Computational sociophonetics using automatic speech recognition

Coto-Solano, Rolando

doi:10.1111/lnc3.12474

Cited by 7 publications

(3 citation statements)

References 118 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The arduous nature of human transcription, however, creates a bottleneck. Fortunately, novel technologies allow for automatic transcription of spoken language using artificial intelligence (Coto‐Solano, 2022; Liao et al., 2023). Currently, these approaches have limitations, and they may struggle with noisy settings involving multiple speakers (Southwell et al., 2022).…”

Section: Discussionmentioning

confidence: 99%

The impact of alcohol on affiliative verbal behavior: A systematic review and meta‐analysis

Goodwin,

Sayette

2024

Alcohol, Clinical and Experimental Research

View full text Add to dashboard Cite

BackgroundLanguage is a fundamental aspect of human social behavior that is linked to many rewarding social experiences, such as social bonding. Potential effects of alcohol on affiliative language may therefore be an essential feature of alcohol reward and may elucidate pathways through which alcohol is linked to social facilitation. Examinations of alcohol's impact on language content, however, are sparse. Accordingly, this investigation represents the first systematic review and meta‐analysis of alcohol's effects on affiliative language. We test the hypothesis that alcohol increases affiliative verbal approach behaviors and discuss future research directions.MethodsPsycInfo and Web of Science were systematically searched in March 2023 according to our preregistered plan. Eligible studies included social alcohol administration experiments in which affiliative verbal language was assessed. We present a random‐effects meta‐analysis that examines the effect of alcohol compared to control on measures of affiliative verbal behavior.ResultsOur search identified 16 distinct investigations (comprising 961 participants) that examined the effect of alcohol on affiliative verbal behavior. Studies varied greatly in methods and measures. Meta‐analytic results demonstrated that alcohol is modestly associated with increases in affiliative verbal behavior (Hedges' g = 0.164, 95% CI [0.027, 0.301], p = 0.019). Study quality was rated using an adapted version of the Quality Assessment Tool for Quantitative Studies and did not significantly moderate alcohol's effects.ConclusionsThis study provides preliminary evidence that alcohol can increase affiliative verbal behaviors. This effect may be an important feature of alcohol reward. Given heterogeneity in study features, low study quality ratings, and limited reporting of effect size data, results simultaneously highlight the promise of this research area and the need for more work. Advances in language processing methodologies that could allow future work to systematically expand upon this finding are discussed.

show abstract

Section: Discussionmentioning

confidence: 99%

The impact of alcohol on affiliative verbal behavior: A systematic review and meta‐analysis

Goodwin,

Sayette

2024

Alcohol, Clinical and Experimental Research

View full text Add to dashboard Cite

show abstract

“…Recent studies explored fine-tuning of pretrained self-supervised models for ASR using speech from low-resource languages (e.g., Coto-Solano et al 2022;Guillaume et al 2022), and difficulties of modeling resource-scarce languages and dialects were acknowledged in previous work (Aksënova et al, 2022). It remains an open question to what extent model performance is dependent on the amount of fine-tuning data and the type of language, when the total amount of available data for a language is limited.…”

Section: Introductionmentioning

confidence: 99%

Making More of Little Data: Improving Low-Resource Automatic Speech Recognition Using Data Augmentation

Bartelds¹,

San²,

McDonnell³

et al. 2023

Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

View full text Add to dashboard Cite

The performance of automatic speech recognition (ASR) systems has advanced substantially in recent years, particularly for languages for which a large amount of transcribed speech is available. Unfortunately, for low-resource languages, such as minority languages, regional languages or dialects, ASR performance generally remains much lower. In this study, we investigate whether data augmentation techniques could help improve low-resource ASR performance, focusing on four typologically diverse minority languages or language variants (West Germanic: Gronings, West-Frisian; Malayo-Polynesian: Besemah, Nasal). For all four languages, we examine the use of selftraining, where an ASR system trained with the available human-transcribed data is used to generate transcriptions, which are then combined with the original data to train a new ASR system. For Gronings, for which there was a preexisting text-to-speech (TTS) system available, we also examined the use of TTS to generate ASR training data from text-only sources. We find that using a self-training approach consistently yields improved performance (a relative WER reduction up to 20.5% compared to using an ASR system trained on 24 minutes of manually transcribed speech). The performance gain from TTS augmentation for Gronings was even stronger (up to 25.5% relative reduction in WER compared to a system based on 24 minutes of manually transcribed speech). In sum, our results show the benefit of using selftraining or (if possible) TTS-generated data as an efficient solution to overcome the limitations of data availability for resource-scarce languages in order to improve ASR performance.

show abstract

“…Underlined text is in a language other than standard Indonesian or English Claims of state-of-the-art performance from finetuning a pretrained ASR model with as little as 10 minutes of labelled data (Baevski et al, 2020) often depend on large-vocabulary language models (San et al, 2023). For contexts where matching language models are not readily available, more realistic results are to be expected, such as in Coto-Solano et al (2022) where median word error rate (WER) ranged from 18-66% for Cook Islands Maori. Even with language models, WERs remained high for low-resource languages: 32.91% for read speech in Bemba language in Sikasote and Anastasopoulos (2022) and 48% for Kurmanji Kurdish in Gupta and Boulianne (2022).…”

Section: Introductionmentioning

confidence: 99%

Automated speech recognition of Indonesian-English language lessons on YouTube using transfer learning

Maxwell-Smith,

Foley

2023

Proceedings of the Second Workshop on NLP Applications to Field Linguistics

View full text Add to dashboard Cite

Experiments to fine-tune large multilingual models with limited data from a specific domain or setting has potential to improve automatic speech recognition (ASR) outcomes. This paper reports on the use of the Elpis ASR pipeline to fine-tune two pre-trained base models, Wav2Vec2-XLSR-53 and Wav2Vec2-Large-XLSR-Indonesian, with various mixes of data from 3 YouTube channels teaching Indonesian with English as the language of instruction. We discuss our results inferring new lesson audio (22-46% word error rate) in the context of speeding data collection in diverse and specialised settings. This study is an example of how ASR can be used to accelerate natural language research, expanding ethically sourced data in low-resource settings.

show abstract

Computational sociophonetics using automatic speech recognition

Cited by 7 publications

References 118 publications

The impact of alcohol on affiliative verbal behavior: A systematic review and meta‐analysis

The impact of alcohol on affiliative verbal behavior: A systematic review and meta‐analysis

Making More of Little Data: Improving Low-Resource Automatic Speech Recognition Using Data Augmentation

Automated speech recognition of Indonesian-English language lessons on YouTube using transfer learning

Contact Info

Product

Resources

About