Automatic Speech Recognition for Low-resource Languages and Accents Using Multilingual and Crosslingual Information PDF Download
Are you looking for read ebook online? Search for your book and save it on your Kindle device, PC, phones or tablets. Download Automatic Speech Recognition for Low-resource Languages and Accents Using Multilingual and Crosslingual Information PDF full book. Access full book title Automatic Speech Recognition for Low-resource Languages and Accents Using Multilingual and Crosslingual Information by Ngoc Thang Vu. Download full books in PDF and EPUB format.
Author: Ngoc Thang Vu
Publisher:
ISBN: 9783844028928
Category :
Languages : en
Pages : 203
Get Book Here
Book Description
Author: Ngoc Thang Vu
Publisher:
ISBN: 9783844028928
Category :
Languages : en
Pages : 203
Get Book Here
Book Description
Author: L. Ashok Kumar
Publisher: John Wiley & Sons
ISBN: 1394214170
Category : Computers
Languages : en
Pages : 428
Get Book Here
Book Description
AUTOMATIC SPEECH RECOGNITION and TRANSLATION for LOW-RESOURCE LANGUAGES This book is a comprehensive exploration into the cutting-edge research, methodologies, and advancements in addressing the unique challenges associated with ASR and translation for low-resource languages. Automatic Speech Recognition and Translation for Low Resource Languages contains groundbreaking research from experts and researchers sharing innovative solutions that address language challenges in low-resource environments. The book begins by delving into the fundamental concepts of ASR and translation, providing readers with a solid foundation for understanding the subsequent chapters. It then explores the intricacies of low-resource languages, analyzing the factors that contribute to their challenges and the significance of developing tailored solutions to overcome them. The chapters encompass a wide range of topics, ranging from both the theoretical and practical aspects of ASR and translation for low-resource languages. The book discusses data augmentation techniques, transfer learning, and multilingual training approaches that leverage the power of existing linguistic resources to improve accuracy and performance. Additionally, it investigates the possibilities offered by unsupervised and semi-supervised learning, as well as the benefits of active learning and crowdsourcing in enriching the training data. Throughout the book, emphasis is placed on the importance of considering the cultural and linguistic context of low-resource languages, recognizing the unique nuances and intricacies that influence accurate ASR and translation. Furthermore, the book explores the potential impact of these technologies in various domains, such as healthcare, education, and commerce, empowering individuals and communities by breaking down language barriers. Audience The book targets researchers and professionals in the fields of natural language processing, computational linguistics, and speech technology. It will also be of interest to engineers, linguists, and individuals in industries and organizations working on cross-lingual communication, accessibility, and global connectivity.
Author: Sarah Flora Samson Juan
Publisher:
ISBN:
Category :
Languages : en
Pages : 0
Get Book Here
Book Description
Languages in Malaysia are dying in an alarming rate. As of today, 15 languages are in danger while two languages are extinct. One of the methods to save languages is by documenting languages, but it is a tedious task when performed manually.Automatic Speech Recognition (ASR) system could be a tool to help speed up the process of documenting speeches from the native speakers. However, building ASR systems for a target language requires a large amount of training data as current state-of-the-art techniques are based on empirical approach. Hence, there are many challenges in building ASR for languages that have limited data available.The main aim of this thesis is to investigate the effects of using data from closely-related languages to build ASR for low-resource languages in Malaysia. Past studies have shown that cross-lingual and multilingual methods could improve performance of low-resource ASR. In this thesis, we try to answer several questions concerning these approaches: How do we know which language is beneficial for our low-resource language? How does the relationship between source and target languages influence speech recognition performance? Is pooling language data an optimal approach for multilingual strategy?Our case study is Iban, an under-resourced language spoken in Borneo island. We study the effects of using data from Malay, a local dominant language which is close to Iban, for developing Iban ASR under different resource constraints. We have proposed several approaches to adapt Malay data to obtain pronunciation and acoustic models for Iban speech.Building a pronunciation dictionary from scratch is time consuming, as one needs to properly define the sound units of each word in a vocabulary. We developed a semi-supervised approach to quickly build a pronunciation dictionary for Iban. It was based on bootstrapping techniques for improving Malay data to match Iban pronunciations.To increase the performance of low-resource acoustic models we explored two acoustic modelling techniques, the Subspace Gaussian Mixture Models (SGMM) and Deep Neural Networks (DNN). We performed cross-lingual strategies using both frameworks for adapting out-of-language data to Iban speech. Results show that using Malay data is beneficial for increasing the performance of Iban ASR. We also tested SGMM and DNN to improve low-resource non-native ASR. We proposed a fine merging strategy for obtaining an optimal multi-accent SGMM. In addition, we developed an accent-specific DNN using native speech data. After applying both methods, we obtained significant improvements in ASR accuracy. From our study, we observe that using SGMM and DNN for cross-lingual strategy is effective when training data is very limited.
Author: Ekapol Chuangsuwanich
Publisher:
ISBN:
Category :
Languages : en
Pages : 143
Get Book Here
Book Description
Out of the approximately 7000 languages spoken around the world, there are only about 100 languages with Automatic Speech Recognition (ASR) capability. This is due to the fact that a vast amount of resources is required to build a speech recognizer. This often includes thousands of hours of transcribed speech data, a phonetic pronunciation dictionary or lexicon which spans all words in the language, and a text collection on the order of several million words. Moreover, ASR technologies usually require years of research in order to deal with the specific idiosyncrasies of each language. This makes building a speech recognizer on a language with few resources a daunting task. In this thesis, we propose a universal ASR framework for transcription and keyword spotting (KWS) tasks that work on a variety of languages. We investigate methods to deal with the need of a pronunciation dictionary by using a Pronunciation Mixture Model that can learn from existing lexicons and acoustic data to generate pronunciation for new words. In the case when no dictionary is available, a graphemic lexicon provides comparable performance to the expert lexicon. To alleviate the need for text corpora, we investigate the use of subwords and web data which helps im- prove KWS spotting results. Finally, we reduce the need for speech recordings by using bottleneck (BN) features trained on multilingual corpora. We first propose the Low-rank Stacked Bottleneck architecture which improves ASR performance over previous state-of-the-art systems. We then investigate a method to select data from various languages that is most similar to the target language in a data-driven manner, which helps improve the eectiveness of the BN features. Using techniques described and proposed in this thesis, we are able to more than double the KWS performance for a low-resource language compared to using standard techniques geared towards rich resource domains.
Author: Ronit Damania
Publisher:
ISBN:
Category : Automatic speech recognition
Languages : en
Pages : 37
Get Book Here
Book Description
"In this thesis, we explore several novel data augmentation methods for improving the performance of automatic speech recognition (ASR) on low-resource languages. Using a 100-hour subset of English LibriSpeech to simulate a low-resource setting, we compare the well-known SpecAugment augmentation approach to these new methods, along with several other competitive baselines. We then apply the most promising combinations of models and augmentation methods to three genuinely under-resourced languages using the 40-hour Gujarati, Tamil, Telugu datasets from the 2021 Interspeech Low Resource Automatic Speech Recognition Challenge for Indian Languages. Our data augmentation approaches, coupled with state-of-the-art acoustic model architectures and language models, yield reductions in word error rate over SpecAugment and other competitive baselines for the LibriSpeech-100 dataset, showing a particular advantage over prior models for the ``other'', more challenging, dev and test sets. Extending this work to the low-resource Indian languages, we see large improvements over the baseline models and results comparable to large multilingual models."--Abstract.
Author: Ping Xu
Publisher:
ISBN:
Category : Automatic speech recognition
Languages : en
Pages : 69
Get Book Here
Book Description
Author: Zahriladha Zakaria
Publisher: Springer Nature
ISBN: 9811512892
Category : Technology & Engineering
Languages : en
Pages : 332
Get Book Here
Book Description
This book presents the proceedings of ICCEE 2019, held in Kuala Lumpur, Malaysia, on 29th–30th April 2019. It includes the latest advances in electrical engineering and electronics from leading experts around the globe.
Author:
Publisher:
ISBN:
Category :
Languages : en
Pages : 5
Get Book Here
Book Description
The paper describes a method for dealing with multilingual vocabularies in speech recognition tasks. We present an approach that combines acoustic descriptive precision and capability of generalization to multiple languages. The approach is based on the concept of classes of transitions between phones. The classes are defined by means of objective measures on acoustic similarities among sounds of different languages. This procedure stems from the definition of a general language-independent model. When a new language is to be added, the phonological structure of the language is mapped onto the set of classes belonging to the general model. Successively, if a limited amount of language-specific speech data becomes available for the new language, we identify those sounds which require the definition of additional classes. The experiments have been conducted in Italian, English and Spanish languages. The method can also be considered as a way of implementing cross-lingual porting of recognition models for a rapid prototyping of recognizers in a new target language, specifically in cases whereby the collection of large training databases would be economically infeasible.
Author: Christoph Nieuwoudt
Publisher:
ISBN:
Category :
Languages : en
Pages :
Get Book Here
Book Description
Speech recognition systems have been developed for the major languages of the world, yet for the majority of languages there are currently no large vocabulary continuous speech recognition (LVCSR) systems. The development of an LVCSR system for a new language is very costly, mainly because a large speech database has to be compiled to robustly capture the acoustic characteristics of the new language. This thesis investigates techniques that enable the re-use of acoustic information from a source language, in which a large amount of data is available, in implementing a system for a new target language. The assumption is that too little data is available in the target language to train a robust speech recognition system on that data alone, and that use of acoustic information from a source language can improve the performance of a target language recognition system. Strategies for cross-language use of acoustic information are proposed, including training on pooled source and target language data, adaptation of source language models using target language data, adapting multilingual models using target language data and transforming source language data to augment target language data for model training. These strategies are allied with Bayesian and transformation-based techniques, usually used for speaker adaptation, as well as with discriminative learning techniques, to present a framework for cross-language re-use of acoustic information. Extensions to current adaptation techniques are proposed to improve the performance of these techniques specifically for cross-language adaptation. A new technique for transformation-based adaptation of variance parameters and a cost-based extension of the minimum classification error (MCE) approach are proposed. Experiments are performed for a large number of approaches from the proposed framework for cross-language re-use of acoustic information. Relatively large amounts of English speech data are used in conjunction with smaller amounts of Afrikaans speech data to improve the performance of an Afrikaans speech recogniser. Results indicate that a significant reduction in word error rate (between 26% and 50%, depending on the amount of Afrikaans data available) is possible when English acoustic data is used in addition to Afrikaans speech data from the same database (i.e both sets of data were recorded under the same c1̀2onditions and the same labelling process was used). For same-database experiments, best results are achieved for approaches that train models on pooled source and target language data and then perform further adaptation of the models using Bayesian or discriminative techniques on target language data only. Experiments are also performed to evaluate the use of English data from a different database than the Afrikaans data. Peak reductions in word error rate of between 16% and 35% are delivered, depending on the amount of Afrikaans data available. Best results are achieved for an approach that performs a simple transformation of source model parameters using target language data, and then performs Bayesian adaptation of the transformed model on target language data.
Author: Silke Goronzy
Publisher: Springer
ISBN: 3540362908
Category : Computers
Languages : en
Pages : 135
Get Book Here
Book Description
Speech recognition technology is being increasingly employed in human-machine interfaces. A remaining problem however is the robustness of this technology to non-native accents, which still cause considerable difficulties for current systems. In this book, methods to overcome this problem are described. A speaker adaptation algorithm that is capable of adapting to the current speaker with just a few words of speaker-specific data based on the MLLR principle is developed and combined with confidence measures that focus on phone durations as well as on acoustic features. Furthermore, a specific pronunciation modelling technique that allows the automatic derivation of non-native pronunciations without using non-native data is described and combined with the previous techniques to produce a robust adaptation to non-native accents in an automatic speech recognition system.
