Day 1: Aug 29, 2018 (WEDNESDAY)
Two Parallel Tutorials: ASR -Kaldi (Sanjeev Khudanpur) and NMT (Kevin Duh)
08:30	09:30		Registration of Participants
09:30	11:00		Tutorial Part-I
11:00	11:30		Tea/Coffee Break
11:30	13:30		Tutorial Part-II
13:30	14:30		Lunch Break
14:30	16:00		Tutorial Part-III
16:00	16:30		Tea/Coffee Break
16:30	18:00		Tutorial Part-IV
18:00	19:30		Free Time
19:30	-		Welcome Reception at Hotel Red Fox, Gurugram
Day 2: Aug 30, 2018 (THURSDAY)
08:30	09:30		Registration of Participants
09:30	10:30		Inaugural Session
10:30	11:15		Keynote Speaker - I Pushpak Bhattacharya - IIT (Bombay, Patna)
11:15	11:45		Tea/Coffee Break
11:45	13:15		Oral session-I: Zero & Low Resource Languages 6 Papers (15min each; 12 min presentation + 3 min Q&A) 1 Optimizing DPGMM Clustering InZero Resource Setting Based on Functional Load Bin Wu, Sakriani Sakti, Jinsong Zhang and Satoshi Nakamura 2 Low-Resource Tibetan Dialect Acoustic Modeling Based on Transfer Learning Jinghao Yan, ZhiqiangLv, Shen Huang and Hongzhi Yu 3 Interspeech2018 Low Resource Automatic Speech Recognition Challenge for Indian Languages Brij Mohan Lal Srivastava, Sunayana Sitaram, Rupesh Kumar Mehta, Krishna Doss Mohan, Pallavi Matani, Sandeepkumar Satpal, Kalika Bali, Radhakrishnan Srikanth and Niranjan Nayak 4 Advances InLow Resource ASR: A Deep Learning Perspective Hardik B. Sailor, Ankur T. Patil and Hemant A. Patil 5 ASR-Free CNN-DTW Keyword Spotting Using Multilingual Bottleneck Features for Almost Zero-Resource Languages Raghav Menon, Herman Kamper, Emre Yilmaz, John Quinn and Thomas Niesler 6 Signal Processing Cues to Improve Automatic Speech Recognition for Low Resource Indian Languages Arun Baby, Karthik Pandia D S and Hema A Murthy
13:15	14:00		Lunch Break & SLTU Board Meeting
14:00	15:30		Oral Session -II: Data Collection, Crowd Sourcing 6 Papers (15min each; 12 min presentation + 3 min Q&A) 1 Diarization In Maximally Ecological Recordings: Data From Tsimane Children Julien Karadayi, Camila Scaff, Jonathan Stieglitz and Alejandrina Cristia 2 A Small Griko-Italian Speech Translation Corpus Marcely Zanon Boito, Antonis Anastasopoulos, Marika Lekakou, Aline Villavicencio and Laurent Besacier 3 Corpus Construction and Semantic Analysis of Indonesian Image Description Khumaisa Nur'aini, Johanes Effendi, Sakriani Sakti, Mirna Adriani and Satoshi Nakamura 4 Designing AnIVR Based Framework for Telephony Speech Data Collection and Transcription In Under-Resourced Languages Joyanta Basu, Soma Khan, Milton Samirakshma Bepari, Rajib Roy, Madhab Pal, Sushmita Nandi, Karunesh Kumar Arora, Sunita Arora, Shweta Bansal, Shyam Sunder Agrawal 5 Crowd-Sourced Speech Corpora for Javanese, Sundanese, Sinhala, Nepali, and Bangladeshi Bengali Oddur Kjartansson, Supheakmungkol Sarin, Knot Pipatsrisawat, Martin Jansche and Linne Ha 6 IIITH-ILSC Speech Database for Indain Language Identification Ravi Kumar Vuddagiri, Krishna Gurugubelli, Priyam Jain, Hari Krishna Vydana and Anil Kumar Vuppala
15:30	16:50		Poster Session & Tea Time 1 Mining Training Data for Language Modeling Across the World's Languages Manasa Prasad, Theresa Breiner and Daan Van Esch 2 A Step-By-Step Process for Building TTS Voices Using Open Source Data and Frameworks for Bangla, Javanese, Khmer, Nepali, Sinhala, and Sundanese Keshan Sodimana, Pasindu De Silva, Supheakmungkol Sarin, Oddur Kjartansson, Martin Jansche, Knot Pipatsrisawat and Linne Ha 3 Prosodic Analysis of Non-Native South Indian English Speech Radha Krishna Guntur, R Krishnan and V.K. Mittal 4 Implementation of Concatenation Technique for Low Resource Text-To-Speech System-Based on Marathi Talking Calculator Monica Mundada, Sangramsing Kayte and Pradip Das 5 A Unified Phonological Representation of South Asian Languages for Multilingual Text-To-Speech Isin Demirsahin, Martin Jansche and Alexander Gutkin 6 Acoustic Characretistics of Vowel InPunjabi Swaran Lata, Prashant Verma and Simerjeet Kaur 7 A Comparative Study of SMT and NMT: Case Study of English-Nepali Language Pair Praveen Acharya and Bal Krishna Bal 8 Post-Processing Using Speech Enhancement Techniques for Unit Selection and Hidden Markov Model-Based Low Resource Language Marathi Text-To-Speech System Sangramsing Kayte and Monica Mundada 9 Relative Phase Shift Features for Replay Spoof Detection System Srinivas Kantheti and Hemant Patil 10 Empirical Study of Speech Synthesis Markup Language and Its Implementation for Punjabi Language Atul Kumar and Shyam Agrawal 11 Development of IIITH Hindi-English Code-Mixed Speech Database Banothu Rambabu and Suryakanth V Gangashetty 12 Sinhala G2P Conversion for Speech Processing Thilini Nadungodage, Chamila Liyanage, Amathri Prerera, Randil Pushpananda and Ruvan Weerasinghe
16:50	18:05		Oral session - III: Code Switching & Speech Detection 5 Papers (15min each; 12 min presentation + 3 min Q&A) 1 Automatic Detection of Palatalized Consonants In Kashmiri Ramakrishna Thirumuru, Krishna Gurugubelli and Anil Kumar Vuppala 2 Improving ASR for Code-Switched Speech In Under-Resourced Languages Using Out-Of-Domain Data Astik Biswas, Ewald Van Der Westhuizen, Thomas Niesler and FebeDe Wet 3 Code-Switching Detection WithData-Augmented Acoustic and Language Models Emre Yilmaz, Henk Van Den Heuvel and David A. Van Leeuwen 4 SVM-Based Language Diarization for Code-Switched Bilingual Indian Speech Using Bottleneck Features Spoorthy V, Veena Thenkanidiyoor and Dileep A.D 5 Dialect Identification Using Tonal and Spectral Features In Two Dialects of Ao Moakala Tzudir, Priyankoo Sarmah and S R Mahadeva Prasanna
18:05	19:30		Free Time
19:30	-		Gala Dinner (Banquet Hall)
Day 3: Aug 31, 2018 (FRIDAY)
09:00	10:00		Oral session-IV: Speech Synthesis 4 Papers (15 min each; 12 min presentation + 3 min Q&A) 1 DNN-Based Myanmar Speech Synthesis Aye Mya Hlaing, Win Pa Pa and Ye Kyaw Thu 2 Text Normalization for Bangla, Khmer, Nepali, Javanese, Sinhala and Sundanese Text-To-Speech Systems Keshan Sodimana, Pasindu De Silva, Richard Sproat, Theeraphol Wattanavekin, Chenfang Li, Alexander Gutkin, Supheakmungkol Sarin, and Knot Pipatsrisawat 3 Building A Natural Sounding Text-To-Speech System for the Nepali Language - Research and Development Challenges and Solutions Roop Shree Ratna Bajracharya, Santosh Regmi, Bal Krishna Bal and Balaram Prasain 4 A Human Quality Text to Speech System for Sinhala Lakshika Nanayakkara, Chamila Liyanage, Pubudu Tharaka Viswakula, Thilini Nagungodage, Randil Pushpananda and Ruvan Weerasinghe
10:00	10:45		Keynote Speaker - II Emmanuel Dupoux - EHESS ,Paris
10:45	11:15		Tea Break
11:15	13:15		Panel Discussion
13:15	14:00		Lunch
14:00	15:30		Oral Session V: Automatic Speech Recognition & Language Identification 6 Papers (15 min each; 12 min presentation + 3 min Q&A) 1 Neural Networks-Based Automatic Speech Recognition for Agricultural Commodity InGujarati Language Hardik B. Sailor and Hemant A. Patil 2 Building An ASR System for Mboshi Using A Cross-Language Definition of Acoustic Units Approach Odette Scharenborg, Patrick Ebel, Francesco Ciannella, Mark Hasegawa-Johnson and NajimDehak 3 Incorporating Speaker Normalizing Capabilities to An End-To-End Speech Recognition System Hari Krishna Vydana, Sivanand Achanta and Anil Kumar Vuppala 4 Language Identification of Assamese, Bengali and English Speech Joyshree Chakraborty, Shikhamoni Nath, S R Nirmala and Samudravijaya K 5 Automatic Speech Recognition for Humanitarian Applications In Somali Raghav Menon, Astik Biswas, Armin Saeb, John Quinn and Thomas Niesler 6 Improving ASR Output for Endangered Language Documentation Robbie Jimerson, Kruthika Simha, Raymond Ptucha and Emily Prud'hommeaux
15:30	16:30		Poster Session / Tea Break 1 Assessing Performance of Bengali Speech Recognizers under Real World Conditions using GMM-HMM and DNN Based Methods Soma Khan, Madhab Pal, Joyanta Basu, Milton SamirakshmaBepari and Rajib Roy 2 Evaluating Code-Switched Malay-English Speech using Time Delay Neural Networks Anand Singh and Tien-Ping Tan 3 Hindi Speech Vowel Recognition using Hidden Markov Model Shobha Bhatt, Dr. Amita Dev and Dr. Anurag Jain 4 Building Speech Recognition Systems for Language Documentation: the Coedl Endangered Language Pipeline and Inference System (ELPIS) Ben Foley, Josh Arnold, Rolando Coto-Solano, Gautier Durantin, T. Mark Ellison, DaanVan Esch, Scott Heath, František Kratochvíl, Zara Maxwell-Smith, David Nash, Ola Olsson, Mark Richards, Nay San, Hywel Stoakes, Nick Thieberger and Janet Wiles 5 Improved Language Identification using Stacked SDC Features and Residual Neural Network Ravi Kumar Vuddagiri, Hari Krishna Vydana and Anil Kumar Vuppala 6 Investigating the Use of Mixed-Units based Modelling for Improving Uyghur Speech Recognition Pengfei Hu, Shen Huang and Zhiqiang Lv 7 Development of Assamese Continuous Speech Recognition System Barsha Deka, Nirmala S.R. and Samudravijaya K. 8 Segmental and Supra Segmental Feature Based Speech Recognition System for Under Resourced Languages Tanmay Bhowmik and Shyamal Kumar Das Mandal 9 Application of Egyptian Vulture Optimization In Speech Emotion Recognition Shreya Sahu, Arpan Jain, Ritu Tiwari and Anupam Shukla 10 Marathi Speech Recognition Supriya Paulose, Shikhamoni Nath and Samudravijaya K 11 Building AnAutomatic Speech Recognition System In Sora Language Using Data Collected for Acoustic Phonetic Studies Kishalay Chakraborty, Luke Horo and PriyankooSarmah 12 Jamlit: A Corpus of Jamaican Standard English for Automatic Speech Recognition of Children’s Speech Stefan Watson and Andre Coy
16:30	18:00		Oral Session VI: Feature Analysis of Speech Signal 6 Papers (15 min each; 12 min presentation + 3 min Q&A) 1 Predicting the Features of World Atlas of Language Structures FromSpeech Alexander Gutkin, Tatiana Merkulova and Martin Jansche 2 Visually Grounded Cross-Lingual Keyword Spotting In Speech Herman Kamper and Michael Roth 3 The Intonation System of Tajik: Is It Identical to Persian? Marina Agafonova 4 Brahmic Schwa-Deletion With Neural Classifiers: Experiments with Bengali CibuJohny and Martin Jansche 5 Preliminary Acoustic Analysis of Manipuri Vowels TulikaBasu, Arup Saha and Potsangbam Madhubala 6 Analysis and Comparison of Features for Text-Independent Bengali Speaker Recognition Shubhadeep Das and Pradip K. Das
18:00	18:30		Valedictory Function

 

Download Technical Program HERE !

General Instructions for ORAL Presentation:

• Each speaker will have 12 minutes for presentation followed by 3 minutes for summary and question answer session.
• Speakers will be notified at the 10^th minute of the presentation to start concluding their presentation.
• Speakers are required to use the computers provided by the conference organizers for their oral presentations. Personal laptops should not be used.
• Please load your PPT in advance before the start of your session.
• It is recommended that multimedia, sound, or video files are embedded in the presentation.
• The selection of font size and type should be wisely done so that the content are easily readable and understandable.

General Guidelines for Poster Presentations:

The poster must be no less than A1 and no larger than A0 size (A0 size is 33.1 x 46.8 inches i.e. width x height). Orientation of your poster must be in POTRAIT style.

Presenters are advised to mount their posters 20 minutes before the start of the session, and remove it after the session ends. Conference organizers will not be responsible for posters left behind after the session ends.

At least one of the authors must be present at the poster during the designated session.

The poster should be a visual presentation of your submitted paper and should meet the following criteria:

TITLE

The title should be the same as in the submitted paper. The title of your poster should appear at the top in CAPITAL letters.Characters should be a minimum of 48 point font size. Put the author(s)' name(s) and affiliation(s) below the title.

LETTERING

The poster should be easily readable at a distance of two metres. Use UPPER and lower case for general content as the use of all-capital text is difficult to read. Avoid using a mixture of type/font styles.

CONTENT

The text should be concise and easy to read. 24 to 32 font size single spaced is recommended.

The message that your poster contains should be clear and understandable with minimum requirement of oral explanation. If relevant, methods should be presented simply and concisely.

Results should be presented graphically if possible. Avoid large tables of data. Results should be in line with those originally submitted in your abstract.

Use pictures, symbols and colour. Figure legends are essential and should be short but informative. If using graphs, they should have a short heading.

For visual effect, we recommend that graphs be no smaller than 12cm x 18cm. Photographs should be no smaller than 12cm x 18cm.

Prepare a short presentation of about 5 or 10 minutes that you can periodically give to those assembled around your poster throughout the 1 hour poster session.

 

---

Internet Explorer is not supported

© 2018 MICA International Research Institute