# Optimizing Alignment of Speech and Language Latent Spaces for End-to-End Speech Recognition and Understanding

arXiv: https://arxiv.org/abs/2110.12138 · HTML: https://mlsanity.com/paper/2110.12138/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Oct 2021.

## Built on by (most cited first, 11 of 11)

- [SpeechLM: Enhanced Speech Pre-Training with Unpaired Textual Data](https://mlsanity.com/paper/2209.15329/) (2022)
- [SpeechUT: Bridging Speech and Text with Hidden-Unit for Encoder-Decoder Based Speech-Text Pre-training](https://mlsanity.com/paper/2210.03730/) (2022)
- [VATLM: Visual-Audio-Text Pre-Training with Unified Masked Prediction for Speech Representation Learning](https://mlsanity.com/paper/2211.11275/) (2022)
- [Code-Switching Text Generation and Injection in Mandarin-English ASR](https://mlsanity.com/paper/2303.10949/) (2023)
- [Speech-text based multi-modal training with bidirectional attention for improved speech recognition](https://mlsanity.com/paper/2211.00325/) (2022)
- [Temporal Order Preserved Optimal Transport-based Cross-modal Knowledge Transfer Learning for ASR](https://mlsanity.com/paper/2409.02239/) (2024)
- [CLASP: Contrastive Language-Speech Pretraining for Multilingual Multimodal Information Retrieval](https://mlsanity.com/paper/2412.13071/) (2024)
- [Cross-modal Knowledge Transfer Learning as Graph Matching Based on Optimal Transport for ASR](https://mlsanity.com/paper/2505.13079/) (2025)
- [PASG: A Closed-Loop Framework for Automated Geometric Primitive Extraction and Semantic Anchoring in Robotic Manipulation](https://mlsanity.com/paper/2508.05976/) (2025)
- [New Insights into Optimal Alignment of Acoustic and Linguistic Representations for Knowledge Transfer in ASR](https://mlsanity.com/paper/2509.05609/) (2025)
- [Optimal transport meets speech: a tutorial review](https://mlsanity.com/paper/2609.31787/) (2026)

## Abstract (arXiv)

The advances in attention-based encoder-decoder (AED) networks have brought great progress to end-to-end (E2E) automatic speech recognition (ASR). One way to further improve the performance of AED-based E2E ASR is to introduce an extra text encoder for leveraging extensive text data and thus capture more context-aware linguistic information. However, this approach brings a mismatch problem between the speech encoder and the text encoder due to the different units used for modeling. In this paper, we propose an embedding aligner and modality switch training to better align the speech and text latent spaces. The embedding aligner is a shared linear projection between text encoder and speech encoder trained by masked language modeling (MLM) loss and connectionist temporal classification (CTC), respectively. The modality switch training randomly swaps speech and text embeddings based on the forced alignment result to learn a joint representation space. Experimental results show that our proposed approach achieves a relative 14% to 19% word error rate (WER) reduction on Librispeech ASR task. We further verify its effectiveness on spoken language understanding (SLU), i.e., an absolute 2.5% to 2.8% F1 score improvement on SNIPS slot filling task.