Related papers: ConcateNet: Dialogue Separation Using Local And Gl…

Achieving robust speech separation for overlapping speakers in various acoustic environments with noise and reverberation remains an open challenge. Although existing datasets are available to train separators for specific scenarios, they…

Deep dilated temporal convolutional networks (TCN) have been proved to be very effective in sequence modeling. In this paper we propose several improvements of TCN for end-to-end approach to monaural speech separation, which consists of 1)…

The demand of applying semantic segmentation model on mobile devices has been increasing rapidly. Current state-of-the-art networks have enormous amount of parameters hence unsuitable for mobile devices, while other small memory footprint…

Goal-oriented dialogue systems are now being widely adopted in industry where it is of key importance to maintain a rapid prototyping cycle for new products and domains. Data-driven dialogue system development has to be adapted to meet this…

We propose Universal target audio Separation (UniSep), addressing the separation task on arbitrary mixtures of different types of audio. Distinguished from previous studies, UniSep is performed on unlimited source domains and unlimited…

This paper addresses the challenge of speaker separation, which remains an active research topic despite the promising results achieved in recent years. These results, however, often degrade in real recording conditions due to the presence…

Recent trend towards increasing large machine learning models require both training and inference tasks to be distributed. Considering the huge cost of training these models, it is imperative to unlock optimizations in computation and…

We present a unified model capable of simultaneously grounding both spoken language and non-speech sounds within a visual scene, addressing key limitations in current audio-visual grounding models. Existing approaches are typically limited…

Dataset Condensation is a newly emerging technique aiming at learning a tiny dataset that captures the rich information encoded in the original dataset. As the size of datasets contemporary machine learning models rely on becomes…

Target speech extraction remains difficult for compact devices because monaural neural models lack spatial evidence and classical beamformers lose resolving power when the microphone aperture is only a few centimetres. We present IsoNet, a…

Automatic speech recognition (ASR) in multimedia content is one of the promising applications, but speech data in this kind of content are frequently mixed with background music, which is harmful for the performance of ASR. In this study,…

This work proposes a multichannel narrow-band speech separation network. In the short-time Fourier transform (STFT) domain, the proposed network processes each frequency independently, and all frequencies use a shared network. For each…

This paper addresses the challenge of audio-visual single-microphone speech separation and enhancement in the presence of real-world environmental noise. Our approach is based on generative inverse sampling, where we model clean speech and…

Existing datasets for audio understanding primarily focus on single-turn interactions (i.e. audio captioning, audio question answering) for describing audio in natural language, thus limiting understanding audio via interactive dialogue. To…

In recent years, many deep learning techniques for single-channel sound source separation have been proposed using recurrent, convolutional and transformer networks. When multiple microphones are available, spatial diversity between…

Speech separation is very important in real-world applications such as human-machine interaction, hearing aids devices, and automatic meeting transcription. In recent years, a significant improvement occurred towards the solution based on…

Audio classification is the task of identifying the sound categories that are associated with a given audio signal. This paper presents an investigation on large-scale audio classification based on the recently released AudioSet database.…

We present a technique for adding global context to deep convolutional networks for semantic segmentation. The approach is simple, using the average feature for a layer to augment the features at each location. In addition, we study several…

Separating a song into vocal and accompaniment components is an active research topic, and recent years witnessed an increased performance from supervised training using deep learning techniques. We propose to apply the visual information…

Identifying the topic (domain) of each user's utterance in open-domain conversational systems is a crucial step for all subsequent language understanding and response tasks. In particular, for complex domains, an utterance is often routed…