Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userWav-BERT: Cooperative Acoustic and Linguistic Representation Learning for Low-Resource Speech Recognition
WAV-BERT: التعلم التعاوني الصوتي واللغوي التعلم للتعرف على الكلام منخفض الموارد
244
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
أصبح توحيد التعلم الصوتي واللغوي أمرا مهما بشكل متزايد بنقل المعرفة المستفادة بشأن وفرة بيانات لغة الموارد عالية الموارد للحصول على التعرف على الكلام المنخفض الموارد. الأساليب الحالية ببساطة تتالي النماذج الصوتية واللغة المدربة مسبقا لتعلم النقل من الكلام إلى النص. ومع ذلك، فإن كيفية حل تناقض التمثيل في الكلام والنص غير مستكشفة، مما يعيق استخدام المعلومات الصوتية واللغوية. علاوة على ذلك، يعمل الأمر السابق ببساطة استبدال طبقة تضمين نموذج اللغة المدربة مسبقا مع الميزات الصوتية، والتي قد تتسبب في مشكلة نسيان الكارثي. في هذا العمل، نقدم WAV-Bert، وهي طريقة تعليمية تعاونية وصوتية وممثلة على الصمامات والاستفادة من المعلومات السياقية من الكلام والنص. على وجه التحديد، نقوم بتحديد نموذج صوت صوتي مدرب مسبقا (WAV2VEC 2.0) ونموذج لغة (Bert) في إطار قابل للتدريب من طرف إلى نهاية. تم تصميم وحدة تجميع التمثيل لتجميع التمثيل الصوتي واللغوي، ويتم تقديم وحدة الانتباه التضمين لإدماج المعلومات الصوتية في بيرت، والتي يمكن أن تسهل بفعالية تعاون نماذج مدربة مسبقا وبالتالي تعزيز تعلم التمثيل. تشير التجارب الواسعة إلى أن لدينا WAV-Bert تنفأ بشكل كبير على النهج الحالية وتحقيق الأداء الحديث في التعرف على الكلام المنخفض الموارد.
Unifying acoustic and linguistic representation learning has become increasingly crucial to transfer the knowledge learned on the abundance of high-resource language data for low-resource speech recognition. Existing approaches simply cascade pre-trained acoustic and language models to learn the transfer from speech to text. However, how to solve the representation discrepancy of speech and text is unexplored, which hinders the utilization of acoustic and linguistic information. Moreover, previous works simply replace the embedding layer of the pre-trained language model with the acoustic features, which may cause the catastrophic forgetting problem. In this work, we introduce Wav-BERT, a cooperative acoustic and linguistic representation learning method to fuse and utilize the contextual information of speech and text. Specifically, we unify a pre-trained acoustic model (wav2vec 2.0) and a language model (BERT) into an end-to-end trainable framework. A Representation Aggregation Module is designed to aggregate acoustic and linguistic representation, and an Embedding Attention Module is introduced to incorporate acoustic information into BERT, which can effectively facilitate the cooperation of two pre-trained models and thus boost the representation learning. Extensive experiments show that our Wav-BERT significantly outperforms the existing approaches and achieves state-of-the-art performance on low-resource speech recognition.
References used
https://aclanthology.org/
rate research
Read More
This paper explores the effect of using multitask learning for abstractive summarization in the context of small training corpora. In particular, we incorporate four different tasks (extractive summarization, language modeling, concept detection, and
paraphrase detection) both individually and in combination, with the goal of enhancing the target task of abstractive summarization via multitask learning. We show that for many task combinations, a model trained in a multitask setting outperforms a model trained only for abstractive summarization, with no additional summarization data introduced. Additionally, we do a comprehensive search and find that certain tasks (e.g. paraphrase detection) consistently benefit abstractive summarization, not only when combined with other tasks but also when using different architectures and training corpora.
The combination of multilingual pre-trained representations and cross-lingual transfer learning is one of the most effective methods for building functional NLP systems for low-resource languages. However, for extremely low-resource languages without
large-scale monolingual corpora for pre-training or sufficient annotated data for fine-tuning, transfer learning remains an understudied and challenging task. Moreover, recent work shows that multilingual representations are surprisingly disjoint across languages, bringing additional challenges for transfer onto extremely low-resource languages. In this paper, we propose MetaXL, a meta-learning based framework that learns to transform representations judiciously from auxiliary languages to a target one and brings their representation spaces closer for effective transfer. Extensive experiments on real-world low-resource languages -- without access to large-scale monolingual corpora or large amounts of labeled data -- for tasks like cross-lingual sentiment analysis and named entity recognition show the effectiveness of our approach. Code for MetaXL is publicly available at github.com/microsoft/MetaXL.
Low-resource Relation Extraction (LRE) aims to extract relation facts from limited labeled corpora when human annotation is scarce. Existing works either utilize self-training scheme to generate pseudo labels that will cause the gradual drift problem
, or leverage meta-learning scheme which does not solicit feedback explicitly. To alleviate selection bias due to the lack of feedback loops in existing LRE learning paradigms, we developed a Gradient Imitation Reinforcement Learning method to encourage pseudo label data to imitate the gradient descent direction on labeled data and bootstrap its optimization capability through trial and error. We also propose a framework called GradLRE, which handles two major scenarios in low-resource relation extraction. Besides the scenario where unlabeled data is sufficient, GradLRE handles the situation where no unlabeled data is available, by exploiting a contextualized augmentation method to generate data. Experimental results on two public datasets demonstrate the effectiveness of GradLRE on low resource relation extraction when comparing with baselines.
While Automatic Speech Recognition has been shown to be vulnerable to adversarial attacks, defenses against these attacks are still lagging. Existing, naive defenses can be partially broken with an adaptive attack. In classification tasks, the Random
ized Smoothing paradigm has been shown to be effective at defending models. However, it is difficult to apply this paradigm to ASR tasks, due to their complexity and the sequential nature of their outputs. Our paper overcomes some of these challenges by leveraging speech-specific tools like enhancement and ROVER voting to design an ASR model that is robust to perturbations. We apply adaptive versions of state-of-the-art attacks, such as the Imperceptible ASR attack, to our model, and show that our strongest defense is robust to all attacks that use inaudible noise, and can only be broken with very high distortion.
We address the task of automatic hate speech detection for low-resource languages. Rather than collecting and annotating new hate speech data, we show how to use cross-lingual transfer learning to leverage already existing data from higher-resource l
anguages. Using bilingual word embeddings based classifiers we achieve good performance on the target language by training only on the source dataset. Using our transferred system we bootstrap on unlabeled target language data, improving the performance of standard cross-lingual transfer approaches. We use English as a high resource language and German as the target language for which only a small amount of annotated corpora are available. Our results indicate that cross-lingual transfer learning together with our approach to leverage additional unlabeled data is an effective way of achieving good performance on low-resource target languages without the need for any target-language annotations.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
