EEG Database for language detection ============================================================= Version 1.0 Copyright©2025, ATIC Research Group, Universidad de Malaga Authors: Isaac Ariza (iariza@ic.uma.es), Ana M. Barbancho (abp@uma.es), Lorenzo J. Tardón (ltg@uma.es), Isabel Barbancho (ibp@uma.es) Date: 12/01/2025 This database is made up of EEG signals from 6 subjects listening to sentences in different languages and their answers to the questions: have you understood the meaning of the sentence?. The languages chosen are: english, german, italian, korean and spanish. These signals have been captured with the BrainVision actiCHAMP-PLUS system and consist of a total of 64 EEG channels. The BrainVision Recorder software was used to store the signals. The stimulus presentation software used to design the experiment is Eprime 3. For more detailed information on this database, the capture system used and its applications, see [1]. If these data are used for any publication, the following paper must be cited: [1] Isaac Ariza, Ana M. Barbancho, Lorenzo J. Tardón, Isabel Barbancho, Energy-based features and bi-LSTM neural network for EEG-based music and voice classification. Neural Comput & Applic 36, 791–802 (2024). https://doi.org/10.1007/s00521-023-09061-3 Folder included ./Raw_Data ---------------------- In this folder contains the original raw data of each subject doing the experiment. For each subject there are four different files: - S_00XX_E_0002_0001.eeg: contains the voltage values of the EEG signals. - S_00XX_E_0002_0001.vhdr: is the header file, which has information about the EEG signals such as the sampling rate and the impedance level of the electrodes. - S_00XX_E_0002_0001.vmrk: contains information about the events (triggers) occurring in the data. - S_00XX_E_0002_0001.txt: is generated by the stimulus presentation program running the experiment (Eprime 3) and collects the responses of the subjects. In these files, XX indicates the number of the subject performing the experiment. Table 1 shows the age and gender of each subject. Subject # Age Gender 0009 26 Male 0010 20 Female 0013 20 Female 0014 21 Female 0015 22 Male 0017 25 Female Table 1. Subjects participating in the experiments Before the experiment begins, the subjects answer a questionnaire about their level of language proficiency. They select a number from 1 to 5, where 1 means they don’t understand anything, and 5 is their mother tongue. They are also asked if they know any other languages. Table 2 shows the answers of the subjects carrying out this experiment. Subject Spanish English Italian German Korean Other language 0009 4 4 1 1 1 Chinese and Japanese 0010 5 3 1 1 1 French 0013 5 3 1 1 1 French 0014 5 3 1 3 1 - 0015 5 4 1 1 1 - 0017 5 4 4 1 1 French Table 2. Subjects’ answers to the questionnaire about their level of language proficiency. The txt files generated by Eprime contain the information of each sentence. The ID of a sentence of a particular language can be found in the field SpanishList, GermanyList, EnglishList, ItalianList or KoreanList. In the EEG data the onset times of the presentation of a stimulus are marked with the StimVal. Fields SlideSpanish.RESP, SlideGermany.RESP, SlideEnglish.RESP, SlideItalian.RESP and SlideKorean.RESP contain the answer to the question: “did you understand this sentence?”, with the following possible values: · 1: understand. · 2: understand part of the meaning. · 3: don´t understand. EnglishList StimVal Transcription Duration 1 121 He fell asleep, although the TV was on. 0:05 2 122 It was already late. Nevertheless, he stayed a while. 0:06 3 123 Despite having no license, he drives the car. 0:05 4 124 I don't know if he'll come back. 0:03 5 125 Maybe he won't come back. 0:03 6 126 I wonder if he thinks about me. 0:04 7 127 What is the name of the capital city of Switzerland? 0:05 8 128 What are the doctor's consultation times? 0:04 9 129 He is going to stay either with us or in the hotel. 0:04 10 130 I become tired as soon as I have to study. 0:03 11 131 She reads the newspaper instead of cooking. 0:03 12 132 I overslept. Otherwise, I'd have been on time. 0:04 13 133 During the holidays, the children were allowed to remain outside late. 0:05 14 134 Were you allowed to drink beer in the hospital? 0:03 15 135 You speak so softly. Don't speak so softly. 0:06 16 136 You are so lazy. Don't be so lazy. 0:05 17 137 I want to deposit money in my account. 0:03 18 138 No, I don't understand them so well. 0:03 19 139 She has lived in Madrid as well as in London. 0:03 20 140 Are tickets for the theatre still available? 0:03 21 141 He was disloyal, but she was loyal. 0:05 22 142 He had no money, only debts. 0:05 23 143 She listens to music while she does her work. 0:04 24 144 I can't smell anything when I have a cold. 0:04 25 145 After he had lost his job, he went to America. 0:03 26 146 I'm not drinking it because I have to drive. 0:04 27 147 Is the exhibition open on Tuesdays? 0:04 28 148 I'm not eating it because I must lose weight. 0:05 29 149 I want to go to the bookstore to buy a book. 0:05 30 150 Drive until you reach the third traffic light. 0:03 Table 3. EnglishList value, transcription and duration of each English sentence. GermanList StimVal Transcription Duration 1 61 Ich arbeite bis 13.30 Uhr und bin um 14:00 Uhr zu Hause 0:04 2 62 Es gibt einen Kurs montags, mittwochs und freitags von 14:30 bis 18:00 Uhr. 0:05 3 63 Viele Touristen reisen nach Bern, und auch viele Besucher aus der Region. 0:05 4 64 Ich weiß nicht, ob er mich liebt. 0:03 5 65 Ich frage mich, ob er an mich denkt. 0:04 6 66 Es ärgert mich, dass du schnarchst. 0:04 7 67 Das Wetter wird vielleicht morgen besser. 0:04 8 68 Ich finde, dass er sogar sehr gut aussieht. 0:05 9 69 Es ist gut möglich, dass er eine Freundin hat. 0:05 10 70 Ich warte, bis meine Haare trocken sind. 0:03 11 71 Ich warte, bis der Film zu Ende ist. 0:04 12 72 Seit wann arbeitet sie nicht mehr? 0:03 13 73 Sie arbeitet nicht mehr, seitdem sie geheiratet hat. 0:04 14 74 Seitdem sie sich kennen, sind sie glücklich. 0:04 15 75 Seitdem sie Kinder haben, gehen sie selten aus. 0:04 16 76 Hast du einen Flaschenöffner? 0:03 17 77 Der Fernseher war an; trotzdem ist er eingeschlafen. 0:04 18 78 Das Hotel war zwar gemütlich, aber zu teuer. 0:04 19 79 Er nimmt entweder den Bus oder den Zug. 0:04 20 80 Sie spricht sowohl Spanisch als auch Englisch. 0:04 21 81 Er ist nicht nur dumm, sondern auch faul. 0:03 22 82 Sie ist nicht nur hübsch, sondern auch intelligent. 0:04 23 83 Ich kann weder Klavier noch Gitarre spielen. 0:04 24 84 Mein Sohn wollte nicht mit der Puppe spielen. 0:04 25 85 Meine Kinder wollten keinen Spaziergang machen. 0:04 26 86 Durftest du den Hund ins Hotel mitnehmen? 0:04 27 87 In den Ferien durften die Kinder lange draußen bleiben. 0:04 28 88 Ich dachte, du wolltest deine Frau anrufen. 0:04 29 89 Welche Kreditkarten kann man benutzen? 0:04 30 90 Ich esse sie nicht, weil ich abnehmen muss. 0:04 Table 4. GermanList value, transcription and duration of each German sentence. ItalianList StimVal Transcription Duration 1 31 Milano è una grande città nel nord Italia. 0:05 2 32 Gli abitanti di Milano si chiamano milanesi. 0:04 3 33 La prima stagione dell'anno è la primavera. 0:05 4 34 Io sono a casa con mia moglie e siamo raffreddati. 0:05 5 35 Questa sedie è di legno e quel tavolo è di plastica. 0:05 6 36 Queste scarpe sono marroni e quei pantaloni sono blu. 0:04 7 37 Mi piace questa canzone e odio quel film. 0:04 8 38 Il cane si ha spaventato per i petardi. 0:04 9 39 Sono di Cagliari, la città più importante della Sardegna. 0:04 10 40 Sono le due di notte e il cane dei vicini non smette di abbaiare. 0:05 11 41 Non sono mai stato a Pamplona, ma vorrei andarci per vedere la corsa dei tori. 0:05 12 42 Hanno aperto un nuovo centro commerciale proprio proprio dietro alla piazza principale. 0:05 13 43 In Piazza Garibaldi ci sono i Carabinieri, l'ufficio postale e la biblioteca. 0:06 14 44 Questa mattina sono andato in Piazza Garibaldi a presentare di documenti in municipio. 0:05 15 45 Prima di ritornare a casa sono passato per Piazza Marco Polo e mi sono fermato a l’ufficio postale per spedire una lettera. 0:08 16 46 Quando era bambina ricordo che i miei genitori mi portavano in vacanza al mare. 0:05 17 47 A me piaceva tuffarmi nel agua che se era fredda, a mia sorella invece il mare faceva un può di paura. 0:06 18 48 Dopo una mezz'ora ci asciughiamo e torniamo in albergo per il pranzo. 0:05 19 49 Alle quatre tornavamo in spiaggia e ci tuffavamo subito in mare per il bagno di pomeriggio. 0:05 20 50 Dopo aver cenato, ricordo che andavamo tutti insieme a fare una passeggiata per la città. 0:05 21 51 Alle nove di solito arrivano anche la seggretaria ed il direttore. 0:05 22 52 Alle due preparo un report su la produzione dell ultimo mese. 0:05 23 53 Di primo abbiamo la lasagna al ragu, penne al pomodoro e gnocchi al pesto. 0:05 24 54 Non ho capito qual è il nome della stazione della quale ha partito il suo treno. 0:05 25 55 Fare il enfermiere non è il lavoro che io sempre ho sognato di fare. 0:04 26 56 Gli studenti con i quali vai a lezioni sono tutti più giovani di te. 0:04 27 57 L’aeroporto verso cui si dirige l’aereo del presidente è il più importante del paese. 0:06 28 58 Il film del quale mi hai parlato non fa per me; preferisco altre generi. 0:05 29 59 Ho comprato un nuovo telecomando universale che funziona con tutte le televisioni che abbiamo in casa. 0:06 30 60 Giovanni dice che la sua ricetta preferita è quella che gli ha insegnato Maria. 0:05 Table 5. ItalianList value, transcription and duration of each Italian sentence. KoreanList StimVal Transcription Duration 1 91 Naneun han·gugeo·reur chogeum har su iseumnida 0:03 2 92 Yeogiseo inteones·eur iyong·har su iseumni·kka? 0:03 3 93 Kan·jang·gong·jang kong·jang·jang·eun kang kong·jang·jang·igo. 0:04 4 94 Tashi malsseumae·juseyo. 0:03 5 95 Choe kajogi yogui issoyeo 0:04 6 96 Onje chorel jan bon panmunaseyo. 0:03 7 97 Urinen jakyoe issoyo. 0:03 8 98 Urinen saramdelgua marago shipoyo. 0:04 9 99 Urinen panguasari piriojeyo. 0:04 10 100 Urinen yorume sanchek kanengosel choajeyo. 0:04 11 101 Kyorenen nuni ogona piga huayo. 0:04 12 102 Chonen clashic umaguel choajeyo. 0:04 13 103 Chonen chiguem i chegl ilgo issoyeo. 0:04 14 104 Chaueguiga innenbanguel uanjeyo. 0:03 15 105 Myoshie sonyok shiksarel choyo? 0:03 16 106 Koguirel annon kosel chuseyo. 0:03 17 107 Senkrim onyen aiskrimel chuseyo. 0:04 18 108 Kichaga onje Vienae totchakeo? 0:04 19 109 Yogui choen shiktangui odi issoyeo? 0:04 20 110 Odissoe kochel salso issoyeo? 0:03 21 111 Chisangui irioil mada yoroyo? 0:03 22 112 Onel choniogue yongjaguaneso mol sanguonjeyo? 0:04 23 113 Toguil timi yonguk timgua yonguihago issoyeo. 0:04 24 114 Yoguie chogumdo momurel koyeyo? 0:04 25 115 Do nuga kopirel mashigo shipoyo? 0:03 26 116 Cho yochaie pomonimi nuguseyo? 0:03 27 117 Kenyoi punmunyim chibe ottoke kayo? 0:04 28 118 Ke chibun ke kireil kette issoyeo. 0:04 29 119 Chochennaren uorioirieyo. 0:03 30 120 Ilchoirenen chiriri issoyeo. 0:03 Table 6. KoreanList value, transcription and duration of each Korean sentence. SpanishList StimVal Transcription Duration 1 1 Yo ayudo a mi padre en la cocina. 0:04 2 2 Mi hermana estudia en su habitación. 0:04 3 3 Mi madre lava el coche verde. 0:04 4 4 Mi abuela pasea todos los días. 0:04 5 5 Los perros juegan en el jardín. 0:04 6 6 El cerdo come bellotas. 0:04 7 7 El conejo es veloz. 0:04 8 8 Me levanto a las 8:00 de la mañana. 0:04 9 9 El próximo 4 de octubre José Sáez publica su tercer disco. 0:04 10 10 El Congreso español prohibió fumar en sus instalaciones, anticipándose a una ley del Gobierno que prohíbe el cigarrillo en los sitios de trabajo de toda España. 0:08 11 11 No sé lo que tiene todavía, pero le duele mucho la cabeza y la garganta. 0:06 12 12 Tome estas pastillas tres veces al día después de comer algo. 0:04 13 13 Mi compañero tiene una niña muy bonita. 0:04 14 14 El menú de 14 euros consiste en sopa de pescado, lenguado y tarta de manzana. 0:07 15 15 Como ve, el piso es pequeño pero está muy limpio. 0:03 16 16 Desde las 2 hasta las 5 las tiendas están cerradas. 0:05 17 17 En cuanto llegues, quiero que prepares la merienda para Luisito y su amigo Jaime. 0:04 18 18 Después de merendar, no quiero que vean la tele; diles que hagan los deberes primero. 0:05 19 19 Hay unos filetes de pescado en la nevera, pero no creo que haya ninguna verdura fresca. 0:05 20 20 En febrero se celebra el Carnaval en casi todas las ciudades de España. 0:04 21 21 Durante la Feria de Abril de Sevilla, los sevillanos llevan los trajes típicos de Andalucía, bailan sevillanas y flamenco y montan a caballo. 0:08 22 22 En agosto y septiembre hay muchas fiestas y verbenas locales por todo el país. 0:05 23 23 A mí no me gusta nada la música clásica. 0:04 24 24 A mí me gustan mucho las películas de los hermanos Cohen. 0:04 25 25 Dentro de la ciudad, el metro es el medio de transporte más rápido y popular. 0:05 26 26 Funciona desde la 6.00 de la mañana hasta la 1.30 de la madrugada. 0:05 27 27 Además, Madrid tiene 165 líneas de autobuses que funcionan entre las 6.00 y las 24.00 horas. 0:07 28 28 Esos girasoles y esos geranios son gigantes. 0:04 29 29 La gente de Gibraltar habla inglés y español. 0:04 30 30 ¿Podría hablar con el señor López, por favor? 0:03 Table 7. SpanishList value, transcription and duration of each Spanish sentence. References ----------------------------------- [1] Isaac Ariza, Ana M. Barbancho, Lorenzo J. Tardón, Isabel Barbancho, Energy-based features and bi-LSTM neural network for EEG-based music and voice classification. Neural Comput & Applic 36, 791–802 (2024). https://doi.org/10.1007/s00521-023-09061-3