The SLT 2021 Children Speech Recognition Challenge: Open Datasets, Rules and Baselines

Yu, Fan; Yao, Zhuoyuan; Wang, Xiong; An, Keyu; Xie, Lei; Ou, Zhijian; Liu, Bo; Li, Xiulin; Guanqiong, Miao,

doi:10.1109/slt48900.2021.9383608

Cited by 11 publications

(5 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The use of SSL for child ASR was first seen at Interspeech2021, where a model using SSL [32] received first place for non-native child speech challenge. A similar use case [24] was also presented in the SLT 2021 children speech recognition challenge [33]. Another approach is used in [34], where the author uses a bidirectional unsupervised model pretraining with child speech ASR.…”

Section: B Self-supervised Learning For Child Asrmentioning

confidence: 99%

A WAV2VEC2-Based Experimental Study on Self-Supervised Learning Methods to Improve Child Speech Recognition

Jain,

Barcovschi,

Yiwere

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Despite recent advancements in deep learning technologies, Child Speech Recognition remains a challenging task. Current Automatic Speech Recognition (ASR) models require substantial amounts of annotated data for training, which is scarce. In this work, we explore using the ASR model, wav2vec2, with different pretraining and finetuning configurations for self-supervised learning (SSL) toward improving automatic child speech recognition. The pretrained wav2vec2 models were finetuned using different amounts of child speech training data, adult speech data, and a combination of both, to discover the optimum amount of data required to finetune the model for the task of child ASR. Our trained model achieves the best Word Error Rate (WER) of 7.42 on the MyST child speech dataset, 2.91 on the PFSTAR dataset and 12.77 on the CMU KIDS dataset using cleaned variants of each dataset. Our models outperformed the unmodified wav2vec2 BASE 960 on child speech using as little as 10 hours of child speech data in finetuning. The analysis of different types of training data and their effect on inference is provided by using a combination of custom datasets in pretraining, finetuning and inference. These 'cleaned' datasets are provided for use by other researchers to provide comparisons with our results.

show abstract

Section: B Self-supervised Learning For Child Asrmentioning

confidence: 99%

A WAV2VEC2-Based Experimental Study on Self-Supervised Learning Methods to Improve Child Speech Recognition

Jain,

Barcovschi,

Yiwere

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Noise from background sources affects capacity of fault tolerance, reliability, accuracy, efficiency and performance of the audio input processing (17) system thus resulting in low output. Another issue is the synchronization of the user reaction with that of ready audio input device.…”

Section: Efficiency and Performance Of The Input System For Audio Pro...mentioning

confidence: 99%

KHiTE: Multilingual Speech Acquisition to Monolingual Text Translation

Rudrappa¹,

Reddy²,

Hanumanthappa³

2023

IJST

View full text Add to dashboard Cite

Objectives: To develop a system that accepts cross-lingual spoken reviews consisting of two to four languages, translate to target language text for Indic languages namely Kannada, Hindi, Telugu and/or English termed as cross lingual speech identification and text translation system. Methods: Hybridization of software engineering models are used in natural languages for pre-processing such as noise removal and speech splitting to obtain phonemes. Combinatorial models namely Hidden-Markov-Model, Artificial Neural Networks, Deep Neural Networks and Convulutional Neural Networks were deployed for direct and indirect speech mapping. Trained corpus consisting of thousand phonemes in the form of wave files for each language considered is named as KHiTEShabdanjali. The basic parameters cosidered for training dataset are pause, pitch, sampling frequency, threshold etc. Findings: The research has resulted in the development of mono-lingual and multi-lingual speech identification, tool for processing of cross-lingual speech and language identification, mono-lingual, bi-lingual, tri-lingual and quad-lingual speech to monolingual text translation for the four languages. It is a generic approach and can be used for other regional languages of India by training the corpus with the selected language. Novelty: Cross-lingual speech identification and text translation system helps users in e-shopping by reducing the time incurred in making a decision to purchase a product having enough features at an economical price, e-tutoring, e-farming activities, digitizing, defence etc.

show abstract

“…Dentre os problemas existentes está a necessidade de amplo volume de dados rotulados para treinamento adequado de modelos que sejam capazes de identificar variac ¸ões de fala e regionalismos. Recentemente, abordagens com treinamento autosupervisionado têm permitido o surgimento de modelos pré-treinados que podem ser especializados para determinadas tarefas utilizando conjuntos mais reduzidos de áudios, como é o caso do Wav2Vec2 [Yu et al 2021, Fan et al 2021, Jain et al 2022]. Contudo, essa abordagem ainda não foi explorada no contexto de avaliac ¸ão de fluência.…”

Section: Trabalhos Relacionadosunclassified

Avaliação de modelos para reconhecimento automático de fala aplicados para identificação da qualidade de leituras em voz alta de narrativas breves

Ferreira

Silva²,

Assis³

et al. 2022

Anais Do XXXIII Simpósio Brasileiro De Informática Na Educação (SBIE 2022)

View full text Add to dashboard Cite

Os avanços na área de reconhecimento automático de fala (ASR) tem permitido o surgimento de soluções inovadoras na área de Informática na Educação, especialmente no domínio de avaliação da alfabetização. O seu uso para reconhecimento de fala infantil, contudo, ainda traz desafios e faltam trabalhos que analisem novas tecnologias neste domínio de aplicação. Este trabalho apresenta uma comparação entre duas tecnologias de ASR no contexto de fala de crianças para a avaliação automática de fluência de leitura: uma abordagem supervisionada e uma abordagem auto-supervisionada. Foram utilizados 59 áudios de leituras de crianças. O Wav2Vec2 em conjunto com um modelo de língua apresentou resultados substancialmente melhores que os demais modelos em relação à taxa de erro de palavras.

show abstract

The SLT 2021 Children Speech Recognition Challenge: Open Datasets, Rules and Baselines

Cited by 11 publications

References 14 publications

A WAV2VEC2-Based Experimental Study on Self-Supervised Learning Methods to Improve Child Speech Recognition

A WAV2VEC2-Based Experimental Study on Self-Supervised Learning Methods to Improve Child Speech Recognition

KHiTE: Multilingual Speech Acquisition to Monolingual Text Translation

Avaliação de modelos para reconhecimento automático de fala aplicados para identificação da qualidade de leituras em voz alta de narrativas breves

Contact Info

Product

Resources

About