The ABAIR Initiative: Bringing Spoken Irish into the Digital Space

Chasaide, Ailbhe Nı́; Chiaráin, Neasa Ní; Wendler, Christoph; Berthelsen, Harald; Murphy, Andy; Gobl, Christer

doi:10.21437/interspeech.2017-1407

Cited by 10 publications

(14 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a parallel research strand, we are developing text-tospeech synthesis for the dialects of Irish (see [23,24]), and plan to exploit them in educational games [25] and dialogue systems [26]. Our basic research on voice modelling thus goes hand in hand with our goal to provide more adequate descriptions of voice modulation in prosody, which is essential for this kind of application where speaker affect is important.…”

Section: Introductionmentioning

confidence: 99%

On the Relationship between Glottal Pulse Shape and Its Spectrum: Correlations of Open Quotient, Pulse Skew and Peak Flow with Source Harmonic Amplitudes

Gobl¹,

Murphy²,

Yanushevskaya³

et al. 2018

Interspeech 2018

Self Cite

View full text Add to dashboard Cite

This paper explores the relationship between the glottal pulse amplitude (Up) and the amplitude of the first harmonic (H1), as well as the combined effects of Up, the open quotient (Oq) and degree of pulse asymmetry/skew (Rk) on the low end of the source spectrum. This serves to elucidate their relationship to the H1-H2 estimate, widely used to make inferences on changes in Oq and voice quality. It has been suggested that H1 is mainly determined by Up and that the pulse shape has a relatively small impact. To investigate this, a series of glottal pulses were generated using the LF model, where Up was kept constant, while Oq and Rk were systematically varied. The resulting harmonic amplitudes of these pulses show that Up is not the sole determinant of H1. Rather, H1 is highly dependent on Oq and to a certain degree also on Rk. Although the effects of these parameters on the lowest harmonics is rather complex, we find that the H1-H2 measure is broadly correlated with Oq. However, there is also a strong effect of differences in glottal skew, particularly at high Oq values, which could invalidate inferences on Oq and voice quality from estimates of H1-H2.

show abstract

Section: Introductionmentioning

confidence: 99%

On the Relationship between Glottal Pulse Shape and Its Spectrum: Correlations of Open Quotient, Pulse Skew and Peak Flow with Source Harmonic Amplitudes

Gobl¹,

Murphy²,

Yanushevskaya³

et al. 2018

Interspeech 2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…An Scéalaí is configured with an integrated TTS capacity of the ABAIR system [6]. This TTS system allows a choice of the three main dialects, including both male and female 'speakers'.…”

Section: Designmentioning

confidence: 99%

An Scéalaí: autonomous learners harnessing speech and language technologies

Chiaráin¹,

Chasaide²

2019

8th ISCA Workshop on Speech and Language Technology in Education (SLaTE 2019)

Self Cite

View full text Add to dashboard Cite

This paper presents an autonomous language learning platform which has speech and language technology at its core. An Scéalaí ('the Storyteller') is a web-based interactive iCALL system that allows learners to compose their own text and correct it by listening to the text spoken with synthetic voices (aural proofing) and by responding to NLP prompts that detect errors. All learner interactions are logged and monitored, allowing researchers to observe the learning processes. A pilot study by 14 learners of Irish in the US was conducted to explore the efficacy of the corrective mechanisms currently implemented in the platform. The results of the pilot study indicate that both mechanisms currently on offer were effective in the development of writing skills but work in rather different ways. Aural proofing appears to generate an immediate corrective response which indicates that it is serving both to develop awareness of specific phonological contrasts as well as basic phonic rules of the language. In the case of the NLP prompts, corrections were also made, although the data suggest that this is a slower process and that learners may, at least initially, merely be satisfying the system's prompts rather than discovering the grammatical basis of the correction. The pilot has been useful in pointing towards future directions for platform development that can take the needs of this type of adult autonomous learner into account.

show abstract

“…Work on speech technology development for Irish has been underway in the Phonetics and Speech Lab., Trinity College, Dublin for some years [20]. Synthetic voices representing the three main dialects of Irish have been developed as part of the ABAIR initiative and are freely available at www.abair.ie.…”

Section: Irish Language Learnersmentioning

confidence: 99%

CARAMILLA - Speech Mediated Language Learning Modules for Refugee and High School Learners of English and Irish

Gilmartin

Kim

Diallo

et al. 2017

7th ISCA Workshop on Speech and Language Technology in Education (SLaTE 2017)

View full text Add to dashboard Cite

In the development of Computer-Assisted Language Learning (CALL) modules there is a growing emphasis on the use of evolving technological developments which include text-to-speech technology (TTS) and automatic speech recognition (ASR). These technologies allow for greater spoken interaction between the learner and the computer, which is particularly useful when native speaker input is not readily available and to elicit learner speech in a quasi-natural environment. They also allow for greater learner autonomy, and facilitate the creation of modules based on effective learning activities at all levels to address needs for accuracy as well as fluency. The present paper reports on two modules which integrate speech technology, (1) a spoken dictogloss, or text reconstruction, module and (2) a pronunciation module. These modules have been implemented in JAVA as part of CARAMILLA, a spoken dialogue-based language learning tool, which is based on an earlier prototype, MILLA. The dictogloss module is being evaluated with two distinct learner groups -adult refugees learning English while living in the host country and learners of Irish, a minority endangered language. The pronunciation module is also being evaluated with the adult refugee group.

show abstract

The ABAIR Initiative: Bringing Spoken Irish into the Digital Space

Cited by 10 publications

References 7 publications

On the Relationship between Glottal Pulse Shape and Its Spectrum: Correlations of Open Quotient, Pulse Skew and Peak Flow with Source Harmonic Amplitudes

On the Relationship between Glottal Pulse Shape and Its Spectrum: Correlations of Open Quotient, Pulse Skew and Peak Flow with Source Harmonic Amplitudes

An Scéalaí: autonomous learners harnessing speech and language technologies

CARAMILLA - Speech Mediated Language Learning Modules for Refugee and High School Learners of English and Irish

Contact Info

Product

Resources

About