English
Related papers

Related papers: Efficient acoustic feature transformation in misma…

200 papers

Spatial target speaker extraction isolates a desired speaker's voice in multi-speaker environments using spatial information, such as the direction of arrival (DoA). Although recent deep neural network (DNN)-based discriminative methods…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-23 Shrishti Saha Shetu , Emanuël A. P. Habets , Andreas Brendel

We present a frontend for improving robustness of automatic speech recognition (ASR), that jointly implements three modules within a single model: acoustic echo cancellation, speech enhancement, and speech separation. This is achieved by…

Audio and Speech Processing · Electrical Eng. & Systems 2021-11-22 Tom O'Malley , Arun Narayanan , Quan Wang , Alex Park , James Walker , Nathan Howard

Generative adversarial networks (GANs) and diffusion models have recently achieved state-of-the-art performance in audio super-resolution (ADSR), producing perceptually convincing wideband audio from narrowband inputs. However, existing…

Audio and Speech Processing · Electrical Eng. & Systems 2026-01-08 Mikhail Silaev , Konstantinos Drossos , Tuomas Virtanen

Generative Adversarial Networks (GANs) have shown great performance on super-resolution problems since they can generate more visually realistic images and video frames. However, these models often introduce side effects into the outputs,…

Image and Video Processing · Electrical Eng. & Systems 2024-03-19 Xijun Wang , Santiago López-Tapia , Alice Lucas , Xinyi Wu , Rafael Molina , Aggelos K. Katsaggelos

We propose a unified signal compression framework that uses a generative adversarial network (GAN) to compress heterogeneous signals. The compressed signal is represented as a latent vector and fed into a generator network that is trained…

Signal Processing · Electrical Eng. & Systems 2021-09-24 Bowen Liu , Changwoo Lee , Ang Cao , Hun-Seok Kim

Training a semi-supervised end-to-end speech recognition system using noisy student training has significantly improved performance. However, this approach requires a substantial amount of paired speech-text and unlabeled speech, which is…

Computation and Language · Computer Science 2024-08-01 Chia-Yu Li , Ngoc Thang Vu

This paper presents an audio visual automatic speech recognition (AV-ASR) system using a Transformer-based architecture. We particularly focus on the scene context provided by the visual information, to ground the ASR. We extract…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-01 Georgios Paraskevopoulos , Srinivas Parthasarathy , Aparna Khare , Shiva Sundaram

Advanced Generative Adversarial Networks (GANs) are remarkable in generating intelligible audio from a random latent vector. In this paper, we examine the task of recovering the latent vector of both synthesized and real audio. Previous…

Sound · Computer Science 2020-10-19 Andrew Keyes , Nicky Bayat , Vahid Reza Khazaie , Yalda Mohsenzadeh

Generative Adversarial Network (GAN) and its variants exhibit state-of-the-art performance in the class of generative models. To capture higher-dimensional distributions, the common learning procedure requires high computational complexity…

Machine Learning · Computer Science 2018-04-02 Xingwei Cao , Xuyang Zhao , Qibin Zhao

Generative adversarial network (GAN)-based vocoders have been intensively studied because they can synthesize high-fidelity audio waveforms faster than real-time. However, it has been reported that most GANs fail to obtain the optimal…

Sound · Computer Science 2024-03-26 Takashi Shibuya , Yuhta Takida , Yuki Mitsufuji

Recently, convolution-augmented transformer (Conformer) has achieved promising performance in automatic speech recognition (ASR) and time-domain speech enhancement (SE), as it can capture both local and global dependencies in the speech…

Sound · Computer Science 2024-05-07 Ruizhe Cao , Sherif Abdulatif , Bin Yang

We propose Relativistic Adversarial Feedback (RAF), a novel training objective for GAN vocoders that improves in-domain fidelity and generalization to unseen scenarios. Although modern GAN vocoders employ advanced architectures, their…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-13 Yongjoon Lee , Jung-Woo Choi

In the realm of automatic speech recognition (ASR), robustness in noisy environments remains a significant challenge. Recent ASR models, such as Whisper, have shown promise, but their efficacy in noisy conditions can be further enhanced.…

Sound · Computer Science 2024-06-28 Yehoshua Dissen , Shiry Yonash , Israel Cohen , Joseph Keshet

Conditional generative adversarial networks have shown exceptional generation performance over the past few years. However, they require large numbers of annotations. To address this problem, we propose a novel generative adversarial…

Machine Learning · Computer Science 2020-03-06 Ligong Han , Ruijiang Gao , Mun Kim , Xin Tao , Bo Liu , Dimitris Metaxas

Automatic speech recognition (ASR) is a crucial tool for linguists aiming to perform a variety of language documentation tasks. However, modern ASR systems use data-hungry transformer architectures, rendering them generally unusable for…

Computation and Language · Computer Science 2025-10-09 Massimo Daul , Alessio Tosolini , Claire Bowern

Bootstrapping speech recognition on limited data resources has been an area of active research for long. The recent transition to all-neural models and end-to-end (E2E) training brought along particular challenges as these models are known…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-21 Manuel Giollo , Deniz Gunceler , Yulan Liu , Daniel Willett

We previously proposed a method that allows for nonparallel voice conversion (VC) by using a variant of generative adversarial networks (GANs) called StarGAN. The main features of our method, called StarGAN-VC, are as follows: First, it…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-11 Hirokazu Kameoka , Takuhiro Kaneko , Kou Tanaka , Nobukatsu Hojo

Existing dominant methods for audio generation include Generative Adversarial Networks (GANs) and diffusion-based methods like Flow Matching. GANs suffer from slow convergence during training, while diffusion methods require multi-step…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-10 Zengwei Yao , Wei Kang , Han Zhu , Liyong Guo , Lingxuan Ye , Fangjun Kuang , Weiji Zhuang , Zhaoqing Li , Zhifeng Han , Long Lin , Daniel Povey

This paper presents a deep learning-based approach for the spatio-temporal reconstruction of sound fields using Generative Adversarial Networks (GANs). The method utilises a plane wave basis and learns the underlying statistical…

Audio and Speech Processing · Electrical Eng. & Systems 2023-08-02 Xenofon Karakonstantis , Efren Fernandez-Grande

We propose a novel autoencoding model called Pairwise Augmented GANs. We train a generator and an encoder jointly and in an adversarial manner. The generator network learns to sample realistic objects. In turn, the encoder network at the…

Machine Learning · Statistics 2018-10-12 Aibek Alanov , Max Kochurov , Daniil Yashkov , Dmitry Vetrov