Technical Program
Wednesday, November 21 |
|
| Oral 1: Speaker Recognition Wednesday, 21 November 2018, 09:20 – 10:40 Chair: Xavier Anguera |
|
| O1.1 09:20 – 09:40 |
Differentiable Supervector Extraction for Encoding Speaker and Phrase Information in Text Dependent Speaker Verification   |
| Victoria Mingote, Antonio Miguel, Alfonso Ortega and Eduardo Lleida | |
| O1.2 09:40 – 10:00 |
Phonetic Variability Influence on Short Utterances in Speaker Verification |
| Ignacio Viñals, Alfonso Ortega, Antonio Miguel and Eduardo Lleida | |
| O1.3 10:00 – 10:20 |
Restricted Boltzmann Machine Vectors for Speaker Clustering |
| Umair Khan, Pooyan Safari and Javier Hernando | |
| O1.4 10:20 – 10:40 |
Speaker Recognition under Stress Conditions |
| Esther Rituerto-González, Ascensión Gallardo-Antolín and Carmen Peláez-Moreno | |
| Keynote 1 Wednesday, 21 November 2018, 11:00 – 12:00 Chair: Joan Serrà |
|
| KN1 11:00 – 12:00 |
Bio signal-based Spoken Communication |
| Tanja Schultz | |
| Posters: Topics on Speech Technologies Wednesday, 21 November 2018, 12:00 – 13:30 Chair: Alberto Abad |
|
| P1.1 12:00 – 13:30 |
Bilingual Prosodic Dataset Compilation for Spoken Language Translation |
| Alp Oktem, Mireia Farrús and Antonio Bonafonte | |
| P1.2 12:00 – 13:30 |
Building an Open Source Automatic Speech Recognition System for Catalan |
| Baybars Külebi and Alp Öktem | |
| P1.3 12:00 – 13:30 |
Multi-Speaker Neural Vocoder |
| Oriol Barbany Mayor, Antonio Bonafonte and Santiago Pascual | |
| P1.4 12:00 – 13:30 |
Improving the Automatic Speech Recognition through the improvement of Laguage Models |
| Andrés Piñeiro-Martín, Carmen Garcia-Mateo and Laura Docio-Fernandez | |
| P1.5 12:00 – 13:30 |
Towards expressive prosody generation in TTS for reading aloud applications |
| Monica Dominguez, Alicia Burga, Mireia Farrús and Leo Wanner | |
| P1.6 12:00 – 13:30 |
Performance evaluation of front- and back-end techniques for ASV spoofing detection systems based on deep features |
| Alejandro Gomez-Alanis, Antonio M. Peinado, Jose A. Gonzalez and Angel M. Gomez | |
| P1.7 12:00 – 13:30 |
The observation likelihood of silence: analysis and prospects for VAD applications |
| Igor Odriozola, Inma Hernaez, Eva Navas, Luis Serrano and Jon Sanchez | |
| P1.8 12:00 – 13:30 |
On the use of Phone-based Embeddings for Language Recognition |
| Christian Salamea, Ricardo Córdoba, Luis Fernando D’Haro, Rubén San-Segundo and Javier Ferreiros | |
| P1.9 12:00 – 13:30 |
End-to-End Speech Translation with the Transformer |
| Laura Cross Vila, Carlos Escolano, José A. R. Fonollosa and Marta R. Costa-Jussà | |
| P1.10 12:00 – 13:30 |
Audio event detection on Google’s Audio Set database: Preliminary results using different types of DNNs |
| Javier Darna-Sequeiros and Doroteo T. Toledano | |
| P1.11 12:00 – 13:30 |
Emotion Detection from Speech and Text |
| Mikel de Velasco, Raquel Justo, Josu Antón, Mikel Carrilero and M. Inés Torres | |
| P1.12 12:00 – 13:30 |
Experimental Framework Design for Sign Language Automatic Recognition |
| Darío Tilves Santiago, Ian Benderitter and Carmen García Mateo | |
| P1.13 12:00 – 13:30 |
Baseline Acoustic Models for Brazilian Portuguese Using Kaldi Tools |
| Cassio Batista, Ana Larissa Dias and Nelson Sampaio Neto | |
| Oral 2: ASR & Speech Applications Wednesday, 21 November 2018, 15:00 – 16:40 Chair: Carmen García Mateo |
|
| O2.1 15:00 – 15:20 |
Converted Mel-Cepstral Coefficients for Gender Variability Reduction in Query-by-Example Spoken Document Retrieval |
| Paula López Otero and Laura Docío Fernández | |
| O2.2 15:20 – 15:40 |
A Recurrent Neural Network Approach to Audio Segmentation for Broadcast Domain Data |
| Pablo Gimeno, Ignacio Viñals, Alfonso Ortega, Antonio Miguel and Eduardo Lleida | |
| O2.3 15:40 – 16:00 |
Improving Transcription of Manuscripts with Multimodality and Interaction |
| Emilio Granell, Carlos David Martinez Hinarejos and Verónica Romero | |
| O2.4 16:00 – 16:20 |
Improving Pronunciation of Spanish as a Foreign Language for L1 Japanese Speakers with Japañol CAPT Tool |
| Cristian Tejedor-García, Valentín Cardeñoso-Payo, María J. Machuca, David Escudero, Antonio Ríos and Takuya Kimura | |
| O2.5 16:20 – 16:40 |
Exploring E2E speech recognition systems for new languages |
| Conrad Bernath, Aitor Alvarez, Haritz Arzelus and Carlos David Martínez | |
| Oral 3: Speech & Language Technologies Applied to Health Wednesday, 21 November 2018, 17:00 – 18:40 Chair: Mireia Farrús |
|
| O3.1 17:00 – 17:20 |
Listening to Laryngectomees: A study of Intelligibility and Self-reported Listening Effort of Spanish Oesophageal Speech |
| Sneha Raman, Inma Hernaez, Eva Navas and Luis Serrano | |
| O3.2 17:20 – 17:40 |
Towards an automatic evaluation of the prosody of people with Down syndrome |
| Mario Corrales-Astorgano, Pastora Martínez-Castilla, David Escudero-Mancebo, Lourdes Aguilar, César González-Ferreras and Valentín Cardeñoso-Payo | |
| O3.3 17:40 – 18:00 |
Whispered-to-voiced Alaryngeal Speech Conversion with Generative Adversarial Networks |
| Santiago Pascual, Antonio Bonafonte, Joan Serrà and Jose Andrés González | |
| O3.4 18:00 – 18:20 |
LSTM based voice conversion for laryngectomees |
| Luis Serrano, David Tavarez, Xabier Sarasola, Sneha Raman, Ibon Saratxaga, Eva Navas and Inma Hernaez | |
| O3.5 18:20 – 18:40 |
Sign Language Gesture Classification using Neural Networks |
| Zuzanna Parcheta and Carlos David Martinez Hinarejos | |
Thursday, November 22 |
|
| Oral 4: Synthesis, Production & Analysis Thursday, 22 November 2018, 09:00 – 10:40 Chair: Francesc Alías Pujol |
|
| O4.1 09:00 – 09:20 |
Influence of tense, modal and lax phonation on the three-dimensional finite element synthesis of vowel [A] |
| Marc Freixes, Marc Arnela, Joan Claudi Socoró, Francesc Alías Pujol and Oriol Guasch | |
| O4.2 09:20 – 09:40 |
Exploring Advances in Real-time MRI for Speech Production Studies of European Portuguese |
| Conceicao Cunha, Samuel Silva, António Teixeira, Catarina Oliveira, Paula Martins, Arun Joseph and Jens Frahm | |
| O4.3 09:40 – 10:00 |
A postfiltering approach for dual-microphone smartphones |
| Juan M. Martín-Doñas, Iván López-Espejo, Angel M. Gomez and Antonio M. Peinado | |
| O4.4 10:00 – 10:20 |
Speech and monophonic singing segmentation using pitch parameters |
| Xabier Sarasola, Eva Navas, David Tavarez, Luis Serrano and Ibon Saratxaga | |
| O4.5 10:20 – 10:40 |
Self-Attention Linguistic-Acoustic Decoder |
| Santiago Pascual, Antonio Bonafonte and Joan Serrà | |
| Keynote 2 Thursday, 22 November 2018, 11:00 – 12:00 Chair: Antonio Bonafonte |
|
| KN2 11:00 – 12:00 |
Synthesizing variation in prosody for Text-to-Speech |
| Rob Clark | |
| Special Session: Demo, Projects & PhD Thesis Thursday, 22 November 2018, 12:00 – 13:30 Chair: Ricardo de Córdoba |
|
12:00 – 12:20 |
Thesis in 4 Minutes competition. |
| Papers SP.8, SP.9, SP.10 and SP.11 | |
| Show and Tell | |
| SP.1 12:20 – 13:30 |
Japañol: a mobile application to help improving Spanish pronunciation by Japanese native speakers |
| Cristian Tejedor-García, Valentín Cardeñoso-Payo and David Escudero-Mancebo | |
| Research Projects | |
| SP.2 12:20 – 13:30 |
Towards the Application of Global Quality-of-Service Metrics in Biometric Systems |
| Juan Manuel Espín, Roberto Font, Juan Francisco Inglés-Romero and Cristina Vicente-Chicote | |
| SP.3 12:20 – 13:30 |
Incorporation of a Module for Automatic Prediction of Oral Productions Quality in a Learning Video Game |
| David Escudero and Valentín Cardeñoso-Payo | |
| SP.4 12:20 – 13:30 |
Silent Speech: Restoring the Power of Speech to People whose Larynx has been Removed |
| Jose Andres Gonzalez Lopez, Phil D. Green, Damian Murphy, Amelia Gully and James M. Gilbert | |
| SP.5 12:20 – 13:30 |
RESTORE Project: REpair, STOrage and REhabilitation of speech |
| Inma Hernaez, Eva Navas, Jose Antonio Municio Martín and Javier Gomez Suárez | |
| SP.6 12:20 – 13:30 |
Corpus for Cyberbullying Prevention |
| Asuncion Moreno, Antonio Bonafonte, Igor Jauk, Laia Tarrés and Victor Pereira | |
| SP.7 12:20 – 13:30 |
EMPATHIC, Expressive, Advanced Virtual Coach to Improve Independent Healthy-Life-Years of the Elderdy |
| M. Ines Torres, Gérard Chollet, César Montenegro, Jofre Tenorio-Laranga, Olga Gordeeveva, Anna Esposito, Cornelius Glackin, Stephan Schlögl, Olivier Deroo, Begoña Fernández-Ruanova, Riberto Santana, Maria S. Kornes, Fred Lindner, Daria Kyslitska, Miriam Reiner, Gennaro Cordasco, Mari Aksnes and Raquel Justo Blanco | |
| PhD Thesis | |
| SP.8 12:20 – 13:30 |
Advances on the Transcription of Historical Manuscripts based on Multimodality, Interactivity and Crowdsourcing |
| Emilio Granell, Carlos David Martinez Hinarejos and Verónica Romero | |
| SP.9 12:20 – 13:30 |
Bottleneck and Embedding Representation of Speech for DNN-based Language and Speaker Recognition |
| Alicia Lozano-Diez, Joaquin Gonzalez-Rodriguez and Javier Gonzalez-Dominguez | |
| SP.10 12:20 – 13:30 |
Deep Learning for i-Vector Speaker and Language Recognition: A Ph.D. Thesis Overview |
| Omid Ghahabi | |
| SP.11 12:20 – 13:30 |
Unsupervised Learning for Expressive Speech Synthesis |
| Igor Jauk | |
| Albayzin Evaluation Thursday, 22 November 2018, 15:00 – 16:40 Chair: Alfonso Ortega & Eduardo Lleida |
|
| Multimodal Diarization Challenge | |
| AE.1 15:00 – 19:00 |
ODESSA/PLUMCOT at Albayzin Multimodal Diarization Challenge 2018 |
| Benjamin Maurice, Hervé Bredin, Ruiqing Yin, Jose Patino, Héctor Delgado, Claude Barras, Nicholas Evans and Camille Guinaudeau | |
| AE.2 15:00 – 19:00 |
UPC Multimodal Speaker Diarization System for the 2018 Albayzin Challenge |
| Miquel Angel India Massana, Itziar Sagastiberri, Ponç Palau, Elisa Sayrol, Josep Ramon Morros and Javier Hernando | |
| AE.3 15:00 – 19:00 |
The GTM-UVIGO System for Audiovisual Diarization |
| Eduardo Ramos-Muguerza, Laura Docío-Fernández and José Luis Alba-Castro | |
| Speaker Diarization Challenge | |
| AE.4 15:00 – 19:00 |
The SRI International STAR-LAB System Description for IberSPEECH-RTVE 2018 Speaker Diarization Challenge |
| Diego Castan, Mitchell McLaren and Mahesh Kumar Nandwana | |
| AE.5 15:00 – 19:00 |
ODESSA at Albayzin Speaker Diarization Challenge 2018 |
| Jose Patino, Héctor Delgado, Ruiqing Yin, Hervé Bredin, Claude Barras and Nicholas Evans | |
| AE.6 15:00 – 19:00 |
EML Submission to Albayzin 2018 Speaker Diarization Challenge |
| Omid Ghahabi and Volker Fischer | |
| AE.7 15:00 – 19:00 |
In-domain Adaptation Solutions for the RTVE 2018 Diarization Challenge |
| Ignacio Viñals, Pablo Gimeno, Alfonso Ortega, Antonio Miguel and Eduardo Lleida | |
| AE.8 15:00 – 19:00 |
DNN-based Embeddings for Speaker Diarization in the AuDIaS-UAM System for the Albayzin 2018 IberSPEECH-RTVE Evaluation |
| Alicia Lozano-Diez, Beltran Labrador, Diego de Benito, Pablo Ramirez and Doroteo T. Toledano | |
| AE.9 15:00 – 19:00 |
CENATAV Voice-Group Systems for Albayzin 2018 Speaker Diarization Evaluation Campaign |
| Edward L. Campbell, Gabriel Hernandez and José R. Calvo de Lara | |
| AE.10 15:00 – 19:00 |
The Intelligent Voice System for the IberSPEECH-RTVE 2018 Speaker Diarization Challenge |
| Abbas Khosravani, Cornelius Glackin, Nazim Dugan, Gérard Chollet and Nigel Cannings | |
| AE.11 15:00 – 19:00 |
JHU Diarization System Description |
| Zili Huang, L. Paola García-Perera, Jesús Villalba, Daniel Povey and Najim Dehak | |
| Search on Speech Challenge | |
| AE.12 15:00 – 19:00 |
GTM-IRLab Systems for Albayzin 2018 Search on Speech Evaluation |
| Paula López Otero and Laura Docio-Fernandez | |
| AE.13 15:00 – 19:00 |
AUDIAS-CEU: A Language-independent approach for the Query-by-Example Spoken Term Detection task of the Search on Speech ALBAYZIN 2018 evaluation |
| Maria Cabello, Doroteo Torre and Javier Tejedor | |
| AE.14 15:00 – 19:00 |
GTTS-EHU Systems for the Albayzin 2018 Search on Speech Evaluation |
| Luis Javier Rodríguez-Fuentes, Mikel Peñagarikano, Amparo Varona and Germán Bordel | |
| AE.15 15:00 – 19:00 |
Cenatav Voice Group System for Albayzin 2018 Search on Speech Evaluation |
| Ana R. Montalvo, Jose M. Ramirez, Alejandro Roble and Jose R. Calvo | |
| Speech to Text Challenge | |
| AE.16 15:00 – 19:00 |
MLLP-UPV and RWTH Aachen Spanish ASR Systems for the IberSpeech-RTVE 2018 Speech-to-Text Transcription Challenge |
| Javier Jorge, Adrià Martínez-Villaronga, Pavel Golik, Adrià Giménez, Joan Albert Silvestre-Cerdà, Patrick Doetsch, Vicent Andreu Císcar, Hermann Ney, Alfons Juan and Albert Sanchis | |
| AE.17 15:00 – 19:00 |
Limecraft Flow – workflows for story editing, subtitling and archiving |
| Victor Garcia, Nuria Sanchez, Angus Knights and Maarten Verwaest | |
| AE.18 15:00 – 19:00 |
Exploring Open-Source Deep Learning ASR for Speech-to-Text TV program transcription |
| Juan M. Perero-Codosero, Javier Antón-Martín, Daniel Tapias Merino, Eduardo López-Gonzalo and Luis A. Hernández-Gómez | |
| AE.19 15:00 – 19:00 |
The Vicomtech-PRHLT Speech Transcription Systems for the IberSPEECH-RTVE 2018 Speech to Text Transcription Challenge |
| Haritz Arzelus, Aitor Alvarez, Conrad Bernath, Eneritz García, Emilio Granell and Carlos David Martinez Hinarejos | |
| AE.20 15:00 – 19:00 |
Intelligent Voice ASR system for Iberspeech 2018 Speech to Text Transcription Challenge |
| Nazim Dugan, Cornelius Glackin, Gérard Chollet and Nigel Cannings | |
| AE.21 15:00 – 19:00 |
The GTM-UVIGO System for Albayzin 2018 Speech-to-Text Evaluation |
| Laura Docio-Fernandez and Carmen Garcia-Mateo | |
| AE.22 15:00 – 19:00 |
University of the Basque Country (GTTS@EHU) System for IberSPEECH-RTVE 2018 Speech to Text Transcription Challenge |
| Mikel Penagarikano, Amparo Varona, Luis J. Rodriguez-Fuentes and German Bordel | |
Friday, November 23 |
|
| Oral 5: Text & NLP Applications Friday, 23 November 2018, 09:00 – 10:40 Chair: José F. Quesada |
|
| O5.1 09:00 – 09:20 |
Topic coherence analysis for the classification of Alzheimer’s disease |
| Anna Pompili, Alberto Abad, David Martins de Matos and Isabel Pavão Martins | |
| O5.2 09:20 – 09:40 |
Building a global dictionary for semantic technologies |
| Iklódi Eszter, Gábor Recski, Gábor Borbély and Maria Jose Castro-Bleda | |
| O5.3 09:40 – 10:00 |
TransDic, a public domain tool for the generation of phonetic dictionaries in standard and dialectal Spanish and Catalan |
| Juan-María Garrido, Marta Codina and Kimber Fodge | |
| O5.4 10:00 – 10:20 |
Wide Residual Networks 1D for Automatic Text Punctuation |
| Jorge Llombart, Antonio Miguel, Alfonso Ortega and Eduardo Lleida | |
| O5.5 10:20 – 10:40 |
End-to-End Multi-Level Dialog Act Recognition |
| Eugénio Ribeiro, Ricardo Ribeiro and David Martins de Matos | |
| Keynote 3 Friday, 23 November 2018, 11:00 – 12:00 Chair: Carlos Segura |
|
| KN3 11:00 – 12:00 |
Automatic Question Answering: Problem Solved? |
| Lluís Màrquez | |
| Round Table Friday, 23 November 2018, 12:00 – 13:00 Chair: Marta R. Costa-Jussà |
|
| RT 12:00 – 13:00 |
Panel discussion on Speech technologies: Industry and Academy |
| Tanja Schultz, Rob Clark and David Val La Torre | |