paper-with-me

홈 › Papers

Cycle-Consistent GAN Front-End to Improve ASR Robustness to Perturbed Speech

2018-10-22 · NIPS Workshop IRASL 2018 · Anonymous

Automatic Speech Recognition (ASR) systems, which perform well on regular speech, are found to be vulnerable to adversarial examples generated by small perturbations in the audio signal. Even naturally introduced perturbations in audio signal, caused by emotional and physical states of the speaker, can significantly degrade ASR performance. In this paper, we propose a front-end based on Cycle-Consistent Generative Adversarial Network (CycleGAN) to reduce the perturbations, and hence add robustness to ASR performance. CycleGAN is trained using non-parallel examples of perturbed and normal speech. Experiments on spontaneously generated laughter-speech and creaky voice datasets tested with Google cloud ASR show absolute improvements in WER of 14.9% and 11%, respectively, on speech converted using the CycleGAN based front-end as compared to the original perturbed speech.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Generative Adversarial Networkspeech-recognitionSpeech Recognition

Similar Papers 제목 키워드 기반

A Cycle-GAN Approach to Model Natural Perturbations in Speech for ASR Applications

2019-12-18 · Sri Harsha Dumpala, Imran Sheikh, Rupayan Chakraborty, Sunil Kumar Kopparapu

Naturally introduced perturbations in audio signal, caused by emotional and physical states of the speaker, can significantly degrade the performance of Automatic Speech Recognition (ASR) systems. In this paper, we propo…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Generative Adversarial Networkspeech-recognition+1

A Jagged Frontier: Evaluating Robustness of Code Agents to Semantics-Preserving Transformations

2026-08-18 · Hasan Najib Mahmud, Shreya Gupta, Isha Chaudhary, Nathaniel Enis 외 arxiv

AI code agents are increasingly deployed to resolve real software issues, yet their reliability under superficial code variations remains poorly understood. We evaluate whether coding agents that repair repository-level …

Wiggling Weights to Improve the Robustness of Classifiers

2021-11-18 · Sadaf Gulshad, Ivan Sosnovik, Arnold Smeulders

Robustness against unwanted perturbations is an important aspect of deploying neural network classifiers in the real world. Common natural perturbations include noise, saturation, occlusion, viewpoint changes, and blur d…

Safer Policy Compliance with Dynamic Epistemic Fallback

2026-01-30 · Joseph Marvin Imperial, Harish Tayyar Madabushi arxiv

Humans develop a series of cognitive defenses, known as epistemic vigilance, to combat risks of deception and misinformation from everyday interactions. Developing safeguards for LLMs inspired by this mechanism might be …

Assessing LLMs for Zero-shot Abstractive Summarization Through the Lens of Relevance Paraphrasing

2024-06-06 · Hadi Askari, Anshuman Chhabra, Muhao Chen, Prasant Mohapatra

Large Language Models (LLMs) have achieved state-of-the-art performance at zero-shot generation of abstractive summaries for given articles. However, little is known about the robustness of such a process of zero-shot su…

Abstractive Text SummarizationArticles