Related papers: Jointly Detecting and Separating Singing Voice: A …
This paper summarizes some recent advances on a set of tasks related to the processing of singing using state-of-the-art deep learning techniques. We discuss their achievements in terms of accuracy and sound quality, and the current…
While log-amplitude mel-spectrogram has widely been used as the feature representation for processing speech based on deep learning, the effectiveness of another aspect of speech spectrum, i.e., phase information, was shown recently for…
Singing voice beat tracking is a challenging task, due to the lack of musical accompaniment that often contains robust rhythmic and harmonic patterns, something most existing beat tracking systems utilize and can be essential for estimating…
Audio source separation aims to separate a mixture into target sources. Previous audio source separation systems usually conduct one-step inference, which does not fully explore the separation ability of models. In this work, we reveal that…
Although automatic pathological speech detection approaches show promising results when clean recordings are available, they are vulnerable to additive noise. Recently it has been shown that databases commonly used to develop and evaluate…
Fully-supervised models for source separation are trained on parallel mixture-source data and are currently state-of-the-art. However, such parallel data is often difficult to obtain, and it is cumbersome to adapt trained models to mixtures…
Speech separation aims to separate individual voice from an audio mixture of multiple simultaneous talkers. Although audio-only approaches achieve satisfactory performance, they build on a strategy to handle the predefined conditions,…
Despite the progress in self-supervised learning (SSL) for speech and music, existing models treat these domains separately, limiting their capacity for unified audio understanding. A unified model is desirable for applications that require…
In recent years, deep neural networks (DNNs) based approaches have achieved the start-of-the-art performance for music source separation (MSS). Although previous methods have addressed the large receptive field modeling using various…
Self-supervised learning approaches have lately achieved great success on a broad spectrum of machine learning problems. In the field of speech processing, one of the most successful recent self-supervised models is wav2vec 2.0. In this…
Traditional speech separation and speaker diarization approaches rely on prior knowledge of target speakers or a predetermined number of participants in audio signals. To address these limitations, recent advances focus on developing…
Lately there have been novel developments in deep learning towards solving the cocktail party problem. Initial results are very promising and allow for more research in the domain. One technique that has not yet been explored in the neural…
Multi-source localization is an important and challenging technique for multi-talker conversation analysis. This paper proposes a novel supervised learning method using deep neural networks to estimate the direction of arrival (DOA) of all…
Dialects introduce syntactic and lexical variations in language that occur in regional or social groups. Most NLP methods are not sensitive to such variations. This may lead to unfair behavior of the methods, conveying negative bias towards…
Professional vocalists modulate their voice timbre or pitch to make their vocal performance more expressive. Such fluctuations are called singing techniques. Automatic detection of singing techniques from audio tracks can be beneficial to…
Accents, as variations from standard pronunciation, pose significant challenges for speech recognition systems. Although joint automatic speech recognition (ASR) and accent recognition (AR) training has been proven effective in handling…
Data-based and learning-based sound source localization (SSL) has shown promising results in challenging conditions, and is commonly set as a classification or a regression problem. Regression-based approaches have certain advantages over…
We introduce UNMIXX, a novel framework for multiple singing voices separation (MSVS). While related to speech separation, MSVS faces unique challenges: data scarcity and the highly correlated nature of singing voices mixture. To address…
Speech separation with several speakers is a challenging task because of the non-stationarity of the speech and the strong signal similarity between interferent sources. Current state-of-the-art solutions can separate well the different…
We present a novel deep neural model for text detection in document images. For robust text detection in noisy scanned documents, the advantages of multi-task learning are adopted by adding an auxiliary task of text enhancement. Namely, our…