Italy

Intonation of telephone conversations in a Customer Care Service RATP-DECODA is a Customer Care Service corpus part of the ORFEO project (2020). It includes 1988 recordings of client requests made between 2009 and 2011 to the RATP call center (Régie Autonome des Transports Parisiens). The total duration of these calls is about 98 hours, with an average of 177 seconds per call. Recordings were made in a mp3 format, converted in the Orfeo corpus into stereo 16 bit 8000 Hz sampling rate, and for the present research in mono 16 bit 22050 Hz. The files are originally annotated in word and phone segments, in trs (Transcriber) and also into TextGrid (Praat) format. The compressed recording format used (mp3) and the telephone line characteristics limit the sound bandwidth to about 120-3900 Hz, which affects the reliability of most pitch trackers and of the automatic segmentation program used for word and phone annotations, especially for male voices. Nevertheless, using dedicated functions of the WinPitch (2020) speech analysis software, errors of segmentation were easily corrected manually, and pitch detection errors have been monitored by the simultaneous display of a narrow band spectrogram and graphically corrected (Martin, 2018a). Conversations usually involve 2 participants: a client, the customer agent and eventually a service voice. Call types as noted in Brechet et al. (2012) were:&lt;br&gt;
Info Traffic 22.5%; Route planning 17.2%; Lost and Found 15.9%; Registration card 11.4; Timetable 4.6%; Ticket 4.5%; Specialized calls 4.5%; empty 3.6%; New registration 3.4%; Price info 3.0%.
While some semantic and syntactic observations have already be made in Brechet et al. (2012), no analysis of intonation has so far been conducted, showing in these specific discourse conditions the role of prosody in structuring controlled exchanges between two participants. As most of the recordings have a duration below 3 minutes, the effect of client characteristics on the agents, for instance perceived age and fluency, can be analyzed more easily in this restricted time frame.&lt;br&gt;
Melodic changes were annotated with WinPitch, allowing an easy graphic contour annotation from the existing segmentation into words and phones, as well as with an underlying narrow band spectrogram that would guarantee the validity of the annotated contour in term of frequency and duration (see Martin, 2018a). According to the incremental prosodic structure model (Martin, 2018b), prosodic annotations consist of melodic contours, mostly linear, located on stressed vowels (not syllables), and automatically classified from their slope in terms of direction and glissando values (i.e. perceived as a melodic change vs. perceived as a static tone): Cdec conclusive déclarative contour, perceived as sentence terminal; Cint conclusive interrogative contour, also perceived as sentence terminal; Cris rising continuation contour, as a melodic change; Cfal falling continuation contour, perceived as a melodic change; Cneu rising or falling contour, perceived as a static tone. Description of these contours in terms of frequency, duration and intensity, are automatically transferred on a spreadsheet program such as Excel for detailed phonetic analysis. In the intonation grammar of French retained for this research, the prosodic structure is defined by dependency relations “to the right”, i.e. when a given contour category depends on the category of another contour located further in the sentence. For instance, the falling contour Cfal depends on a rising contour Cris placed further in the sentence, Cris depends on a Cdec occurring later in the sentence, whereas Cneu depends on either a Cfal, Cris or Cdec / Cint located on its “right”.&lt;br&gt;
This intonation grammar is based on the contrast of melodic slope principle, essentially validated earlier on various read and spontaneous speech corpora involving mostly declarative sentences (see Martin, 2018b). The issue here is to validate this slope inversion principle for sentences using a final rising contour to indicate its interrogative modality. in which we would have Cfal depending on a terminal interrogative Cint, and possibly Cris depending on a Cfal located further in the sentence. However, most interrogative sentences of the corpus were rather of short duration, preventing the occurrence of a prosodic structure with 2 or 3 levels, therefore using the Cris -&gt; Cfal dependency with the expected melodic contrast. Speaker sentences are usually quite short, with limited occurrences of reformulation and abandons, contrary to other spontaneous speech corpora. The speaker sentence prosody appears therefore rather well planned, striving for the shortest duration possible. Given the fact that clients had no clue in advance as to the personality of customer agent that will answer them, they usually start their calls with indirect questions with a declarative prosodic structure ended by Cdec, or alternatively with a statement describing the problem followed by a very short question associated to an interrogative prosodic structure (ended by a rising contour Cint). Likewise, if most customer use indirect questions in their demands, the eventual questions made by the agent to obtain some clarification use intonation to express an interrogative modality.&lt;br&gt;
In some recordings, agents will slow down the speech rate and expanding the melodic variations on stressed syllables in order to be better understood. Typical prosodic structure configuration such as long lists in route planning exchanges, segmentation of the sentence into prosodic nucleus and postnucleus (with a limited melodic excursion), etc. Analysis of abandons and reformulations in client sentences also illustrate the planning of the prosodic structure before the lexical items, which are substituted afterwards keeping the same melodic contour of the planned prosodic structure.&lt;br&gt;

References

Bechet F. et al. (2012) DECODA: a call-centre human-human spoken conversation corpus, Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC&#39;12), pp. 1343-1347.&lt;br&gt;
Martin, Ph (2018a) Prosodic annotation in adverse recording conditions, a cura di A. De Dominicis, Speech audio archives: preservation, restoration, annotation, aimed at supporting the linguistic analysis, Accademia Nazionale dei Lincei,&lt;br&gt;
Martin Ph. (2018b) Intonation, structure prosodique et ondes cérébrales, London : ISTE, 322 p.&lt;br&gt;
ORFEO (2020) Corpus d’étude pour le français contemporain https://www.projet-orfeo.fr/&lt;br&gt;
WinPitch (2020) Computer program, www.winpitch.com

LIV Congresso SLI 2021

Intonation of telephone conversations in a Customer Care Service

### Benvenuti 
al *LIV Congresso internazionale della Società di Linguistica Italiana ''Corpora e Studi Linguistici''* che si tiene qui in rete nella piattaforma fornita da Underline. Il Congresso si sviluppa su 3 giornate divise in:

* cinque Sessioni plenarie, 
* due Sessioni Demo dedicate ai corpora italiani e internazionali, 
* una Sessione Poster e 
* una Sessione workshop con 5 workshop in parallelo. 

Gli interventi orali saranno sia in diretta che preregistrati, secondo la volontà degli autori, ma per tutti sarà possibile l’interazione dal vivo con domande e risposte. A tutte le sessioni si accede attraverso le icone sulla sinistra di questa pagina. 
 Nelle sessioni Poster e Demo ci si muove virtualmente tra le proposte attraverso Gather-Town, che permette ai congressisti anche di incontrarsi in qualsiasi momento nella Lounge virtuale.
 Ringraziamo tutti per l’impegno e la pazienza e ci auguriamo una buona riuscita del Congresso. Un ringraziamento particolare ai relatori invitati Bas Aarts (University College London), Gu Yueguo (The Chinese Academy of Social Sciences) e Mirko Tavoni (Università di Pisa) 
 

**Welcome** to the *54th Congress of the International Society of Italian Linguistics ''Corpora and Linguistic Studies''*
which is held here through the Underline Platform. The Congress develops in 3 days which host:

* five Plenary sections, 
* two Demo sessions, 
* dedicated to Italian and international corpus building initiatives, 
* one Poster session and 
* one Workshops session hosting 5 workshops in parallel. 

Oral presentations are given in synchronous or are pre registered according to the will of each author, however Q/A will be live for all. All sessions can be accessed through the icons on the left side of this page. 
 In the Poster and Demo sessions you will be able to move among the various items though Gather-town. Congress participants can always meet in the Virtual lounge.
 We wish to thank all participants for their work and patience. A special thanks to our invited speakers Bas Aarts (University College London), Gu Yueguo (The Chinese Academy of Social Sciences) e Mirko Tavoni (Università di Pisa)

![](https://assets.underline.io/uploads/markdown_image/1/image/dacffc533f05582ca945abd01bb616ea.png)

If you have already registered, please **login** to Underline.io to be able to see full conference content. 
 In case you do not have an Underline account, please **create** one. Thank you!

Intonation of telephone conversations in a Customer Care Service RATP-DECODA is a Customer Care Service corpus part of the ORFEO project (2020). It includes 1988 recordings of client requests made between 2009 and 2011 to the RATP call center (Régie Autonome des Transports Parisiens). The total duration of these calls is about 98 hours, with an average of 177 seconds per call. Recordings were made in a mp3 format, converted in the Orfeo corpus into stereo 16 bit 8000 Hz sampling rate, and for the present research in mono 16 bit 22050 Hz. The files are originally annotated in word and phone segments, in trs (Transcriber) and also into TextGrid (Praat) format. The compressed recording format used (mp3) and the telephone line characteristics limit the sound bandwidth to about 120-3900 Hz, which affects the reliability of most pitch trackers and of the automatic segmentation program used for word and phone annotations, especially for male voices. Nevertheless, using dedicated functions of the WinPitch (2020) speech analysis software, errors of segmentation were easily corrected manually, and pitch detection errors have been monitored by the simultaneous display of a narrow band spectrogram and graphically corrected (Martin, 2018a). Conversations usually involve 2 participants: a client, the customer agent and eventually a service voice. Call types as noted in Brechet et al. (2012) were: 
Info Traffic 22.5%; Route planning 17.2%; Lost and Found 15.9%; Registration card 11.4; Timetable 4.6%; Ticket 4.5%; Specialized calls 4.5%; empty 3.6%; New registration 3.4%; Price info 3.0%.
While some semantic and syntactic observations have already be made in Brechet et al. (2012), no analysis of intonation has so far been conducted, showing in these specific discourse conditions the role of prosody in structuring controlled exchanges between two participants. As most of the recordings have a duration below 3 minutes, the effect of client characteristics on the agents, for instance perceived age and fluency, can be analyzed more easily in this restricted time frame. 
Melodic changes were annotated with WinPitch, allowing an easy graphic contour annotation from the existing segmentation into words and phones, as well as with an underlying narrow band spectrogram that would guarantee the validity of the annotated contour in term of frequency and duration (see Martin, 2018a). According to the incremental prosodic structure model (Martin, 2018b), prosodic annotations consist of melodic contours, mostly linear, located on stressed vowels (not syllables), and automatically classified from their slope in terms of direction and glissando values (i.e. perceived as a melodic change vs. perceived as a static tone): Cdec conclusive déclarative contour, perceived as sentence terminal; Cint conclusive interrogative contour, also perceived as sentence terminal; Cris rising continuation contour, as a melodic change; Cfal falling continuation contour, perceived as a melodic change; Cneu rising or falling contour, perceived as a static tone. Description of these contours in terms of frequency, duration and intensity, are automatically transferred on a spreadsheet program such as Excel for detailed phonetic analysis. In the intonation grammar of French retained for this research, the prosodic structure is defined by dependency relations “to the right”, i.e. when a given contour category depends on the category of another contour located further in the sentence. For instance, the falling contour Cfal depends on a rising contour Cris placed further in the sentence, Cris depends on a Cdec occurring later in the sentence, whereas Cneu depends on either a Cfal, Cris or Cdec / Cint located on its “right”. 
This intonation grammar is based on the contrast of melodic slope principle, essentially validated earlier on various read and spontaneous speech corpora involving mostly declarative sentences (see Martin, 2018b). The issue here is to validate this slope inversion principle for sentences using a final rising contour to indicate its interrogative modality. in which we would have Cfal depending on a terminal interrogative Cint, and possibly Cris depending on a Cfal located further in the sentence. However, most interrogative sentences of the corpus were rather of short duration, preventing the occurrence of a prosodic structure with 2 or 3 levels, therefore using the Cris -> Cfal dependency with the expected melodic contrast. Speaker sentences are usually quite short, with limited occurrences of reformulation and abandons, contrary to other spontaneous speech corpora. The speaker sentence prosody appears therefore rather well planned, striving for the shortest duration possible. Given the fact that clients had no clue in advance as to the personality of customer agent that will answer them, they usually start their calls with indirect questions with a declarative prosodic structure ended by Cdec, or alternatively with a statement describing the problem followed by a very short question associated to an interrogative prosodic structure (ended by a rising contour Cint). Likewise, if most customer use indirect questions in their demands, the eventual questions made by the agent to obtain some clarification use intonation to express an interrogative modality. 
In some recordings, agents will slow down the speech rate and expanding the melodic variations on stressed syllables in order to be better understood. Typical prosodic structure configuration such as long lists in route planning exchanges, segmentation of the sentence into prosodic nucleus and postnucleus (with a limited melodic excursion), etc. Analysis of abandons and reformulations in client sentences also illustrate the planning of the prosodic structure before the lexical items, which are substituted afterwards keeping the same melodic contour of the planned prosodic structure. 

References

Bechet F. et al. (2012) DECODA: a call-centre human-human spoken conversation corpus, Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pp. 1343-1347. 
Martin, Ph (2018a) Prosodic annotation in adverse recording conditions, a cura di A. De Dominicis, Speech audio archives: preservation, restoration, annotation, aimed at supporting the linguistic analysis, Accademia Nazionale dei Lincei, 
Martin Ph. (2018b) Intonation, structure prosodique et ondes cérébrales, London : ISTE, 322 p. 
ORFEO (2020) Corpus d’étude pour le français contemporain https://www.projet-orfeo.fr/ 
WinPitch (2020) Computer program, www.winpitch.com

keynote

El corpus ESLORA contiene 60 horas de entrevistas semidirigidas y 20 horas de conversaciones de hablantes de Galicia. Los registros sonoros se transcribieron ortográficamente con alineación texto-voz. Los textos han sido lematizados y anotados morfosintácticamente para faciltar la consulta mediante diversos tipos de búsquedas que combinan variables sociales e interaccionales (grupo de edad, nivel de estudios, mujer/hombre, rol comunicativo) junto a categorías lingüísticas (lemas, clases de palabras y categorías morfológicas). El proyecto se ha guiado por tres objetivos generales: (i) Incrementar la amplitud y variedad de los materiales orales disponibles en español. En comparación con la extensión de los corpus escritos, la escasez de muestras orales accesibles en condiciones idóneas resultaba especialmente notoria en el caso del español hablado en Galicia. (ii) Avanzar en el conocimiento de los métodos de construcción de corpus orales. Se han evaluado las dos técnicas más usadas en la obtención de registros de habla informal: la entrevista semidirigida y la grabación de conversaciones espontáneas. El contraste entre ambos subcorpus confirma que el empleo de una u otra técnica condiciona en diversos aspectos las características de los datos obtenidos. (iii) Desarrollar recursos computacionales para la consulta, el análisis y la explotación del corpus. Se generaron recursos accesibles que permiten a los investigadores y al conjunto de la comunidad desarrollar nuevos estudios relacionados con el español oral. Tanto el etiquetador estadístico para la anotación morfosintáctica de los textos como la aplicación de consulta son herramientas de gran utilidad para un aprovechamiento adecuado del corpus.

ESLORA: un corpus de español hablado en Galicia

Read abstract **[here](https://s3.amazonaws.com/pf-upload-01/u-59356/0/2021-08-27/ee52nmg/abstract%20SLI%202020%20aggiornato.pdf)**



Banche dati per il trasmesso: il LIR e il LIT

Read abstract **[here](https://drive.google.com/file/d/1j5F8tyesX0hM_T6MHaKeSm1YtQ5RkseB/view?usp=sharing)** 




Corpus Multimodale Annotato per lo studio della gestualità co-verbale nel parlato parlato e nel parlato recitato

Read abstract **[here](https://s3.amazonaws.com/pf-upload-01/u-59356/0/2021-08-02/40330jp/SLI_2020_abstract_36.pdf)**





Corpus dell'Italiano Parlato LABLITA; Corpora comparabili delle lingue romanze parlate (C-ORAL-ROM); Corpora didattici dello spagnolo (CORDIAL); Data Base interlinguistico dell'articolazione dell'informazione (DB-IPIC)

Read abstract **[here](https://s3.amazonaws.com/pf-upload-01/u-59356/0/2021-08-30/j532mnx/DEMO%20SLI_ag2021.pdf)**



Corpora di italiano parlato patologico dell'età adulta e senile: CIPPS, CIPP-ma, CIPP-mci

Read abstract **[here](https://s3.amazonaws.com/pf-upload-01/u-59356/0/2021-08-07/ln23sov/SLI_2020_Ganfi%26Piunno_revised%20Abstract.pdf)**


Il corpus KIParla

Presenteremo i tre grandi corpora sviluppati dal nostro gruppo di ricerca, con la collaborazione di John Sinclair, e liberamente consultabili sul Web. Per tutti i tre corpora è stato effettuato un attento studio preliminare per garantirne il maggior grado di rappresentatività possibile rispetto alla varietà linguistica considerata. Il progetto più rilevante ha riguardato la creazione di un corpus di riferimento rappresentativo dell’italiano contemporaneo (CORIS); è disponibile online dal 2001 e costantemente aggiornato, ogni tre anni, per cogliere le variazioni nel lessico e nei rapporti di frequenza. E’ stato annotato automaticamente per parti del discorso e lemmi. CODIS, la sua controparte dinamica, consente allo studioso di combinare liberamente insiemi predefiniti di testi per costruire il corpus ideale per studi specifici o per studi interlinguistici. DiaCORIS, sviluppato in collaborazione con L’Accademia della Crusca, riproduce la struttura in macro-varietà testuali di CORIS a livello diacronico. Contiene testi dall’Unità d’Italia agli anni 2000 adeguatamente annotati rispetto ai principali metadati. E’ disponibile online dal 2006. BoLC è un corpus bilingue (italiano/inglese) di linguaggio giuridico contenente una sezione parallela (documenti dell’UE) e una sezione comparabile. Consente lo studio delle differenti terminologie adottate da due sistemi giuridici (common law vs civil law) così diversi. E’ disponibile online dal 2011.

I corpora del FICLIT, Università di Bologna

Read abstract **[here](https://s3.amazonaws.com/pf-upload-01/u-59356/0/2021-08-05/4r33j97/SLI_proposal-EvaLatin-11.pdf)**



EvaLatin 1.0: un Corpus per la Valutazione delle Tecnologie del Linguaggio Applicate al Latino

Read abstract **[here](https://s3.amazonaws.com/pf-upload-01/u-59356/0/2021-08-06/4r13qhs/CfP--SLI2020--v21.pdf)**




Esplorazioni di treebank multilingue per studi tipologici

Lo studio dell’apprendimento (e dell’insegnamento) dell’italiano a stranieri sta vivendo un periodo particolarmente vivace e un corpus di testi scritti da allievi stranieri, se organizzato in modo adeguato, può essere molto utile sia ai docenti di italiano a stranieri in Italia o all’estero, sia agli studenti universitari che desiderano prepararsi ad insegnare italiano LS/L2, sia – ovviamente – ai ricercatori.  VALICO è uno dei maggiori corpora di italiano di stranieri liberamente accessibili in rete. Le sue caratteristiche salienti sono: raccolta di testi a partire da stimoli iconici, base di dati sociolinguistici degli autori dei testi e corpus interrogabili congiuntamente, ricerche attraverso un approccio georeferenziato, integrato con la risorsa orale “le voci di VALICO” ed esercizi tratti dal corpus stesso, possibilità di confrontare le ricerche sul corpus con il corpsu VINCA, composto da testi raccolti a partire dagli stessi stimoli.  Il nuovo arricchimento della risorsa prevede l’annotazione automatica della sintassi (seguendo lo schema di annotazione standard de facto delle Universal Dependencies) e la sua correzione manuale in una sezione gold per la quale è stata realizzata anche l’annotazione manuale degli errori degli apprendenti.

Intonation of telephone conversations in a Customer Care Service

Speakers

Downloads

Next from LIV Congresso SLI 2021

ESLORA: un corpus de español hablado en Galicia

Similar lecture

Costruzioni a lista nell'italiano parlato