def test_word_to_phoneme(self): wer_details = WERDetails("../experiments/baseline/wer_details/per_utt", skip_calculation=True) self.assertEqual(wer_details.word_to_phoneme("cheese", True), ["CH", "IY", "Z"]) self.assertEqual(wer_details.word_to_phoneme("cheese", False), ["CH", "IY1", "Z"])
def articulatory_barplot(poa_afer: list, label_list: list, reference_label: list, filename: str, phoneme_count: np.ndarray, per: list): """ Generates articulatory barplot :param poa_afer: :param label_list: :param reference_label: :return: """ format_dict = { "width_fig": 3.14, "height_fig": 3.14 * 0.8, # 0.62 "dpi": 100, "width": 0.13, # the width of the bars "fontsize": 7, "capsize": 1.5 } num_architectures = len(label_list) x = np.arange(len(reference_label)) mean_experiments = list() std_experiments = list() for experiment in poa_afer: selected_afer = np.zeros((len(experiment),len(reference_label))) for i, labelafer in enumerate(experiment): label, afer = labelafer idx = [label.index(lab) for lab in reference_label] afer = np.array(afer)[idx] selected_afer[i,:] = afer mean_afer = np.mean(selected_afer,axis=0) std_afer = np.std(selected_afer,axis=0) mean_experiments.append(mean_afer) std_experiments.append(std_afer) #width_logic = np.linspace(start=-format_dict["width"]*2,stop=format_dict["width"],num=num_architectures) # Phoeme counts wer_details = WERDetails("../experiments/baseline/wer_details/per_utt", skip_calculation=True) phoneme_labels = per[0][0][0] if "moa" in filename: af_labels = np.array([wer_details.phoneme_to_moa(phoneme_label) for phoneme_label in phoneme_labels]) if "poa" in filename: af_labels = np.array([wer_details.phoneme_to_poa(phoneme_label) for phoneme_label in phoneme_labels]) phoneme_counts = np.mean(phoneme_count,axis=0) af_counts = [round_to_n(np.sum(phoneme_counts[np.where(af_labels == af)]),2) for af in reference_label] fig = plt.figure(num=None, figsize=(format_dict["width_fig"], format_dict["height_fig"]), dpi=format_dict["dpi"], facecolor='w', edgecolor='k') markers = ["v","^","<",">","x"] for i in range(num_architectures): # legend_props = {"elinewidth": 0.5} # plt.bar(x + format_dict["width"]/2 + width_logic[i], # mean_experiments[i],format_dict["width"], # label=label_list[i],yerr=std_experiments[i], # capsize=format_dict["capsize"], error_kw=legend_props) plt.plot(x, mean_experiments[i], markersize=4, marker=markers[i]) plt.fill_between(x, mean_experiments[i] - std_experiments[i], mean_experiments[i] + std_experiments[i], alpha=0.2) r, p = pearsonr(af_counts, mean_experiments[i]) print(label_list[i], " correlation btw data amount and performance", r, "p value", p) ax = plt.gca() ax.set_axisbelow(True) ax.yaxis.grid(color='gray', linestyle='dashed',which="major") ax.axhline(y=0, color="black",linewidth=0.8) ax.set_xticks(x) ax.tick_params(axis='both', which='major', labelsize=format_dict["fontsize"], pad=1) reference_label_to_plot = [ref + " " + str(int(af_counts[i])) for i,ref in enumerate(reference_label)] ax.set_xticklabels(reference_label_to_plot, rotation=45, fontsize=format_dict["fontsize"]) plt.ylabel("AFER (%)",fontsize=format_dict["fontsize"]) plt.legend(label_list, fontsize=6, loc='upper center', bbox_to_anchor=(0.5, +1.32), fancybox=True, shadow=True, ncol=(num_architectures//2)) plt.xlim([0,len(mean_experiments)]) plt.ylim([20,80]) plt.tight_layout(pad=0) fig.tight_layout(pad=0) fig.set_size_inches(format_dict["width_fig"], format_dict["height_fig"]) current_dir = os.path.dirname(__file__) plt.savefig(os.path.join(current_dir, "figures/" + filename + ".pdf"), bbox_inches='tight', pad_inches=0.005)
print(experiment_folders) # Purpose of this is to just store pure phoneme count phoneme_count_per_fold = np.zeros((len(experiment_folders), number_of_phonemes)) for i, experiment in enumerate(experiment_folders): per_per_experiment, poa_afer_per_experiment, moa_afer_per_experiment,\ poa_cm_per_experiment, moa_cm_per_experiment = [[],[],[],[],[]] for fold in range(1,6): t = time.time() test_folder = [folder for folder in os.listdir(os.path.join("./experiments/",experiment,str(fold))) if partition in folder] wer_details = os.path.join("./experiments/",experiment,str(fold),test_folder[0],"wer_details","per_utt") corpus = WERDetails(wer_details) per_per_experiment.append(corpus.all_pers()) poa_afer_per_experiment.append(corpus.all_poa_afers()) moa_afer_per_experiment.append(corpus.all_moa_afers()) poa_cm_per_experiment.append(corpus.poa_confusion_matrix()) moa_cm_per_experiment.append(corpus.moa_confusion_matrix()) s = time.time() - t print("Fold took", s, "seconds") if i == 0: phoneme_type, phoneme_counts = np.unique(corpus.all_ref_phonemes, return_counts=True) phoneme_count_per_fold[fold - 1, :] = phoneme_counts per.append(per_per_experiment) poa_afer.append(poa_afer_per_experiment)
def test_poa_to_phonemes(self): wer_details = WERDetails("../experiments/baseline/wer_details/per_utt", skip_calculation=True) self.assertEqual(sorted(wer_details.poa_to_phonemes("Bilabial")), sorted(["B", "P", "EM", "W", "M"]))
def test_word_in_cmu_dict(self): wer_details = WERDetails("../experiments/baseline/wer_details/per_utt", skip_calculation=True) self.assertEqual(wer_details.word_in_cmu_dict("{asdfhj}"), True) self.assertEqual(wer_details.word_in_cmu_dict("asdfhj"), False)
def test_phoneme_to_poa(self): wer_details = WERDetails("../experiments/baseline/wer_details/per_utt", skip_calculation=True) self.assertEqual(wer_details.phoneme_to_poa("P"), "Bilabial")
import time from corpus import WERDetails from utils import HParam #partition = "test" #number_of_phonemes = 40 preprocessing = True import numpy as np import pandas as pd if preprocessing: config = HParam("configs/dutch.yaml") wer_details = WERDetails( "experiments/jasmin_example/scoring_kaldi/wer_details/per_utt", skip_calculation=False, config=config) #phoneme, other = wer_details.all_poa_afers() t = time.time() moa_mat = wer_details.moa_confusion_matrix() s = time.time() print(s - t, "secs") poa_mat = wer_details.poa_confusion_matrix() k = time.time() print(k - s, "secs") print(poa_mat) print() #df = pd.DataFrame(data=other, index=phoneme)
preprocessing = False separation = True if separation: files = glob("experiments/voicefilter_experiment/*_ss_result.txt") else: files = glob("experiments/voicefilter_experiment/*_se_result.txt") config = HParam("../configs/eng_espnet.yaml") if preprocessing: dfs = list() for file in files: wer_details = WERDetails(file, skip_calculation=False, config=config) phoneme, other = wer_details.all_pers() dfs.append(pd.DataFrame(data=[other[1:]], columns=phoneme[1:], index=[file])) result = pd.concat(dfs, axis=0, join="outer") if separation: result.to_csv("csvs/separation_results_with_clean.csv") else: result.to_csv("csvs/enhancement_results_with_clean.csv") else: if separation: df = pd.read_csv("../csvs/separation_results_with_clean.csv")