Cross-modal Knowledge Transfer Learning as Graph Matching Based on Optimal Transport for ASR

• URL: http://arxiv.org/abs/2505.13079v1
• Date: Mon, 19 May 2025 13:13:18 GMT
• Title: Cross-modal Knowledge Transfer Learning as Graph Matching Based on Optimal Transport for ASR
• Authors: Xugang Lu, Peng Shen, Yu Tsao, Hisashi Kawai,
• Abstract summary: Transferring linguistic knowledge from a pretrained language model to acoustic feature learning has proven effective in enhancing end-to-end automatic speech recognition (E2E-ASR)<n> aligning representations between linguistic and acoustic modalities remains a challenge due to inherent modality gaps.<n>We propose Graph Matching Optimal Transport (GM-OT), which models linguistic and acoustic sequences as structured graphs.
• Score: 36.250914527327005
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Transferring linguistic knowledge from a pretrained language model (PLM) to acoustic feature learning has proven effective in enhancing end-to-end automatic speech recognition (E2E-ASR). However, aligning representations between linguistic and acoustic modalities remains a challenge due to inherent modality gaps. Optimal transport (OT) has shown promise in mitigating these gaps by minimizing the Wasserstein distance (WD) between linguistic and acoustic feature distributions. However, previous OT-based methods overlook structural relationships, treating feature vectors as unordered sets. To address this, we propose Graph Matching Optimal Transport (GM-OT), which models linguistic and acoustic sequences as structured graphs. Nodes represent feature embeddings, while edges capture temporal and sequential relationships. GM-OT minimizes both WD (between nodes) and Gromov-Wasserstein distance (GWD) (between edges), leading to a fused Gromov-Wasserstein distance (FGWD) formulation. This enables structured alignment and more efficient knowledge transfer compared to existing OT-based approaches. Theoretical analysis further shows that prior OT-based methods in linguistic knowledge transfer can be viewed as a special case within our GM-OT framework. We evaluate GM-OT on Mandarin ASR using a CTC-based E2E-ASR system with a PLM for knowledge transfer. Experimental results demonstrate significant performance gains over state-of-the-art models, validating the effectiveness of our approach.

Related papers

• Temporal Order Preserved Optimal Transport-based Cross-modal Knowledge Transfer Learning for ASR [36.250914527327005]
  Transferring linguistic knowledge from a pretrained language model to an acoustic model has been shown to greatly improve the performance of automatic speech recognition. We propose a Temporal Order Preserved OT (TOT)-based Cross-modal Alignment and Knowledge Transfer (CAKT) for ASR.
  arXiv  Detail & Related papers  (2024-09-03T19:11:15Z)
• Utilizing Neural Transducers for Two-Stage Text-to-Speech via Semantic Token Prediction [15.72317249204736]
  We propose a novel text-to-speech (TTS) framework centered around a neural transducer. Our approach divides the whole TTS pipeline into semantic-level sequence-to-sequence (seq2seq) modeling and fine-grained acoustic modeling stages. Our experimental results on zero-shot adaptive TTS demonstrate that our model surpasses the baseline in terms of speech quality and speaker similarity.
  arXiv  Detail & Related papers  (2024-01-03T02:03:36Z)
• Scalable Learning of Latent Language Structure With Logical Offline Cycle Consistency [71.42261918225773]
  Conceptually, LOCCO can be viewed as a form of self-learning where the semantic being trained is used to generate annotations for unlabeled text. As an added bonus, the annotations produced by LOCCO can be trivially repurposed to train a neural text generation model.
  arXiv  Detail & Related papers  (2023-05-31T16:47:20Z)
• End-to-End Active Speaker Detection [58.7097258722291]
  We propose an end-to-end training network where feature learning and contextual predictions are jointly learned. We also introduce intertemporal graph neural network (iGNN) blocks, which split the message passing according to the main sources of context in the ASD problem. Experiments show that the aggregated features from the iGNN blocks are more suitable for ASD, resulting in state-of-the art performance.
  arXiv  Detail & Related papers  (2022-03-27T08:55:28Z)
• Speech recognition for air traffic control via feature learning and end-to-end training [8.755785876395363]
  We propose a new automatic speech recognition (ASR) system based on feature learning and an end-to-end training procedure for air traffic control (ATC) systems. The proposed model integrates the feature learning block, recurrent neural network (RNN), and connectionist temporal classification loss. Thanks to the ability to learn representations from raw waveforms, the proposed model can be optimized in a complete end-to-end manner.
  arXiv  Detail & Related papers  (2021-11-04T06:38:21Z)
• Efficiently Fusing Pretrained Acoustic and Linguistic Encoders for Low-resource Speech Recognition [9.732767611907068]
  In this work, we fuse a pre-trained acoustic encoder (wav2vec2.0) and a pre-trained linguistic encoder (BERT) into an end-to-end ASR model. Our model achieves better recognition performance on CALLHOME corpus (15 hours) than other end-to-end models.
  arXiv  Detail & Related papers  (2021-01-17T16:12:44Z)
• Graph Optimal Transport for Cross-Domain Alignment [121.80313648519203]
  Cross-domain alignment is fundamental to computer vision and natural language processing. We propose Graph Optimal Transport (GOT), a principled framework that germinates from recent advances in Optimal Transport (OT) Experiments show consistent outperformance of GOT over baselines across a wide range of tasks.
  arXiv  Detail & Related papers  (2020-06-26T01:14:23Z)
• Learning Source Phrase Representations for Neural Machine Translation [65.94387047871648]
  We propose an attentive phrase representation generation mechanism which is able to generate phrase representations from corresponding token representations. In our experiments, we obtain significant improvements on the WMT 14 English-German and English-French tasks on top of the strong Transformer baseline.
  arXiv  Detail & Related papers  (2020-06-25T13:43:11Z)
• Jointly Trained Transformers models for Spoken Language Translation [2.3886615435250302]
  This work trains SLT systems with ASR objective as an auxiliary loss and both the networks are connected through neural hidden representations. This architecture has improved from BLEU from 36.8 to 44.5. All the experiments are reported on English-Portuguese speech translation task using How2 corpus.
  arXiv  Detail & Related papers  (2020-04-25T11:28:39Z)
• Joint Contextual Modeling for ASR Correction and Language Understanding [60.230013453699975]
  We propose multi-task neural approaches to perform contextual language correction on ASR outputs jointly with language understanding (LU) We show that the error rates of off the shelf ASR and following LU systems can be reduced significantly by 14% relative with joint models trained using small amounts of in-domain data.
  arXiv  Detail & Related papers  (2020-01-28T22:09:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.