Comparison of Two Forced Alignments Systems for Aligning Bribri Speech

Coto-Solano, Rolando; Solórzano, Sofía Flores

doi:10.19153/cleiej.20.1.2

Cited by 10 publications

(8 citation statements)

References 17 publications

(24 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This paper proposes an alternative; namely, adapting the English-language FAVE-Align to the Nordic languages while using its existing hidden Markov models. Whereas using such 'untrained' models has rendered unreliable results for endangered languages typologically distant from the original language(s) used for training (DiCanio et al 2013;Coto-Solano & Solórzano 2017;Coto-Solano et al 2018;Strunk et al 2014), we show it to be robust and reliable for spontaneous and read-aloud Stockholm Swedishlikely because the variety is more typologically similar to English. In crudely and quickly adapting FAVE-Align to Stockholm Swedish, we were able to reduce total manual segmentation time to approximately 78 hours per recorded hour.…”

Section: Introductionmentioning

confidence: 62%

“…Since we had no guarantee for future alignment accuracy, we felt that the rapid adaptation of a pre-existing aligner was the more prudent investment to make, since it would eliminate steps 1 and 2 no matter what. This is also the viewpoint taken by the researchers who paved the way for this study and used untrained aligners for typologically-rare endangered languages (DiCanio et al 2013;Coto-Solano & Solórzano 2017;Coto-Solano et al 2018;Strunk et al 2014). Although the accuracy levels were poor, they nonetheless saved the authors considerable time in their alignment endeavors.…”

Section: Teasing Apart the Benefits Of Forced Alignmentmentioning

confidence: 91%

“…FAVE-Align has transparent architecture and ample documentation, which makes it particularly handy for adaptation. Although is has been adapted before DiCanio et al 2013;Coto-Solano & Solórzano 2017;Coto-Solano et al 2018), detailed instructions for doing so have never been shared, which has resulted in an unfortunate stream of duplicated and uncoordinated efforts. The first author, who has expertise in Swedish phonetics, therefore scoured the code and identified change spots that would allow the use of the English HTK models for the closest corresponding Swedish phoneme.…”

Section: Adapting Fave-align To Swedishmentioning

confidence: 99%

“…Even for Swedish, a language not typically considered lesser-studied, very few technological tools circulate for phoneticians. This paper seeks to address this gap by incorporating a simple and straight-forward Swedish-language adaptation of FAVE-Align (Rosenfelder et al 2011) that resembles approaches used in the past for endangered languages (DiCanio et al 2013;Coto-Solano & Solórzano 2017;Coto-Solano et al 2018;Strunk et al 2014). The novel contributions of this paper are that (1) this is the first published adaptation for any Nordic language, (2) this adaptation meets most of the accuracy benchmarks established by the literature, (3) a step-by-step guideline is offered in the Appendix for those who wish to duplicate the adaptation for another Nordic language.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Forced alignment for Nordic languages: Rapidly constructing a high-quality prototype

Young¹,

McGarrah²

2021

Nord J Linguist

View full text Add to dashboard Cite

We propose a rapid adaptation of FAVE-Align to the Nordic languages, and we offer our own adaptation to Swedish as a template. This study is motivated by the fact that researchers of lesser-studied languages often neither have sufficient speech material nor sufficient time to train a forced aligner. Faced with a similar problem, we made a limited number of surface changes to FAVE-Align so that it – along with its original hidden Markov models for English – could be used on Stockholm Swedish. We tested the performance of this prototype on the three main sociolects of Stockholm Swedish and found that read-aloud alignments met all of the minimal benchmarks set by the literature. Spontaneous-speech alignments met three of the four minimal benchmarks. We conclude that an adaptation such as ours would especially suit laboratory experiments in Nordic phonetics that rely on elicited speech.

show abstract

Section: Introductionmentioning

confidence: 62%

Section: Teasing Apart the Benefits Of Forced Alignmentmentioning

confidence: 91%

Section: Adapting Fave-align To Swedishmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Forced alignment for Nordic languages: Rapidly constructing a high-quality prototype

Young¹,

McGarrah²

2021

Nord J Linguist

View full text Add to dashboard Cite

show abstract

“…In 2017, we moved from Vanuatu to New Zealand. During this year, the language project initially consisted of my linguistic foundations training with Dr. Rolando Coto-Solano (2017 focusing on phonetic transcription and analysis of recordings done with my native Denggan-speaking husband and family members. During this time, I also worked with Professor Miriam Meyerhoff to prepare for my introduction of the project to the community and for conducting my first preliminary data collection for further phonetic analysis.…”

Section: Introduction To the Language Projectmentioning

confidence: 99%

A Sociolinguistic Study of Language Documentation: Denggan (Banam Bay, Malekula, Vanuatu)

Hoback

View full text Add to dashboard Cite

In the country of Vanuatu, there are estimated to be as many as 138 different languages. Of those, there are still many languages which remain undocumented. Yet, with the move to integrate the vernacular local languages into the education system, speakers of these languages are developing orthography systems as a way of maintaining the vitality of their language in oral and written forms. Often the goals of language documentation and orthography development create a partnership between outside linguists and native speakers of the language. These joint projects are consistent with the current aims of linguists working in the field of language documentation and Indigenous academic researchers, who are calling for more collaborative research projects. Such scholars suggest that research on indigenous languages need to be undertaken ‘with’ communities, rather than ‘on’ or ‘for’ communities. However, this partnership brings questions, such as, what does collaboration look like and how do the community desires get prioritised amongst the various requirements of academic research. Furthermore, what does it mean to research ‘with’ when there may be differences in the epistemological foundations underlying the design of a project.This thesis is a result of a community orthography and language documentation project in Southeast Malekula, Vanuatu. It focuses on the language, Denggan, formerly known as Banam Bay Language or Burmbar (ISO code vrt-639-3) spoken by around 900-1000 speakers. Within this project two initial orthography workshops were conducted with community members to facilitate the transition of Denggan from a completely oral tradition into a new domain of written literacy. A separate grammatical analysis was undertaken to further the language documentation record and to assist in the creation of future pedagogical language resources. The presentation of this thesis is interdisciplinary and hybrid in its structure. It consists of a discussion on collaborative research design and Pacific Indigenous epistemologies, an exploration of the sociolinguistic background of Denggan as an endangered, yet vital language, a grammar sketch of Denggan phonetics and syntax, and a reflection on collaborative projects and the responsibilities of a researcher in working with Indigenous communities within such a project. The hybrid structure of this thesis allows for a contextualised approach of situating the project’s orthography workshop discussions and the linguistic grammatical analysis of Denggan within its historical and sociolinguistic contexts. This hybrid structure also allows for reflection on Pacific Melanesian and Western academic epistemic assumptions in approaching the design of a collaborative research project. This thesis provides an example of a unique language documentation project arising out of a community’s vision and coming to fruition through community involvement. It provides the theoretical basis for creating collaborative language documentation projects grounded in Pacific Indigenous epistemologies and reflects on important questions in navigating the differences between these epistemologies and Western academic assumptions regarding research. Lastly, the thesis contributes to the documentation record of Denggan through a grammar sketch with valuable data from recorded stories and conversations.

show abstract

Improving Automatic Forced Alignment for Phoneme Segmentation in Quranic Recitation

Alqadasi,

Zeki,

Sunar

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Segmentation plays a crucial role in speech processing applications, where high accuracy is essential. The quest for improved accuracy in automatic segmentation, particularly in the context of the Arabic language, has garnered substantial attention. However, the differences between Qur'an recitation and normal Arabic speech, especially with regard to intonation rules affecting the lengthening of long vowels, pose challenges in segmentation especially for Qur'an recitation. This research endeavors to address these challenges by delving into the domain of automatic segmentation for Qur'an recitation recognition. The proposed scheme employs a hidden Markov models (HMMs) forced alignment algorithm. To enhance the precision of segmentation, several refinements have been introduced, with a primary emphasis on the phonetic model of the Qur'an and Tajweed, particularly the intricate rules governing elongation. These enhancements encompass the adaptation of an acoustic model tailored for Qur'anic recitation as preprocessing and culminate in the development of an algorithm aimed at refining forced alignment based on the phonetic nuances of the Qur'an. These enhancements are seamlessly integrated as post-processing components for the classic HMM-based forced alignment. The research utilizes a comprehensive database featuring recordings from 100 renowned Qur'an reciters, encompassing the recitation of 21 Qur'anic verses (Ayat). Additionally, 30 reciters were asked to record the same verses, incorporating various recitation speed patterns. To facilitate the evaluation process, a Random sample of the Qur'anic database was manually segmented, comprised 21 Ayats, totaling 19,800 words, with 89 unique words (14 verses x 3 recitation levels: fast, slow and normal x 6 readers). The outcomes of this study manifest notable advancements in the alignment of long vowels within Qur'an recitation, all while maintaining the precise alignment of vowels and consonants. Objective comparisons between the proposed automatic methods and manual segmentation were conducted to ascertain the superior approach. The findings affirm that the classic forced alignment method produces satisfactory outcomes when employed on verses lacking long vowels. However, its performance diminishes when confronted with verses containing long vowels. Therefore, the test samples were categorized into three groups based on the presence of long vowels, resulting in a Correct Classification Rate (CCR) that ranged from 6% to 57%, contingent on whether the verse includes long vowels or not. The average CCR across all test samples was 23%. In contrast, the proposed algorithm significantly enhances audio segmentation. It achieved CCR values ranging from 16% to 70% within the same database categories, with an average CCR of 45% across all test samples. This marks a notable advancement of 22% in segmented speech accuracy, particularly within a 30 ms tolerance, for verses containing long vowels.

show abstract

Comparison of Two Forced Alignments Systems for Aligning Bribri Speech

Cited by 10 publications

References 17 publications

Forced alignment for Nordic languages: Rapidly constructing a high-quality prototype

Forced alignment for Nordic languages: Rapidly constructing a high-quality prototype

A Sociolinguistic Study of Language Documentation: Denggan (Banam Bay, Malekula, Vanuatu)

Improving Automatic Forced Alignment for Phoneme Segmentation in Quranic Recitation

Contact Info

Product

Resources

About