Masked Audio Text Encoders are Effective Multi-Modal Rescorers
Masked Language Models (MLMs) have proven to be effective for second-pass rescoring in Automatic Speech Recognition (ASR) systems. In this work, we propose Masked Audio Text Encoder (MATE), a multi-modal masked language model rescorer which incorporates acoustic representations into the input space of MLM. We adopt contrastive learning for effectively aligning the modalities by learning shared representations. We show that using a multi-modal rescorer is beneficial for domain generalization of the ASR system when target domain data is unavailable. MATE reduces word error rate (WER) by 4%-16% on in-domain, and 3%-7% on out-of-domain datasets, over the text-only baseline. Additionally, with very limited amount of training data (0.8 hours), MATE achieves a WER reduction of 8%-23% over the first-pass baseline.
Code (0)
등록된 구현이 없습니다.
Tasks
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Contrastive LearningDomain GeneralizationLanguage ModelingLanguage Modellingspeech-recognitionSpeech RecognitionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Language-Guided Contrastive Audio-Visual Masked Autoencoder with Automatically Generated Audio-Visual-Text Triplets from Videos
In this paper, we propose Language-Guided Contrastive Audio-Visual Masked Autoencoders (LG-CAV-MAE) to improve audio-visual representation learning. LG-CAV-MAE integrates a pretrained text encoder into contrastive audio-…
Image CaptioningRepresentation LearningRetrievalMasked Autoencoders that Listen
This paper studies a simple extension of image-based Masked Autoencoders (MAE) to self-supervised representation learning from audio spectrograms. Following the Transformer encoder-decoder design in MAE, our Audio-MAE fi…
Audio ClassificationDecoderRepresentation LearningSpeaker IdentificationFoley-Flow: Coordinated Video-to-Audio Generation with Masked Audio-Visual Alignment and Dynamic Conditional Flows
Coordinated audio generation based on video inputs typically requires a strict audio-visual (AV) alignment, where both semantics and rhythmics of the generated audio segments shall correspond to those in the video frames…
Contrastive LearningAudio GenerationFoley-Flow: Coordinated Video-to-Audio Generation with Masked Audio-Visual Alignment and Dynamic Conditional Flows
Coordinated audio generation based on video inputs typically requires a strict audio-visual (AV) alignment, where both semantics and rhythmics of the generated audio segments shall correspond to those in the video fr…
Audio GenerationContrastive LearningA vector quantized masked autoencoder for audiovisual speech emotion recognition
An important challenge in emotion recognition is to develop methods that can leverage unlabeled training data. In this paper, we propose the VQ-MAE-AV model, a self-supervised multimodal model that leverages masked autoe…
Contrastive LearningEmotion RecognitionRepresentation LearningSelf-Supervised Learning+1