TTS, Language Technology, Kvistur, and Samrómur papers published but no conferences to attend

Sjá íslenska þýðingu neðar

This is a positive but somewhat sad week for LVL. Many LVL members were going to go to Marseille, France this week to attend Language Resources & Evaluation Conference (LREC) 2020 and the joint Spoken Language Technologies for Under-Resourced Languages and Collaboration and Computing for Under-Resourced Languages (SLTU-CCURL) 2020 Workshop. Once there they were going to present their many papers, providing an in-depth look into our TTS, data collection, compound splitting, and general language technology research in recent months. However, due to COVID-19 these conferences were both cancelled. Luckily the organizers have still decided to publish the proceedings this month. The joint SLTU proceedings were published May 8th on the SLTU-CCURL 2020 website at Workshop Proceedings (our paper is on page 316). Head over to the SLTU 2020 website if you want to read more SLTU-CCURL papers. We’re still waiting for the LREC proceedings to be published. But our papers can now be found as pdfs below and on our publications page.

Our TTS paper was accepted at SLTU-CCURL 2020:



Title: Manual Speech Synthesis Data Acquisition – From Script Design to Recording Speech
Authors: Atli Þor Sigurgeirsson, Gunnar Thor Örnólfsson, Jon Gudnason
Summary: In this paper we present the work of collecting a large amount of high quality speech synthesis data for Icelandic. A script design strategy is proposed and three scripts have been generated to maximize diphone coverage, varying in length. The largest reading script contains 14,400 prompts and includes 81% of all Icelandic diphones at least twenty times. As of writing, 58.7 hours of high quality speech data has been collected.
PDF

Our Samrómur, Kvistur, and Language Technology programme papers were accepted at LREC 2020:

The cover of the proposal sent to the Icelandic parliament

Title: Language Technology Programme for Icelandic 2019-2023
Authors: Anna Nikulásdóttir, Jón Guðnason, Anton Karl Ingason, Hrafn Loftsson, Eiríkur Rögnvaldsson, Einar Freyr Sigurðsson and Steinþór Steingrímsson
Summary: In this paper, we describe a national language technology programme for Icelandic. The programme aims at making Icelandic usable in communication and interactions in the digital world, by developing accessible, opensource language resources and software. The research and development work within the programme is carried out by SÍM, a consortium of universities, institutions, and private companies, with a strong emphasis on cooperation between academia and industries. Five core projects will be the main content of the programme: language resources, speech recognition, speech synthesis, machine translation, and
spell and grammar checking.
PDF

A representation of the model with one BiLSTM layer, showing where the compound word raforku ‘electric energy’ is split in two.

Title: Kvistur: a BiLSTM Compound Splitter for Icelandic
Authors: Jón Daðason, David Mollberg and Hrafn Loftsson
Summary: In this paper, we present a character-based BiLSTM model for splitting Icelandic compound words, and show how quantity of training data affects model performance. Compounding is highly productive in Icelandic, and new compounds are constantly being created. This results in a large number of out-of-vocabulary (OOV) words, negatively impacting the performance of many NLP tools. Our model is trained on a dataset of 2.9 million unique word forms and their constituent structures from the Database of Icelandic Morphology. The model learns to split compound words into two and can be used to derive a word form’s constituent structure. Knowing the constituent structure of a word form makes it possible to generate the optimal split for a given task. The model outperforms other previously published methods when evaluated on a corpus of manually split word forms. This method has been integrated into Kvistur, an Icelandic compound word analyzer.
PDF

The cumulative count of votes and utterances. Each utterance can have more than one vote as it needs two positive votes to be considered valid and two negative votes to be considered invalid.

Title: Samrómur: Crowd-sourcing Data Collection for Icelandic Speech Recognition
Authors: David Erik Mollberg, Ólafur Helgi Jónsson, Sunneva Þorsteinsdóttir, Steinþór Steingrímsson, Eydís Huld Magnúsdóttir and Jon Gudnason
Summary: This contribution describes an ongoing speech data collection, using Samrómur which is built upon Mozilla’s Common Voice. The goal is to build a large-scale speech corpus for Automatic Speech Recognition (ASR) for Icelandic. Upon completion, Samrómur will be the largest open speech corpus for Icelandic. The paper discusses the methods used for crowd-sourcing and illustrate the importance of marketing and good media coverage for a crowd-sourced dataset. Preliminary results exceed our
expectations. The paper also reports on the process of validating recordings.
PDF

Our SÍM colleagues also had two papers at LREC 2020: “Facilitating Corpus Usage: Making Icelandic Corpora More Accessible for Researchers and Language Users” and “Parallel Universal Dependencies”. Congratulations!

While it is sad that our LVL members cannot meet with fellow researchers and visit the great city of Marseille, they still look forward to connecting with researchers online through your comments on their papers and links to your related papers.

Þessa vikuna hefði átt að halda Language Resources & Evaluation (LREC) ráðstefnuna í Frakklandi, sem og Spoken Language Technologies for Under-resourced Languages vinnustofuna en báðum þessum viðburðum var aflýst vegna COVID-19.  Margir starfsmenn LVL ætluðu sér að sækja þessa viðburði og kynna þar 4 greinar og veita innsýn í þær máltæknirannsóknir sem hafa farið fram hérna síðustu mánuði. Hérna má lesa nánar um þetta og nálgast greinarnar. (Athugið að greinarnar eru aðeins aðgengilegar á ensku).

Role models?

Sjá íslenska þýðingu neðar.

Will the Icelandic Language Technology program and our efforts become role models for other similar languages? Read about RU’s take on the work we are participating in and see us in action (picture taken pre-Covid).

Gæti íslenska máltækniáætlunin orðið leiðarljós annarra lítilla málsvæða? Hérna er umfjöllun HR um starfsemi okkar (Myndir teknar fyrir Covid).

A large milestone in Named Entity Recognition for Icelandic!

Progress in NER celebrated with a suitable cake.

Last Tuesday Svanhvít and Ásmundur completed the first stage in Named Entity Recognition project for Icelandic. They finished the daunting task of labeling all named entities in a text corpus of 1 million tokens (MIM-GOLD), into the following categories: Person, Location, Organization, Micellaneous, Money, Percent, Time, and Date.

To assist with the task, they first preprocessed the corpus using regular expressions to catch some cases and then verified and completed the labeling using the brat rapid annotation tool. Their next task will be to create a few baseline NER tagging systems using the labelled dataset.

The dataset will be publicly available this spring.

First milestone in the Language Technology for Icelandic project

The LVL team celebrating the first milestone in the Language Technology for Icelandic project. Ólafur Helgi Jónsson, Sunneva Þorsteinsdóttir and Steinþór Steingrímsson are missing from the picture.

Last week we celebrated achieving the first milestone in the Language Technology for Icelandic project with a cake!

After a lot of hard work the past few months we achieved the first milestone in Automatic Speech Recognition (ASR), Text-to-Speech (TTS) and Machine Translation (MT).

In ASR, the focus has mostly been on data creating and gathering. 55,000 utterances have been collected (donated by adults) via the crowd-sourcing platform samromur.is (based on Common Voice) with plans to reach 100.000 utterances for the next milestone. The process is being extended to include younger voices in collaboration with schools and authorities. Today we started working with Öldutúnsskóli in Hafnarfjörður. The goal is to reach 80.000 young voice utterances for the next mileston. Additionally, data has been gathered from RÚV (audio, video and subtitles) and CreditInfo (transcriptions). Along with data gathering, the team is also developing tools to post-process Icelandic ASR text for better readability.

In TTS, we successfully created a voice recording client (LOBE) and three reading scripts in order to collect high quality speech and corresponding text data. The reading scripts were created from Risamálheild and seek to maximize diphone coverage. So far 20 hours have been collected from two speakers, male and female. The aim is to finish collecting 20 hours from each speaker early this year. From the collected data two TTS prototypes have been created in Ossian, which extends the Merlin back-end. The current prototypes are quite naive but we have integrated a grapheme-to-phoneme model for the Icelandic language into the prototypes.

In MT, we successfully created a phrase-based statistical machine translation system using the open source tool Moses. Our collaborators at Miðeind created neural machine translation systems based on BiLSTMs and Transformers. The models were trained on the newly available English-Icelandic parallel corpus, ParIce. The systems were then evaluated w.r.t. training time, throughput and BLEU score. The code and 
systems are freely available but are still under development for milestone two. In milestone two we will continue to develop the systems further and adjust them to specific needs of the Icelandic language.

Donate your voice to bring Icelandic and technology together!

Hello everyone!

We are collecting audio clips to create a new, more robust Icelandic dataset. We plan to use them for automatic speech recognition and text-to-speech applications. This could lead to many applications that you can use in your everyday life, like an Icelandic voice assistant, screenreaders, and searchable audio and video content. The dataset will soon be available directly on the Samromur website for users and developers alike to download and use to creating exciting new technology. But to do this, we need your voices, Icelandic speakers.

You can get started by going to Samromur.is  and choosing Tala. You only need to donate 5 recordings per session, but more is always welcome. If you want to do more, you can also evaluate clips made by other users with Hlusta.

Samromur

 

We are also organizing data gathering competitions within companies. So, please contact us if you and your company would be interested in holding a competition.

This is a joint effort with Deloitte and Almannaromur. If you want to learn more about this project, visit the Um Verkefnið tab on the Samromur site.

Conference – Er íslenskan góður „bisness“?

Tomorrow, 16th of October 2019, there will be a conference on Icelandic language technology. The conference will take place at Veröld – hús Vigdísar and starts at 8:00.

A number of people affiliated (past and present) with the LVL will be giving talks there such as:

  • David Erik Mollberg, Ólafur Helgi Jónsson, Viktor Sveinsson Sunneva Þorsteinssdóttir – students at HÍ and RU will launch an open speech data collection initivate for Icelandic.
  • Anna Björk Nikulásdóttir – project manager at SÍM (Samstarf um íslenska máltækni – Collaboration on Icelandic Language Technology) and CEO of Grammatek will talk about tools in language technology.
  • Hrafn Loftsson – docent at the School of Computer Science in RU will talk about automatic text summarization for Icelandic.

The conference focuses on the importance of Icelandic language technology for academy and industry and is open for anyone to attend.

For more details on the conference and speaker list, see the facebook event (Icelandic)