Related papers: Improved Speech Separation with Time-and-Frequency…

Self-supervised learning (SSL) has driven impressive advances in speech processing by adopting time-domain prediction objectives, while audio representation learning frameworks operate on time-frequency spectrograms. Models optimized for…

Embedding audio signal segments into vectors with fixed dimensionality is attractive because all following processing will be easier and more efficient, for example modeling, classifying or indexing. Audio Word2Vec previously proposed was…

Separating vocal elements from musical tracks is a longstanding challenge in audio signal processing. This study tackles the distinct separation of vocal components from musical spectrograms. We employ the Short Time Fourier Transform…

A three-stage approach is proposed for speaker counting and speech separation in noisy and reverberant environments. In the spatial feature extraction, a spatial coherence matrix (SCM) is computed using whitened relative transfer functions…

Embedding acoustic information into fixed length representations is of interest for a whole range of applications in speech and audio technology. Two novel unsupervised approaches to generate acoustic embeddings by modelling of acoustic…

Deep learning approaches have recently achieved impressive performance on both audio source separation and sound classification. Most audio source separation approaches focus only on separating sources belonging to a restricted domain of…

Recent deep learning approaches have achieved impressive performance on speech enhancement and separation tasks. However, these approaches have not been investigated for separating mixtures of arbitrary sounds of different types, a task we…

Multi-channel speech separation in dynamic environments is challenging as time-varying spatial and spectral features evolve at different temporal scales. Existing methods typically employ sequential architectures, forcing a single network…

Fake speech detection systems have become a necessity to combat against speech deepfakes. Current systems exhibit poor generalizability on out-of-domain speech samples due to lack to diverse training data. In this paper, we attempt to…

Unsupervised word segmentation in audio utterances is challenging as, in speech, there is typically no gap between words. In a preliminary experiment, we show that recent deep self-supervised features are very effective for word…

Capturing high-level structure in audio waveforms is challenging because a single second of audio spans tens of thousands of timesteps. While long-range dependencies are difficult to model directly in the time domain, we show that they can…

Relational thinking refers to the inherent ability of humans to form mental impressions about relations between sensory signals and prior knowledge, and subsequently incorporate them into their model of their world. Despite the crucial role…

This work proposes a multichannel speech separation method with narrow-band Conformer (named NBC). The network is trained to learn to automatically exploit narrow-band speech separation information, such as spatial vector clustering of…

Target speech separation refers to extracting a target speaker's voice from an overlapped audio of simultaneous talkers. Previously the use of visual modality for target speech separation has demonstrated great potentials. This work…

Deep attractor networks (DANs) perform speech separation with discriminative embeddings and speaker attractors. Compared with methods based on the permutation invariant training (PIT), DANs define a deep embedding space and deliver a more…

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,…

Recent advances in the design of neural network architectures, in particular those specialized in modeling sequences, have provided significant improvements in speech separation performance. In this work, we propose to use a bio-inspired…

We present a hybrid framework that leverages the trade-off between temporal and frequency precision in audio representations to improve the performance of speech enhancement task. We first show that conventional approaches using specific…

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…

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…