paper-with-me

홈 › Papers

Joint Encoder-Decoder Self-Supervised Pre-training for ASR

2022-06-09 · Arunkumar A, Umesh S

Self-supervised learning (SSL) has shown tremendous success in various speech-related downstream tasks, including Automatic Speech Recognition (ASR). The output embeddings of the SSL model are treated as powerful short-time representations of the speech signal. However, in the ASR task, the main objective is to get the correct sequence of acoustic units, characters, or byte-pair encodings (BPEs). Usually, encoder-decoder architecture works exceptionally well for a sequence-to-sequence task like ASR. Therefore, in this paper, we propose a new paradigm that exploits the power of a decoder during self-supervised learning. We use Hidden Unit BERT (HuBERT) SSL framework to compute the conventional masked prediction loss for the encoder. In addition, we have introduced a decoder in the SSL framework and proposed a target preparation strategy for the decoder. Finally, we use a multitask SSL setup wherein we jointly optimize both the encoder and decoder losses. We hypothesize that the presence of a decoder in the SSL model helps it learn an acoustic unit-based language model, which might improve the performance of an ASR downstream task. We compare our proposed SSL model with HuBERT and show up to 25% relative improvement in performance on ASR by finetuning on various LibriSpeech subsets.

📄 PDF Abstract BibTeX arXiv:2206.04465

Code (0)

등록된 구현이 없습니다.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)DecoderLanguage ModellingSelf-Supervised Learningspeech-recognitionSpeech Recognition

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Weight Decay 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
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 &…
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 $x$…

Similar Papers 제목 키워드 기반

Channel-Aware Pretraining of Joint Encoder-Decoder Self-Supervised Model for Telephonic-Speech ASR

2022-11-03 · Vrunda N. Sukhadia, A. Arunkumar, S. Umesh

This paper proposes a novel technique to obtain better downstream ASR performance from a joint encoder-decoder self-supervised model when trained with speech pooled from two different channels (narrow and wide band). The…

ClusteringDecoder

Should we pre-train a decoder in contrastive learning for dense prediction tasks?

2025-03-21 · Sébastien Quetin, Tapotosh Ghosh, Farhad Maleki

Contrastive learning in self-supervised settings primarily focuses on pre-training encoders, while decoders are typically introduced and trained separately for downstream dense prediction tasks. This conventional approac…

Contrastive LearningDecoderInstance Segmentationobject-detection+3

Joint-MAE: 2D-3D Joint Masked Autoencoders for 3D Point Cloud Pre-training

2023-02-27 · Ziyu Guo, Renrui Zhang, Longtian Qiu, Xianzhi Li 외

Masked Autoencoders (MAE) have shown promising performance in self-supervised learning for both 2D and 3D computer vision. However, existing MAE-style methods can only learn from the data of a single modality, i.e., eith…

DecoderPoint Cloud Pre-trainingRepresentation LearningSelf-Supervised Learning

Joint Training or Not: An Exploration of Pre-trained Speech Models in Audio-Visual Speaker Diarization

2023-12-07 · Huan Zhao, Li Zhang, Yue Li, Yannan Wang 외

The scarcity of labeled audio-visual datasets is a constraint for training superior audio-visual speaker diarization systems. To improve the performance of audio-visual speaker diarization, we leverage pre-trained superv…

Decoderspeaker-diarizationSpeaker Diarization

Medical visual question answering using joint self-supervised learning

2023-02-25 · Yuan Zhou, Jing Mei, Yiqin Yu, Tanveer Syeda-Mahmood

Visual Question Answering (VQA) becomes one of the most active research problems in the medical imaging domain. A well-known VQA challenge is the intrinsic diversity between the image and text modalities, and in the medi…

DecoderDiversityMedical Visual Question AnsweringQuestion Answering+3