Audio ALBERT: A Lite BERT for Self-supervised Learning of Audio Representation
For self-supervised speech processing, it is crucial to use pretrained models as speech representation extractors. In recent works, increasing the size of the model has been utilized in acoustic model training in order to achieve better performance. In this paper, we propose Audio ALBERT, a lite version of the self-supervised speech representation model. We use the representations with two downstream tasks, speaker identification, and phoneme classification. We show that Audio ALBERT is capable of achieving competitive performance with those huge models in the downstream tasks while utilizing 91\% fewer parameters. Moreover, we use some simple probing models to measure how much the information of the speaker and phoneme is encoded in latent representations. In probing experiments, we find that the latent representations encode richer information of both phoneme and speaker than that of the last layer.
Code (4)
Tasks
Self-Supervised LearningSpeaker IdentificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
Increasing model size when pretraining natural language representations often results in improved performance on downstream tasks. However, at some point further model increases become harder due to GPU/TPU memory limita…
Common Sense ReasoningGPULinguistic AcceptabilityMultimodal Intent Recognition+6BioALBERT: A Simple and Effective Pre-trained Language Model for Biomedical Named Entity Recognition
In recent years, with the growing amount of biomedical documents, coupled with advancement in natural language processing algorithms, the research on biomedical named entity recognition (BioNER) has increased exponential…
Language ModelingLanguage Modellingnamed-entity-recognitionNamed Entity Recognition+3BERT vs ALBERT explained
Implementing Machine Learning and Deep Learning models at scale require an immense amount of training time and computational resources. Particularly in the context of language representation learning, studies have shown …
Representation LearningSelf-Supervised LearningKoreALBERT: Pretraining a Lite BERT Model for Korean Language Understanding
A Lite BERT (ALBERT) has been introduced to scale up deep bidirectional representation learning for natural languages. Due to the lack of pretrained ALBERT models for Korean language, the best available practice is the m…
Representation LearningSentenceEvaluation of BERT and ALBERT Sentence Embedding Performance on Downstream NLP Tasks
Contextualized representations from a pre-trained language model are central to achieve a high performance on downstream NLP task. The pre-trained BERT and A Lite BERT (ALBERT) models can be fine-tuned to give state-ofth…
Language ModellingNatural Language InferenceSemantic Textual SimilaritySentence+5