Related papers: End-to-End Audio Strikes Back: Boosting Augmentati…

This survey overviews various meta-learning approaches used in audio and speech processing scenarios. Meta-learning is used where model performance needs to be maximized with minimum annotated samples, making it suitable for low-sample…

One of the most important parts of an end-to-end speaker verification system is the speaker embedding generation. In our previous paper, we reported that shortcut connections-based multi-layer aggregation improves the representational power…

Conversational context information, higher-level knowledge that spans across sentences, can help to recognize a long conversation. However, existing speech recognition models are typically built at a sentence level, and thus it may not…

We propose an end-to-end model based on convolutional and recurrent neural networks for speech enhancement. Our model is purely data-driven and does not make any assumptions about the type or the stationarity of the noise. In contrast to…

Large-scale coreference resolution presents a significant challenge in natural language processing, necessitating a balance between efficiency and accuracy. In response to this challenge, we introduce an End-to-End Neural Coreference…

In the context of music production, distortion effects are mainly used for aesthetic reasons and are usually applied to electric musical instruments. Most existing methods for nonlinear modeling are often either simplified or optimized to a…

Target confusion, defined as occasional switching to non-target speakers, poses a key challenge for end-to-end speaker extraction (E2E-SE) systems. We argue that this problem is largely caused by the lack of generalizability and…

With the proliferation of video platforms on the internet, recording musical performances by mobile devices has become commonplace. However, these recordings often suffer from degradation such as noise and reverberation, which negatively…

Visual speech recognition remains an open research problem where different challenges must be considered by dispensing with the auditory sense, such as visual ambiguities, the inter-personal variability among speakers, and the complex…

We present Synthio, a novel approach for augmenting small-scale audio classification datasets with synthetic data. Our goal is to improve audio classification accuracy with limited labeled data. Traditional data augmentation techniques,…

In this paper we present a data-driven, integrated approach to speaker verification, which maps a test utterance and a few reference utterances directly to a single score for verification and jointly optimizes the system's components using…

Artificial speech synthesis has made a great leap in terms of naturalness as recent Text-to-Speech (TTS) systems are capable of producing speech with similar quality to human recordings. However, not all speaking styles are easy to model:…

Acoustics-to-word models are end-to-end speech recognizers that use words as targets without relying on pronunciation dictionaries or graphemes. These models are notoriously difficult to train due to the lack of linguistic knowledge. It is…

On-device end-to-end speech recognition poses a high requirement on model efficiency. Most prior works improve the efficiency by reducing model sizes. We propose to reduce the complexity of model architectures in addition to model sizes.…

Echo and noise suppression is an integral part of a full-duplex communication system. Many recent acoustic echo cancellation (AEC) systems rely on a separate adaptive filtering module for linear echo suppression and a neural module for…

Mastering is an essential step in music production, but it is also a challenging task that has to go through the hands of experienced audio engineers, where they adjust tone, space, and volume of a song. Remastering follows the same…

Small adversarial perturbations of input data are able to drastically change performance of machine learning systems, thereby challenging the validity of such systems. We present the very first end-to-end adversarial attacks on a music…

With the similarity between music and speech synthesis from symbolic input and the rapid development of text-to-speech (TTS) techniques, it is worthwhile to explore ways to improve the MIDI-to-audio performance by borrowing from TTS…

Audio-visual speech enhancement (AV-SE) methods utilize auxiliary visual cues to enhance speakers' voices. Therefore, technically they should be able to outperform the audio-only speech enhancement (SE) methods. However, there are few works…

We consider the problem of detecting, isolating and classifying elephant calls in continuously recorded audio. Such automatic call characterisation can assist conservation efforts and inform environmental management strategies. In contrast…