Related papers: An Efficient GPU-based Implementation for Noise Ro…
Electroencephalogram (EEG)-based P300 speller brain-computer interfaces (BCIs) face three main challenges: low signal-to-noise ratio (SNR), poor generalization, and time-consuming calibration. We propose SpellerSSL, a framework that…
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…
Source separation can improve automatic speech recognition (ASR) under multi-party meeting scenarios by extracting single-speaker signals from overlapped speech. Despite the success of self-supervised learning models in single-channel…
The Voice Conversion Challenge 2020 is the third edition under its flagship that promotes intra-lingual semiparallel and cross-lingual voice conversion (VC). While the primary evaluation of the challenge submissions was done through…
Mobile robots increasingly operate alongside humans but are often out of sight, so that humans need to rely on the sounds of the robots to recognize their presence. For successful human-robot interaction (HRI), it is therefore crucial to…
Automatic speech recognition (ASR) has reached a level of accuracy in recent years, that even outperforms humans in transcribing speech to text. Nevertheless, all current ASR approaches show a certain weakness against ambient noise. To…
Self-supervised learning (SSL) has shown tremendous success in various speech-related downstream tasks, including Automatic Speech Recognition (ASR). The output embeddings of the SSL model are treated as powerful short-time representations…
Self-supervised learned models have been found to be very effective for certain speech tasks such as automatic speech recognition, speaker identification, keyword spotting and others. While the features are undeniably useful in speech…
Self-supervised learning (SSL) has transformed speech processing, yet its reliance on massive pre-training datasets remains a bottleneck. While robustness is often attributed to scale and diversity, the role of the data distribution is less…
The objective of this work is to localize sound sources that are visible in a video without using manual annotations. Our key technical contribution is to show that, by training the network to explicitly discriminate challenging image…
We propose to use neural networks for simultaneous detection and localization of multiple sound sources in human-robot interaction. In contrast to conventional signal processing techniques, neural network-based sound source localization…
Cardiac auscultation is an essential clinical skill, requiring excellent hearing to distinguish subtle differences in timing and pitch of heart sounds. However, diagnosing solely from these sounds is often challenging due to interference…
Spoofing-robust speaker verification (SASV) combines the tasks of speaker and spoof detection to authenticate speakers under adversarial settings. Many SASV systems rely on fusion of speaker and spoof cues at embedding, score or decision…
CAPTCHAs are widely used by websites to block bots and spam by presenting challenges that are easy for humans but difficult for automated programs to solve. To improve accessibility, audio CAPTCHAs are designed to complement visual ones.…
With the advances in deep learning, the performance of end-to-end (E2E) single-task models for speech and audio processing has been constantly improving. However, it is still challenging to build a general-purpose model with high…
The potential of deep learning in clinical speech processing is immense, yet the hurdles of limited and imbalanced clinical data samples loom large. This article addresses these challenges by showcasing the utilization of automatic speech…
Deep generative models have achieved significant progress in speech synthesis to date, while high-fidelity singing voice synthesis is still an open problem for its long continuous pronunciation, rich high-frequency parts, and strong…
This paper considers the problem of audio source separation where the goal is to isolate a target audio signal (say Alice's speech) from a mixture of multiple interfering signals (e.g., when many people are talking). This problem has gained…
It is known that adverse environments such as high reverberation and low signal-to-noise ratio (SNR) pose a great challenge to indoor sound source localization. To address this challenge, in this paper, we propose a sound source…
In this paper, we analyze the internal representations of a general-purpose audio self-supervised learning (SSL) model from a neuron-level perspective. Despite their strong empirical performance as feature extractors, the internal…