paper-with-me

Papers

Audio ALBERT: A Lite BERT for Self-supervised Learning of Audio Representation

2020-05-18 · Po-Han Chi, Pei-Hung Chung, Tsung-Han Wu, Chun-Cheng Hsieh, Yen-Hao Chen, Shang-Wen Li, Hung-Yi Lee

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.

📄 PDF Abstract BibTeX arXiv:2005.08575

Code (4)

Vernacular-ai/Multimodal-Slu pytorch
andi611/Self-Supervised-Speech-Pretraining-and-Representation-Learning pytorch
joselyn-rodriguez/s3prl pytorch
s3prl/s3prl pytorch

Tasks

Self-Supervised LearningSpeaker Identification

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Adam 설명 없음
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Attention 설명 없음
WordPiece 설명 없음

Similar Papers 제목 키워드 기반

ALBERT: A Lite BERT for Self-supervised Learning of Language Representations

2019-09-26 · ICLR 2020 1 · Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel 외

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+6

BioALBERT: A Simple and Effective Pre-trained Language Model for Biomedical Named Entity Recognition

2020-09-19 · Usman Naseem, Matloob Khushi, Vinay Reddy, Sakthivel Rajendran 외

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+3

BERT vs ALBERT explained

2022-01-17 · ICLR Track Blog 2022 5 · Anonymous

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 Learning

KoreALBERT: Pretraining a Lite BERT Model for Korean Language Understanding

2021-01-27 · Hyunjae Lee, Jaewoong Yoon, Bonggyu Hwang, Seongho Joe 외

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 LearningSentence

Evaluation of BERT and ALBERT Sentence Embedding Performance on Downstream NLP Tasks

2021-01-26 · Hyunjin Choi, Judong Kim, Seongho Joe, Youngjune Gwon

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