paper-with-me

Papers

MCR-Data2vec 2.0: Improving Self-supervised Speech Pre-training via Model-level Consistency Regularization

2023-06-14 · Ji Won Yoon, Seok Min Kim, Nam Soo Kim

Self-supervised learning (SSL) has shown significant progress in speech processing tasks. However, despite the intrinsic randomness in the Transformer structure, such as dropout variants and layer-drop, improving the model-level consistency remains under-explored in the speech SSL literature. To address this, we propose a new pre-training method that uses consistency regularization to improve Data2vec 2.0, the recent state-of-the-art (SOTA) SSL model. Specifically, the proposed method involves sampling two different student sub-models within the Data2vec 2.0 framework, enabling two output variants derived from a single input without additional parameters. Subsequently, we regularize the outputs from the student sub-models to be consistent and require them to predict the representation of the teacher model. Our experimental results demonstrate that the proposed approach improves the SSL model's robustness and generalization ability, resulting in SOTA results on the SUPERB benchmark.

📄 PDF Abstract BibTeX arXiv:2306.08463

Code (0)

등록된 구현이 없습니다.

Tasks

Self-Supervised Learning

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Position-Wise Feed-Forward Layer 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Similar Papers 제목 키워드 기반

Mandarin-English Code-switching Speech Recognition with Self-supervised Speech Representation Models

2021-10-07 · Liang-Hsuan Tseng, Yu-Kuan Fu, Heng-Jui Chang, Hung-Yi Lee

Code-switching (CS) is common in daily conversations where more than one language is used within a sentence. The difficulties of CS speech recognition lie in alternating languages and the lack of transcribed data. Theref…

Language IdentificationSelf-Supervised LearningSentencespeech-recognition+1

Self-supervised Speech Models for Word-Level Stuttered Speech Detection

2024-09-16 · Yi-Jen Shih, Zoi Gkalitsiou, Alexandros G. Dimakis, David Harwath

Clinical diagnosis of stuttering requires an assessment by a licensed speech-language pathologist. However, this process is time-consuming and requires clinicians with training and experience in stuttering and fluency di…

Self-Supervised Syllable Discovery Based on Speaker-Disentangled HuBERT

2024-09-16 · Ryota Komatsu, Takahiro Shinozaki

Self-supervised speech representation learning has become essential for extracting meaningful features from untranscribed audio. Recent advances highlight the potential of deriving discrete symbols from the features corr…

Acoustic Unit DiscoveryClusteringData AugmentationRepresentation Learning+3

Integrating Self-supervised Speech Model with Pseudo Word-level Targets from Visually-grounded Speech Model

2024-02-08 · Hung-Chieh Fang, Nai-Xuan Ye, Yi-Jen Shih, Puyuan Peng 외

Recent advances in self-supervised speech models have shown significant improvement in many downstream tasks. However, these models predominantly centered on frame-level training objectives, which can fall short in spoke…

modelSpoken Language Understanding

token2vec: A Joint Self-Supervised Pre-training Framework Using Unpaired Speech and Text

2022-10-30 · Xianghu Yue, Junyi Ao, Xiaoxue Gao, Haizhou Li

Self-supervised pre-training has been successful in both text and speech processing. Speech and text offer different but complementary information. The question is whether we are able to perform a speech-text joint pre-t…

intent-classificationIntent ClassificationLanguage ModelingLanguage Modelling