paper-with-me

홈 › Papers

Self-Supervised Audio-and-Text Pre-training with Extremely Low-Resource Parallel Data

2022-04-10 · Yu Kang, Tianqiao Liu, Hang Li, Yang Hao, Wenbiao Ding

Multimodal pre-training for audio-and-text has recently been proved to be effective and has significantly improved the performance of many downstream speech understanding tasks. However, these state-of-the-art pre-training audio-text models work well only when provided with large amount of parallel audio-and-text data, which brings challenges on many languages that are rich in unimodal corpora but scarce of parallel cross-modal corpus. In this paper, we investigate whether it is possible to pre-train an audio-text multimodal model with extremely low-resource parallel data and extra non-parallel unimodal data. Our pre-training framework consists of the following components: (1) Intra-modal Denoising Auto-Encoding (IDAE), which is able to reconstruct input text (audio) representations from a noisy version of itself. (2) Cross-modal Denoising Auto-Encoding (CDAE), which is pre-trained to reconstruct the input text (audio), given both a noisy version of the input text (audio) and the corresponding translated noisy audio features (text embeddings). (3) Iterative Denoising Process (IDP), which iteratively translates raw audio (text) and the corresponding text embeddings (audio features) translated from previous iteration into the new less-noisy text embeddings (audio features). We adapt a dual cross-modal Transformer as our backbone model which consists of two unimodal encoders for IDAE and two cross-modal encoders for CDAE and IDP. Our method achieves comparable performance on multiple downstream speech understanding tasks compared with the model pre-trained on fully parallel data, demonstrating the great potential of the proposed method. Our code is available at: \url{https://github.com/KarlYuKang/Low-Resource-Multimodal-Pre-training}.

📄 PDF Abstract BibTeX arXiv:2204.04645

Code (1)

karlyukang/low-resource-multimodal-pre-training 공식 구현 pytorch

Tasks

Denoising

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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…
Position-Wise Feed-Forward Layer 설명 없음
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…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Similar Papers 제목 키워드 기반

Self-Supervised Beat Tracking in Musical Signals with Polyphonic Contrastive Learning

2022-01-05 · Dorian Desblancs

Annotating musical beats is a very long and tedious process. In order to combat this problem, we present a new self-supervised learning pretext task for beat tracking and downbeat estimation. This task makes use of Splee…

Audio Source SeparationBeat TrackingContrastive LearningSelf-Supervised Learning

The Impact of Spatiotemporal Augmentations on Self-Supervised Audiovisual Representation Learning

2021-10-13 · Haider Al-Tahan, Yalda Mohsenzadeh

Contrastive learning of auditory and visual perception has been extremely successful when investigated individually. However, there are still major questions on how we could integrate principles learned from both domains…

Contrastive LearningRepresentation LearningSelf-Supervised Learning

S-SONDO: Self-Supervised Knowledge Distillation for General Audio Foundation Models

2026-04-27 · Mohammed Ali El Adlouni, Aurian Quelennec, Pierre Chouteau, Geoffroy Peeters 외 arxiv

General audio foundation models have recently achieved remarkable progress, enabling strong performance across diverse tasks. However, state-of-the-art models remain extremely large, often with hundreds of millions of pa…

Knowledge DistillationModel Compression

AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining

2023-08-10 · Haohe Liu, Yi Yuan, Xubo Liu, Xinhao Mei 외

Although audio generation shares commonalities across different types of audio, such as speech, music, and sound effects, designing models for each type requires careful consideration of specific objectives and biases th…

Audio GenerationIn-Context LearningRepresentation LearningText-to-Music Generation+2

Learning Speech Representations from Raw Audio by Joint Audiovisual Self-Supervision

2020-07-08 · Abhinav Shukla, Stavros Petridis, Maja Pantic

The intuitive interaction between the audio and visual modalities is valuable for cross-modal self-supervised learning. This concept has been demonstrated for generic audiovisual tasks like video action recognition and a…

Acoustic Scene ClassificationAction RecognitionScene ClassificationSelf-Supervised Learning+1