Automatic Speech Recognition of Quechua Language Using HMM Toolkit

Zevallos, Rodolfo; Cordova, Johanna; Caballero, Luis Camacho

doi:10.1007/978-3-030-46140-9_6

Cited by 4 publications

(5 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…( Both corpora were preprocessed to improve the quality of the audios, eliminating excess background noise, audios with no voice, those with background music and those not spoken in Quechua, the latter feature added thanks to the first automatic speech recognition developed for Quechua [19]. Finally, audios longer than 30 seconds were divided into segments of no more than 30 seconds and transformed to mono channel, 16 kHz sampling, 16-bit precision encoding and WAV format.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Data Augmentation for Low-Resource Quechua ASR Improvement

Zevallos¹,

Bel²,

Cámbara³

et al. 2022

Interspeech 2022

View full text Add to dashboard Cite

Automatic Speech Recognition (ASR) is a key element in new services that helps users to interact with an automated system. Deep learning methods have made it possible to deploy systems with word error rates below 5% for ASR of English. However, the use of these methods is only available for languages with hundreds or thousands of hours of audio and their corresponding transcriptions. For the so-called low-resource languages to speed up the availability of resources that can improve the performance of their ASR systems, methods of creating new resources on the basis of existing ones are being investigated. In this paper we describe our data augmentation approach to improve the results of ASR models for low-resource and agglutinative languages. We carry out experiments developing an ASR for Quechua using the wav2letter++ model. We reduced WER by 8.73% through our approach to the base model. The resulting ASR model obtained 22.75% WER and was trained with 99 hours of original resources and 99 hours of synthetic data obtained with a combination of text augmentation and synthetic speech generation.

show abstract

Section: Methodsmentioning

confidence: 99%

“…This pilot system was developed using the K-Nearest Neighbor (KNN) using the Hidden Markov Model Toolkit [18]. [19] developed a new ASR model based on the monophone HMM topology, a model with five states per HMM and no jumps, that achieved a WER of 12.7%. This model was trained using the corpus of 97.5 hours of [17].…”

Section: Automatic Speech Recognitionmentioning

confidence: 99%

Data Augmentation for Low-Resource Quechua ASR Improvement

Zevallos¹,

Bel²,

Cámbara³

et al. 2022

Interspeech 2022

View full text Add to dashboard Cite

show abstract

“…But for Indigenous and other under-resourced languages, creating ASR entails first collecting a large mass of already-transcribed data -in addition to the data for the sociolinguistic experiment -so that a new ASR model can be trained. This process is still difficult and expensive, requiring (i) linguists and community experts to settle on an orthographic or phonetic representation of the language, (ii) human experts to transcribe hours of recordings (from 4 to 100), and (iii) programmers to train the system on specialised computer servers (Adams et al, 2019;Besacier et al, 2014;Coto-Solano, 2021;Foley et al, 2018;Gupta & Boulianne, 2020;Levow et al, 2021;Matsuura et al, 2020;Partanen et al, 2020;Prud'hommeaux et al, 2021;Zahrer et al, 2020;Zevallos et al, 2020).…”

Section: Automatic Speech Recognition For Sociophoneticsmentioning

confidence: 99%

Computational sociophonetics using automatic speech recognition

Coto-Solano

2022

Language and Linguist. Compass

View full text Add to dashboard Cite

Recent years have seen numerous advances in natural language processing that can help accelerate sociophonetic work. These include software to align speech recordings with their transcriptions, as well as to transcribe audio automatically. This solves a major bottleneck and will help process larger datasets and test hypotheses more efficiently. This paper will summarise recent progress, highlight relevant examples of sociophonetic research, and comment on the technical and ethical issues at the cutting edge of natural language processing.

show abstract

“…Indigenous and other minority languages usually have few transcribed audio recordings, and so adapting data-hungry ASR algorithms to assist in their documentation is an active area of research (Besacier et al, 2014;Jimerson and Prud'hommeaux, 2018;Michaud et al, 2019;Foley et al, 2018;Gupta and Boulianne, 2020b,a;Zahrer et al, 2020;Thai et al, 2019;Li et al, 2020;Zevallos et al, 2019;Matsuura et al, 2020;Levow et al, 2021). This paper will examine an element that might appear obvious at first, but one where the literature is "inconclusive" (Adams, 2018), and which can have major consequences in performance: How should tones be transcribed when dealing with extremely low-resource languages?…”

Section: Introductionmentioning

confidence: 99%

Explicit Tone Transcription Improves ASR Performance in Extremely Low-Resource Languages: A Case Study in Bribri

Coto-Solano¹

2021

Proceedings of the First Workshop on Natural Language Processing for Indigenous Languages of the Americas

View full text Add to dashboard Cite

Linguistic tone is transcribed for input into ASR systems in numerous ways. This paper shows a systematic test of several transcription styles, using as an example the Chibchan language Bribri, an extremely low-resource language from Costa Rica. The most successful models separate the tone from the vowel, so that the ASR algorithms learn tone patterns independently. These models showed improvements ranging from 4% to 25% in character error rate (CER), and between 3% and 23% in word error rate (WER). This is true for both traditional GMM/HMM and end-to-end CTC algorithms. This paper also presents the first attempt to train ASR models for Bribri. The best performing models had a CER of 33% and a WER of 50%. Despite the disadvantage of using hand-engineered representations, these models were trained on only 68 minutes of data, and therefore show the potential of ASR to generate further training materials and aid in the documentation and revitalization of the language. ResumenTranscribir el tono de forma explícita mejora el rendimiento del reconocimiento de voz en idiomas extremadamente bajos en recursos: Un estudio de caso en bribri. Hay numerosas maneras de transcribir el tono lingüístico a la hora de proveer los datos de entrenamiento a los sistemas de reconocimiento de voz. Este artículo presenta un experimento sistemático de varias formas de transcripción usando como ejemplo la lengua chibcha bribri, una lengua de Costa Rica extremadamente baja en recursos. Los modelos más exitosos fueron aquellos en que el tono aparece separado de la vocal de tal forma que los algoritmos pudieran aprender los patrones tonales por separado. Estos modelos mostraron mejoras de entre 4% y 26% en el error de caracteres (CER), y de entre 3% y 25% en el error de palabras (WER). Esto se observó tanto en los algoritmos GMM/HMM como en los algoritmos CTC de secuenciaa-secuencia. Este artículo también presenta el primer intento de entrenar modelos de reconocimiento de voz en bribri. Los mejores modelos tuvieron un CER de 33% y un WER de 50%. A pesar de la desventaja de usar representaciones diseñadas a mano, estos modelos se entrenaron con solo 68 minutos de datos y muestran el potencial para generar más materiales de entrenamiento, así como de ayudar con la documentación y revitalización de la lengua.

show abstract

Automatic Speech Recognition of Quechua Language Using HMM Toolkit

Cited by 4 publications

References 7 publications

Data Augmentation for Low-Resource Quechua ASR Improvement

Data Augmentation for Low-Resource Quechua ASR Improvement

Computational sociophonetics using automatic speech recognition

Explicit Tone Transcription Improves ASR Performance in Extremely Low-Resource Languages: A Case Study in Bribri

Contact Info

Product

Resources

About