Latent-Level Enhancement with Flow Matching for Robust Automatic Speech Recognition
By: Da-Hee Yang, Joon-Hyuk Chang
Potential Business Impact:
Makes voice assistants understand noisy speech better.
Noise-robust automatic speech recognition (ASR) has been commonly addressed by applying speech enhancement (SE) at the waveform level before recognition. However, speech-level enhancement does not always translate into consistent recognition improvements due to residual distortions and mismatches with the latent space of the ASR encoder. In this letter, we introduce a complementary strategy termed latent-level enhancement, where distorted representations are refined during ASR inference. Specifically, we propose a plug-and-play Flow Matching Refinement module (FM-Refiner) that operates on the output latents of a pretrained CTC-based ASR encoder. Trained to map imperfect latents-either directly from noisy inputs or from enhanced-but-imperfect speech-toward their clean counterparts, the FM-Refiner is applied only at inference, without fine-tuning ASR parameters. Experiments show that FM-Refiner consistently reduces word error rate, both when directly applied to noisy inputs and when combined with conventional SE front-ends. These results demonstrate that latent-level refinement via flow matching provides a lightweight and effective complement to existing SE approaches for robust ASR.
Similar Papers
Investigating training objective for flow matching-based speech enhancement
Sound
Cleans up noisy sounds for clearer talking.
Listening, Imagining \& Refining: A Heuristic Optimized ASR Correction Framework with LLMs
Audio and Speech Processing
Makes voice assistants understand words better.
Latent Flow Matching for Expressive Singing Voice Synthesis
Sound
Makes computer singing sound more human-like.