相关论文: iMetricGAN: Intelligibility Enhancement for Speech…

Generating qualitative responses has always been a challenge for human-computer dialogue systems. Existing dialogue systems generally derive from either retrieval-based or generative-based approaches, both of which have their own pros and…

In this paper we propose a novel defense approach against end-to-end adversarial attacks developed to fool advanced speech-to-text systems such as DeepSpeech and Lingvo. Unlike conventional defense approaches, the proposed approach does not…

As more and more data is collected in various settings across organizations, companies, and countries, there has been an increase in the demand of user privacy. Developing privacy preserving methods for data analytics is thus an important…

Distant supervision can effectively label data for relation extraction, but suffers from the noise labeling problem. Recent works mainly perform soft bag-level noise reduction strategies to find the relatively better samples in a sentence…

We propose a novel training algorithm for a multi-speaker neural text-to-speech (TTS) model based on multi-task adversarial training. A conventional generative adversarial network (GAN)-based training algorithm significantly improves the…

The intelligibility and quality of speech from a mobile phone or public announcement system are often affected by background noise in the listening environment. By pre-processing the speech signal it is possible to improve the speech…

Despite rapid advances in speech recognition, current models remain brittle to superficial perturbations to their inputs. Small amounts of noise can destroy the performance of an otherwise state-of-the-art model. To harden models against…

Intent classification is a fundamental task in the spoken language understanding field that has recently gained the attention of the scientific community, mainly because of the feasibility of approaching it with end-to-end neural models. In…

Speech enhancement is a crucial task for several applications. Among the most explored techniques are the Wiener filter and the LogMMSE, but approaches exploring deep learning adapted to this task, such as SEGAN, have presented relevant…

In recent years, large language models (LLM) have made significant progress in the task of generation error correction (GER) for automatic speech recognition (ASR) post-processing. However, in complex noisy environments, they still face…

Existing deep learning based speech enhancement mainly employ a data-driven approach, which leverage large amounts of data with a variety of noise types to achieve noise removal from noisy signal. However, the high dependence on the data…

Metric learning aims to learn a distance metric such that semantically similar instances are pulled together while dissimilar instances are pushed away. Many existing methods consider maximizing or at least constraining a distance margin in…

Voice conversion is a method that allows for the transformation of speaking style while maintaining the integrity of linguistic information. There are many researchers using deep generative models for voice conversion tasks. Generative…

Eliminating the negative effect of non-stationary environmental noise is a long-standing research topic for automatic speech recognition that stills remains an important challenge. Data-driven supervised approaches, including ones based on…

Spectral subtraction, widely used for its simplicity, has been employed to address the Robot Ego Speech Filtering (RESF) problem for detecting speech contents of human interruption from robot's single-channel microphone recordings when it…

Partial multi-label learning (PML), which tackles the problem of learning multi-label prediction models from instances with overcomplete noisy annotations, has recently started gaining attention from the research community. In this paper,…

Speech enhancement is designed to enhance the intelligibility and quality of speech across diverse noise conditions. Recently, diffusion model has gained lots of attention in speech enhancement area, achieving competitive results. Current…

I present IGAN (Inferent Generative Adversarial Networks), a neural architecture that learns both a generative and an inference model on a complex high dimensional data distribution, i.e. a bidirectional mapping between data samples and a…

Studies have shown that in noisy acoustic environments, providing binaural signals to the user of an assistive listening device may improve speech intelligibility and spatial awareness. This paper presents a binaural speech enhancement…

The estimation of speech intelligibility is still far from being a solved problem. Especially one aspect is problematic: most of the standard models require a clean reference signal in order to estimate intelligibility. This is an issue of…