Data Augmentation for Automatic Speech Recognition for Low Resource Languages 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 Data Augmentation for Automatic Speech Recognition for Low Resource Languages PDF full book. Access full book title Data Augmentation for Automatic Speech Recognition for Low Resource Languages by Ronit Damania. Download full books in PDF and EPUB format.
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: 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: 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: Vigneshwar Lakshminarayanan
Publisher:
ISBN:
Category : Automatic speech recognition
Languages : en
Pages : 0
Get Book Here
Book Description
"The usage of deep learning algorithms has resulted in significant progress in automatic speech recognition (ASR). The ASR models may require over a thousand hours of speech data to accurately recognize the speech. There have been case studies that have indicated that there are certain factors like noise, acoustic distorting conditions, and voice quality that has affected the performance of speech recognition. In this research, we investigate the impact of noise on Automatic Speech Recognition and explore novel methods for developing noise-robust ASR models using the Tamil language dataset with limited resources. We are using the speech dataset provided by SpeechOcean.com and Microsoft for the Indian languages. We add several kinds of noise to the dataset and find out how these noises impact the ASR performance. We also determine whether certain data augmentation methods like raw data augmentation and spectrogram augmentation (SpecAugment) are better suited to different types of noises. Our results show that all noises, regardless of the type, had an impact on ASR performance, and upgrading the architecture alone were unable to mitigate the impact of noise. Raw data augmentation enhances ASR performance on both clean data and noise-mixed data, however, this was not the case with SpecAugment on the same test sets. As a result, raw data augmentation performs way better than SpecAugment over the baseline models."--Abstract.
Author: Ethan Morris
Publisher:
ISBN:
Category : Automatic speech recognition
Languages : en
Pages : 65
Get Book Here
Book Description
"The application of deep neural networks to the task of acoustic modeling for automatic speech recognition (ASR) has resulted in dramatic decreases of word error rates, allowing for the use of this technology in smart phones and personal home assistants in high-resource languages. Developing ASR models of this caliber, however, requires hundreds or thousands of hours of transcribed speech recordings, which presents challenges for most of the world’s languages. In this work, we investigate the applicability of three distinct architectures that have previously been used for ASR in languages with limited training resources. We tested these architectures using publicly available ASR datasets for several typologically and orthographically diverse languages, whose data was produced under a variety of conditions using different speech collection strategies, practices, and equipment. Additionally, we performed data augmentation on this audio, such that the amount of data could increase nearly tenfold, synthetically creating higher resource training. The architectures and their individual components were modified, and parameters explored such that we might find a best-fit combination of features and modeling schemas to fit a specific language morphology. Our results point to the importance of considering language-specific and corpus-specific factors and experimenting with multiple approaches when developing ASR systems for resource-constrained languages."--Abstract.
Author: Alexey Karpov
Publisher: Springer Nature
ISBN: 3030878023
Category : Computers
Languages : en
Pages : 856
Get Book Here
Book Description
This book constitutes the proceedings of the 23rd International Conference on Speech and Computer, SPECOM 2021, held in St. Petersburg, Russia, in September 2021.* The 74 papers presented were carefully reviewed and selected from 163 submissions. The papers present current research in the area of computer speech processing including audio signal processing, automatic speech recognition, speaker recognition, computational paralinguistics, speech synthesis, sign language and multimodal processing, and speech and language resources. *Due to the COVID-19 pandemic, SPECOM 2021 was held as a hybrid event.
Author: Bao Thai
Publisher:
ISBN:
Category : Automatic speech recognition
Languages : en
Pages : 73
Get Book Here
Book Description
"While deep learning algorithms have made significant progress in automatic speech recognition and natural language processing, they require a significant amount of labelled training data to perform effectively. As such, these applications have not been extended to languages that have only limited amount of data available, such as extinct or endangered languages. Another problem caused by the rise of deep learning is that individuals with malicious intents have been able to leverage these algorithms to create fake contents that can pose serious harm to security and public safety. In this work, we explore the solutions to both of these problems. First, we investigate different data augmentation methods and acoustic architecture designs to improve automatic speech recognition performance on low-resource languages. Data augmentation for audio often involves changing the characteristic of the audio without modifying the ground truth. For example, different background noise can be added to an utterance while maintaining the content of the speech. We also explored how different acoustic model paradigms and complexity affect performance on low-resource languages. These methods are evaluated on Seneca, an endangered language spoken by a Native American tribe, and Iban, a low-resource language spoken in Malaysia and Brunei. Secondly, we explore methods to determine speaker identification and audio spoofing detection. A spoofing attack involves using either a text-to-speech voice conversion application to generate audio that mimic the identity of a target speaker. These methods are evaluated on the ASVSpoof 2019 Logical Access dataset containing audio generated using various methods of voice conversion and text-to-speech synthesis."--Abstract.
Author: L. Ashok Kumar
Publisher: John Wiley & Sons
ISBN: 1394213581
Category : Computers
Languages : en
Pages : 500
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: Kruthika Prasanna Simha
Publisher:
ISBN:
Category : Automatic speech recognition
Languages : en
Pages : 76
Get Book Here
Book Description
"As the world moves towards a more globalized scenario, it has brought along with it the extinction of several languages. It has been estimated that over the next century, over half of the world's languages will be extinct, and an alarming 43% of the world's languages are at different levels of endangerment or extinction already. The survival of many of these languages depends on the pressure imposed on the dwindling speakers of these languages. Often there is a strong correlation between endangered languages and the number and quality of recordings and documentations of each. But why do we care about preserving these less prevalent languages? The behavior of cultures is often expressed in the form of speech via one's native language. The memories, ideas, major events, practices, cultures and lessons learnt, both individual as well as the community's, are all communicated to the outside world via language. So, language preservation is crucial to understanding the behavior of these communities. Deep learning models have been shown to dramatically improve speech recognition accuracy but require large amounts of labelled data. Unfortunately, resource constrained languages typically fall short of the necessary data for successful training. To help alleviate the problem, data augmentation techniques fabricate many new samples from each sample. The aim of this master's thesis is to examine the effect of different augmentation techniques on speech recognition of resource constrained languages. The augmentation methods being experimented with are noise augmentation, pitch augmentation, speed augmentation as well as voice transformation augmentation using Generative Adversarial Networks (GANs). This thesis also examines the effectiveness of GANs in voice transformation and its limitations. The information gained from this study will further augment the collection of data, specifically, in understanding the conditions required for the data to be collected in, so that GANs can effectively perform voice transformation. Training of the original data on the Deep Speech model resulted in 95.03% WER. Training the Seneca data on a Deep Speech model that was pretrained on an English dataset, reduced the WER to 70.43%. On adding 15 augmented samples per sample, the WER reduced to 68.33%. Finally, adding 25 augmented samples per sample, the WER reduced to 48.23%. Experiments to find the best augmentation method among noise addition, pitch variation, speed variation augmentation and GAN augmentation revealed that GAN augmentation performed the best, with a WER reduction to 60.03%."--Abstract.
Author: Alexey Karpov
Publisher: Springer
ISBN: 3319995790
Category : Computers
Languages : en
Pages : 806
Get Book Here
Book Description
This book constitutes the proceedings of the 20th International Conference on Speech and Computer, SPECOM 2018, held in Leipzig, Germany, in September 2018. The 79 papers presented in this volume were carefully reviewed and selected from 132 submissions. The papers present current research in the area of computer speech processing, including recognition, synthesis, understanding and related domains like signal processing, language and text processing, computational paralinguistics, multi-modal speech processing or human-computer interaction.
Author: Jennifer Fox Drexler
Publisher:
ISBN:
Category :
Languages : en
Pages : 140
Get Book Here
Book Description
In this thesis, we explore the problem of training end-to-end neural network models for automatic speech recognition (ASR) when limited training data are available. End-to-end models are theoretically well-suited to low-resource languages because they do not rely on expert linguistic resources, but they are difficult to train without large amounts of transcribed speech. This amount of training data is prohibitively expensive to acquire in most of the world’s languages. We present several methods for improving end-to-end neural network-based ASR in low-resource scenarios. First, we explore two methods for creating a shared embedding space for speech and text. In doing so, we learn representations of speech that contain only linguistic content and not, for example, the speaker or noise characteristics in the speech signal. These linguistic-only representations allow the ASR model to generalize better to unseen speech by discouraging the model from learning spurious correlations between the text transcripts and extra-linguistic factors in speech. This shared embedding space also enables semi-supervised training of some parameters of the ASR model with additional text. Next, we experiment with two techniques for probabilistically segmenting text into subword units during training. We introduce the n-gram maximum likelihood loss, which allows the ASR model to learn an inventory of acoustically-inspired subword units as part of the training process. We show that this technique combines well with the embedding space alignment techniques in the previous section, leading to a 44% relative improvement in word error rate in the lowest resource condition tested.
