The fraction of system output which was predicted correctly

See also: evaluation metric

Genauigkeit, Exaktheit

exactitud, precisión

tarkkuus

précision, justesse, exactitude

See also: feature

akustinen piirre

in speech recognition system, model learned from acoustic data

akustinen malli

in neural network, a function to define the output of a neuron

Función de activación

aktivaatiofunktio

Fonction d'activation

a learning technique where algorithm selects the data it learns from

aktiivinen oppiminen

crowdsourcing marketplace enabling the use of human intelligence to perform tasks

adding metadata to audio

annotointi

in binary classification, an evaluation metric to considers all classification thresholds

See also: reciever operating characteristic curve

luokittelijan havintojen erottelukyky

See also: strong artificial intelligence, full artificial intelligence

Künstliche allgemeine Intelligenz

inteligencia artificial fuerte

yleinen tekoäly

intelligence artificielle forte

an ability to have machines act with apparent intelligence

Künstliche Intelligenz

inteligencia artificial

tekoäly

intelligence artificielle

a housing facility for people with disabilities or for adults who cannot or choose not to live independently

Betreutes Wohnen

tuettu asuminen

See also: classification

äänimateriaalien luokittelu

a collection of audio examples used for system development

audiotietokanta

relating to hearing

kuulonmukainen, kuuloon liittyvä, kuulo-

Subjective perception of sound

See also: auditory scene

Hörereignis

kuulotapahtuma

Audition humaine

a model proposed by Albert Bregman for the basis of auditory perception

kuulomaisema-analyysi, kuulema-analyysi

method used in neural networks to calculate gradient descent

propagación hacia atrás

vastavirta, takaisinvirtaus, takaisinlevitys

rétropropagation du gradient

representing frames without taking into account their order

system used as reference point for comparing how well currently developed system is performing

in neural network training, a set of examples used in one iteration for model training

ryhmä, erä

a technique for improving the performance and stability of neural networks

See also: deep neural network, neural network, batch

ryhmänormalisointi, eränormalisointi

technique used in sensor arrays for directional signal reception or transmission

conformación de haces

keilanmuodostus

an ordered sequence of two items

See also: N-gram

bigrama

a type of classification which outputs one of two mutually exclusive classes

binäärinen luokittelu

related to two ears

binauraalinen, kaksikorvainen

cross-disciplinary science that combines biology and acoustics

Bioakustik

bioacústica

bioakustiikka

bioacoustique

data augmentation technique

See also: data augmentation

a machine learning technique which iteratively combines weak classifiers into a classifier with higher accuracy

oppimisen kiihdyttäminen

Systematically going through all possible candidate solutions for the problem

See also: exhaustive search

Brute-Force-Methode

Búsqueda de fuerza bruta

raakavoimahaku

Recherche exhaustive

a group to which items are assigned based on similarity or defined criteria

luokka, kategoria

identification of which categories an item belong

Klassifizierung

clasificación

luokittelu, luokitus

classement, classification

See also: model, classification

evaluation campaign organized on 2006 and 2007

See also: classification

See also: classification

luokittelija, luokitin

See also: open set classification

See also: cluster analysis

Cluster, Klumpen, geschlossene Erfassungsgruppe

conglomerado

ryhmä, ryväs, klusteri

grappe, conglomérat

grouping related examples together

Verklumpung, verklumpend, in Klumpen auftretend

clasificación

ryhmittely, ryhmittelyanalyysi, klusterointi, ryvästäminen

classification, classement

See also: federated learning

See also: content analysis

äänen laskennallinen sisältöanalyysi

an interdisciplinary field concerned with the statistical or rule-based modeling of natural language from a computational perspective

tietokonelingvistiikka

field of study of algorithms and systems for audio understanding by machine

audición por computadora

interval estimate computed from the statistics of the observed data, that might contain the true value of an unknown population parameter

Konfidenzintervall, Vertrauensintervall

intervalo de confianza

luottamusväli

intervalle de confiance

an NxN table to summarize classification performance (predicted class versus actual class)

sekaannusmatriisi

matrice de confusion

mathematical operation of two functions to produce a third function that expresses how the shape of one is modified by the other

Faltung

convolución

konvoluutio

convolution, produit de composition

a neural network with convolutional layers along with pooling and fully connected layers

See also: neural network, deep neural network

redes neuronales convolucionales

konvoluutioverkko, konvoluutioneuroverkko

réseau neuronal convolutif

See also: neural network, deep neural network

the frequency bandwidth of the "auditory filter" created by the cochlea

Frequenzgruppe

bandas críticas

kriittinen kaista, kriittinen kaistanleveys

a method for estimating generalization of a system for new data by reserving a subset of dataset only for testing

Kreuzvalidierung, Kreuzvalidierungsverfahren

validación cruzada

ristiinvalidointi, ristivalidointi

validation croisée

artificially increasing the number of training examples

aineiston täydennys, datan laajennus

See also: data preprocessing

datan jälkikäsittely, aineiston jälkikäsittely

See also: data post-processing

datan esikäsittely, aineiston esikäsittely

learned separating boundary between classes

päätösraja

a learning method using tree-like decision graph

päätöspuu

a multi-level algorithm that gradually identifies things at higher levels of abstraction

aprendizaje profundo

syväoppiminen

See also: deep learning

neural network containing multiple hidden layers

syvä neuroverkosto, syvä neuroverkko

Plot of the false rejection rate versus false acceptance rate for classification systems

virheiden kompromissi

Transform to represent data points with a sum of cosine functions

Diskrete Kosinustransformation

transformada de coseno discreta

diskreetti kosinimuunnos

transformée en cosinus discrète

modeling the dependence of a target variable y on an observed variable x

See also: generative learning

See also: similarity

Dissimilarität, Unähnlichkeit

desemejanza

erilaisuus, erilaisuusmitta

dissimilitude

machine learning field to deal with cases in which a model trained on source distribution is used on different target distribution

Adaptation de domaine

mixing audio channels together

a length of audio signal

kesto

Features from multiple sources are combined into a single feature set before feeding to a classifier.

See also: feature level fusion

a low-dimensional space into which high-dimensional vectors can be translated

See also: word embedding

upotus

predictions of multiple models merged together

See also: ensemble learning

kokoelma, kokoonpano

use multiple learning algorithms to obtain better predictive performance than any of the constituent learning algorithms alone

apprentissage ensembliste

while traning neural networks, one pass of the full training set

See also: deep neural network, neural network

opetuskierros

See also: evaluation metric

tapahtumapohjainen metriikka

the interpretation of the sound in terms of its source

See also: brute-force search

tyhjentävä haku

an iterative method to find maximum likelihood or maximum a posteriori estimates of parameters in statistical models

EM-Algorithmus

algoritmo esperanza-maximización

odotusarvon maksimointi

algorithme espérance-maximisation

an evaluation metric to take into account both the precision and the recall

See also: evaluation metric

Valor-F

an example wrongly predicted as negative class

falsch negativ

negazione falsa

negatiivisten tapausten virhe

faux négatif

an example wrongly predicted as positive class

falsch positiv

positivo falso

positiivisten tapausten virhe

faux positif

a measurable property of the acoustic signal

See also: acoustic feature

piirre

using domain knowledge of the data to manually create suitable features for machine learning

See also: feature learning

automatically discover needed representations

See also: feature engineering

aprendizaje de características

Features from multiple sources are combined into a single feature set before feeding to a classifier.

See also: early fusion

machine learning technique to train a model across multiple devices

See also: collaborative learning

Föderales Lernen

hajautettu oppiminen

See also: deep neural network, neural network

red neuronal prealimentada

eteenpäin syöttävä hermoverkko

réseau de neurones à propagation avant

an array of band-pass filters

banco de filtros, banco de filtros híbrido

suodinpankki

classification based on user's tags

folcsonomía

folksonomia

folksonomie

See also: frame

See also: time domain

Frequenzbereich

dominio de frecuencia

taajuusalue

domaine de fréquence

See also: artifical general intelligence, strong artificial intelligence

See also: deep neural network, neural network

täysin kytketty kerros

See also: neural network, deep neural network

See also: mixture model

Gaussin sekoitemalli, Gaussinen sekoitemalli

model's ability to predict correctly on data not used for training the model

yleistäminen, yleistys

technique where a generator generates data candidates and a discriminator evaluates them.

See also: deep neural network, neural network

generatiivinen kilpaileva verkko

See also: discriminative learning

generatiivinen oppiminen

See also: reference label, annotation

using domain knowledge of the data to manually create suitable features for machine learning

See also: feature engineering

a practical and suboptimial solution

Heuristik

Heurística

heuristinen

in neural network, layer between the input layer and the output layer

See also: deep neural network, neural network

piilokerros

examples which are only used for testing the system's performance

See also: cross-validation

in machine learning, a variable which is set before the learning process starts

See also: parameter

hyperparametri

See also: deep neural network, neural network

syötekerros

a measurement of how well human annotators agree while annotation task

annotoijien yksimielisyys

See also: cross-validation

k-kertainen ristiinvalidointi, k-ositettu ristiinvalidointi

See also: nearest neighbor

k:n lähimmän naapurin menetelmä

an example with audio and assigned category label

Combaning outputs from multiple classifiers.

a variable that is not directly observed but is inferred based on a model from other observed variables

nicht beobachtbare Variable, latente Variable

variable latente

piilomuuttuja, latentti muuttuja

variable latente

in neural network, a set of neurons

See also: deep neural network, neural network

kerros

a board showing the ranking of participant in a competition

tulostaulukko

a hyperparameter to control the size of the learning step, gradient step

See also: deep neural network, neural network

oppimisnopeus

a mathematical operation to estimate future values as a linear function of previous values

Lineare vorhersage

lineaariprediktio, lineaarinen ennustus, lineaarinen ennustaminen

See also: deep neural network, neural network

langes Kurzzeitgedächtnis

a function to measure how far prediction are from its label

Verlustfunktion

función de pérdida

tappiofunktio

fonction de perte

field of artificial intelligence that uses statistical techniques to give computer systems the ability to "learn" from data, without being explicitly programmed

Maschinelles Lernen

aprendizaje automático

koneoppiminen

apprentissage automatique

field of study of algorithms and systems for audio understanding by machine

konekuulo

See also: evaluation metric

makrokeskiarvoistaminen

See also: root mean square error

mittleres Fehlerquadrat

error cuadrático medio

keskineliövirhe, keskimääräinen neliövirhe, keskineliöpoikkeama

erreur quadratique moyenne

non-linear perceptual frequency scale where listners judge frequencies to be equal in distance from one another.

Escala Mel

mel-asteikko

Échelle des mels

See also: evaluation metric

mikrokeskiarvoistaminen

See also: batch

pienerä

See also: Gaussian mixture model

sekoitemalli

in machine learning system, a parameter set learned from the training data

malli

a task of selecting a model from a set of candidate models based on data

mallin valinta

related to one ears

yksikorvainen

See also: monophonic

Monophonie

sonido monoaural

monoääni, yksikanavainen

monophonique

See also: monoaural

monofooninen, yksikanavainen

classification type where prediction is done between three or more classes

moniluokkainen luokittelu

classification type where multiple class labels may be assigned to each instance

See also: single-label classification

approach where multiple learning tasks are solved at the same time

monitehtävä oppiminen, monen tehtävän oppiminen

See also: single-channel

monikanavainen, monikanava-

See also: neural network, deep neural network

Mehrlagiges Perzeptron

perceptrón multicapa

monikerroksinen perseptroniverkko

perceptron multicouche

machine learning method to use a predefined set of kernels and learn optimal combination of these kernels

interdisciplinary science of retrieving information from music

recuperación de información musical

musiikkitiedonhaku

an ordered sequence of N items

See also: bigram, trigram

See also: k-nearest-neighbor

lähin naapuri

Recherche des plus proches voisins

network of (artificial) neurons

neuronales Netzwerk

red de los nervios

neuroverkosto, neuroverkko, hermoverkko

réseau de neurones

a node in a neural network taking in multiple values and generating single value as an output

neuroni

converting values into standard range of values

normalización

normalisaatio

general statement that there is no relationship between two measured phenomena

Nullhypothese

hipótesis de nulidad, hipótesis nula

nollahypoteesi

hypothèse nulle, hypothèse zéro

a metric the algorithm tries to optimize

tavoite, päämäärä

representing categorical variables as binary vectors so that only single element is set to one

machine learning approach where aim is to learn from a single training example

a structure of concepts or entities within a domain which are organized by relationships

Ontologie

ontologia

ontologie

See also: closed set classification

in neural network, an implementation of gradient descent algorithm

optimoija

observation points that are distant from other observations

Ausreißer

valores extremos, valores atípicos, elemento raro

poikkeavat havainnot, vieraat havainnot, ulkopuoliset havainnot

valeurs aberrantes, observations aberrantes

See also: input

ulostulo, lähtö, anto, tuloste

last layer of a neural network outputting predictions

See also: deep neural network, neural network

vastekerros

a model that models the training data too closely and fails to predict correcly on new data

See also: underfitting

Überanpassung

sobreajuste

ylisovittaminen, ylisovittuminen

surapprentissage

in machine learning, a variable which is adjusted during the learning process

See also: hyperparameter

parametri

the process of marking up a word in a text as corresponding to a particular part of speech

See also: part of speech

Part-of-speech-Tagging

etiquetado gramatical

sanaluokan merkitseminen

étiquetage morpho-syntaxique

See also: part-of-speech tagging

Wortart

categoría gramatical

sanaluokka

nature

an algorithm which takes multiple input values, runs a function on the weighted sum of the inputs and computes a single output value

See also: perception

havainnonmukainen

in machine learning, refers to the goodness of the model's predictions

suorituskyky

See also: pitch

Tonhöhenänderung

äänenkorkeuden muuttaminen

in neural network, reducing matrix into a smaller matrix

See also: deep neural network, neural network

kokooma, keräys

a model which has been already trained

esiopetettu malli

a measure how often prediction is correct when predicting the positive class

See also: recall, F-score, evaluation metric

Präzision

precisión

tarkkuus, täsmällisyys

précision, reproducibilité

system's output for the input example

ennustaminen, ennuste

a statistical procedure that uses an orthogonal transformation to convert a set of observations of possibly correlated variables into a set of values of linearly uncorrelated variables called principal components

Hauptkomponentenanalyse

análisis de componentes principales

pääkomponenttianalyysi

See also: prior distribution

Prior-Wahrscheinlichkeit, A-priori-Wahrscheinlichkeit

probabilidad a priori, apuestas a priori

prioritodennäköisyys

probabilité a priori

the scientific study of sound perception and audiology

Psychoakustik

psicoacústica

psykoakustiikka

psychoacoustique

an ensemble learning method which constructs a multiple decision trees at training stage

satunnaismetsä

forêt d'arbres décisionnels

a measure how many positive classes were correctly predicted

See also: precision, F-score, evaluation metric

saanti

a curve of true positive rate versus false positive rate at different classification thresholds

toimintaominaiskäyrä, ROC-käyrä

a neural network to model sequential interactions through a hidden stage or memory

See also: neural network, deep neural network

Rekurrentes Neuronales Netz

uusiutuva neuroverkko, toistuva neuroverkko

réseau de neurones récurrents

See also: ground truth, annotation

in machine learning, penalizes a model's compelixity in order to prevent overfitting

regularización

regularisointi

régularisation

machine learning technique to focusing on peformance, finding a balance between exploration of new knowledge and exploitation of current knowledge

Bestärkendes Lernen

aprendizaje por refuerzo

vahvistusoppiminen, palauteoppiminen

apprentissage par renforcement

See also: mean square error

Wurzel der mittleren quadratischen Abweichung, Wurzel des mittleren quadratischen Fehlers, Wurzel des mittleren quadratischen Gesamt-Fehlers

desviación cuadrática media, desviación standard, desviación típica, desviación estándar, error cuadrático medio

keskineliövirheen neliöjuuri

écart quadratique moyen, écart type, déviation typique, écart-étalon, erreur quadratique moyenne, erreur en moyenne quadratique

See also: sampling rate

näytetaajuus, näytteenottotaajuus

See also: sampling frequency

näytenopeus, näytetaajuus

See also: evaluation metric

segmenttipohjainen metriikka

artificial neural network that is trained using unsupervised learning to produce a low-dimensional discretized representation of the input space

Selbstorganisierende Karte

mapa autoorganizado

itseorganisoituva kartta

carte auto adaptative

machine learning technique to use small amount of labeled data and large amount of unlabeled data in the learning stage

aprendizaje semisupervisado

puoliohjattu oppiminen

apprentissage semi-supervisé

See also: evaluation metric

herkkyys, sensitiivisyys

See also: sensor

Nodo sensor

anturisolmu

a measure to determine how similar two examples are

See also: similarity

samankaltaisuusmitta

See also: multichannel

classification type where single class label may be assigned to each instance

See also: binary classification, multi-label classification

the perception of environmental elements and events with respect to time or space, the comprehension of their meaning, and the projection of their future status

Situationsbewusstsein

consciencia situacional

tilannetietoisuus, tilannekuva

See also: sound event

äänitapahtuman havaitseminen, äänitapahtuman tunnistus

See also: sound pressure

äänenpainetaso, äänipainetaso

matrix which has elements predominantly zero

Dünnbesetzte Matrix

matriz dispersa

harva matriisi

matrice creuse

number of zero elements a matrix divided by the total number of elements

Process of spliting audio signal in to segments accroding to the speakers

puheen diarisointi

See also: evaluation metric

tarkkuus, spesifisyys

grouping related examples together using the eigenvalues of similarity matrix

Agrupamiento espectral

Partitionnement spectral

improvement of speech quality by using various algorithms

puheen ehostus

in convolution or pooling, the delta on horizontal or vertical dimension of the next input slice

See also: annotation, weak annotation

See also: artifical general intelligence, full artificial intelligence

See also: strong annotation, weak label, weak annotation

learning method which learns from labeled examples

See also: unsupervised learning

Überwachtes Lernen

aprendizaje supervisado

ohjattu oppiminen

apprentissage supervisé

a classification in a hierarchical system

Taxonomie

taksonomia, luokittelu

taxonomie

subset of data used to test the system, disjunct from the training set

See also: training set, validation set

testausjoukko, testijoukko

See also: test set

changing the duration of an audio singal without affecting its pitch

See also: pitch shifting

a process of determining the optimal parameters of the model

opetus

subset of data used to train the system, disjunct from the test set

See also: test set, validation set

opetusjoukko

a research problem focusing on storing knowledge gained while solving one problem and applying it to a different problem

siirto-oppiminen, siirretty oppiminen

apprentissage par transfert

an ordered sequence of three items

See also: N-gram

trigramme

an example correctly predicted as negative class

oikea negatiivinen

an example correctly predicted as positive class

oikea positiivinen

a model with low predictive ability because it does not model the training data well nor it does generalize to new data

See also: overfitting

alisovittaminen

machine learning technique to learn from unlabeled data

See also: supervised learning

Unüberwachtes Lernen

aprendizaje no supervisado

ohjaamaton oppiminen

apprentissage non supervisé

subset of data used to adjust hyperparameters, disjunct from the training set and test set

See also: training set, test set

validointijoukko

See also: annotation

See also: weak annotation, strong label, strong annotation

See also: annotation, weak annotation

See also: windowing function

ikkunointi

function that is zero-valued outside of some chosen interval

See also: windowing

Fensterfunktion

ventana

ikkunointifunktio

fenêtrage

mapping word or phrase from the vocabulary into vector of real numbers

See also: embeddings

sanojen upotus

identifying which sense of a word is used in a sentence, when the word has multiple meanings

Disambiguierung

desambiguación lingüística

sananmerkitysten yksikäsitteistäminen

désambiguïsation lexicale