"prepare",3.09768574611813,0.12396992171405
1,"legitimate",2.52993751740923,0.284378862793572
2,"prepare",2.26747255972008,0.333642356819118
2,"legitimate",1.66693911248562,0.540791100123609
3,"prepare",1.62294889937818,0.518464153275649
3,"legitimate",1.11740599192825,0.704882571075402
...
...
38,"prepare",0.18717994078312,0.943809229501442
38,"legitimate",0.23587799138006,0.936418417799753
39,"prepare",0.19338578602993,0.942882159044087
39,"legitimate",0.230597475945365,0.939431396786156
40,"prepare",0.190593419024368,0.942727647301195
40,"legitimate",0.243536252455384,0.936186650185414

With thirty courses to tell apart between, a ultimate validation-set accuracy of ~0.94 seems like a really respectable end result!

We are able to verify this on the take a look at set:

consider(fitted, test_dl)
loss: 0.2373
acc: 0.9324

An attention-grabbing query is which phrases get confused most frequently. (After all, much more attention-grabbing is how error chances are associated to options of the spectrograms – however this, we’ve to depart to the true area specialists. A pleasant means of displaying the confusion matrix is to create an alluvial plot. We see the predictions, on the left, “move into” the goal slots. (Goal-prediction pairs much less frequent than a thousandth of take a look at set cardinality are hidden.)

Alluvial plot for the complex-spectrogram setup.

Wrapup

That’s it for in the present day! Within the upcoming weeks, count on extra posts drawing on content material from the soon-to-appear CRC e book, Deep Studying and Scientific Computing with R torch. Thanks for studying!

Photograph by alex lauzon on Unsplash

Warden, Pete. 2018. “Speech Instructions: A Dataset for Restricted-Vocabulary Speech Recognition.” CoRR abs/1804.03209. http://arxiv.org/abs/1804.03209.

LEAVE A REPLY

Please enter your comment!
Please enter your name here