Unpaired Speech Enhancement By Acoustic And Adversarial Supervision For Speech Recognition

Abstract

Many speech enhancement methods try to learn the relationship between noisy and clean speech, obtained using an acoustic room simulator. We point out several limitations of enhancement methods relying on clean speech targets; the goal of this work is proposing an alternative learning algorithm, called acoustic and adversarial supervision (AAS). AAS makes the enhanced output both maximizing the likelihood of transcription on the pre-trained acoustic model and having general characteristics of clean speech, which improve generalization on unseen noisy speeches. We employ the connectionist temporal classification and the unpaired conditional boundary equilibrium generative adversarial network as the loss function of AAS. AAS is tested on two datasets including additive noise without and with reverberation, Librispeech + DEMAND and CHiME-4. By visualizing the enhanced speech with different loss combinations, we demonstrate the role of each supervision. AAS achieves a lower word error rate

Stats

• citations22
• S2 citations—
• github stars0
• HF likes0
• heat score10.21
• arxiv keykim2018unpaired

Related papers

• Boosting Noise Robustness Of Acoustic Model Via Deep Adversarial Training (2018)9.23
• Audio Adversarial Examples For Robust Hybrid Ctc/attention Speech Recognition (2020)3.58
• Joint Training Of Speech Enhancement And Self-supervised Model For Noise-robust ASR (2022)0.00
• Superm2m: Supervised And Mixture-to-mixture Co-learning For Speech Enhancement And Noise-robust ASR (2024)5.24
• Speaker Reinforcement Using Target Source Extraction For Robust Automatic Speech Recognition (2022)7.50
• Auxiliary Interference Speaker Loss For Target-speaker Speech Recognition (2019)9.76
• Adversarial Joint Training With Self-attention Mechanism For Robust End-to-end Speech Recognition (2021)0.00
• Channel-aware Domain-adaptive Generative Adversarial Network For Robust Speech Recognition (2024)4.52