相关论文: Low Latency Time Domain Multichannel Speech and Mu…

Recently, frequency domain all-neural beamforming methods have achieved remarkable progress for multichannel speech separation. In parallel, the integration of time domain network structure and beamforming also gains significant attention.…

Given a time series of multicomponent measurements x(t), the usual objective of nonlinear blind source separation (BSS) is to find a "source" time series s(t), comprised of statistically independent combinations of the measured components.…

Discriminative segmental models offer a way to incorporate flexible feature functions into speech recognition. However, their appeal has been limited by their computational requirements, due to the large number of possible segments to…

Cinematic audio source separation is a relatively new subtask of audio source separation, with the aim of extracting the dialogue, music, and effects stems from their mixture. In this work, we developed a model generalizing the Bandsplit…

In this paper, we introduce a simple method that can separate arbitrary musical instruments from an audio mixture. Given an unaligned MIDI transcription for a target instrument from an input mixture, we synthesize new mixtures from the midi…

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…

Latent Diffusion Models (LDMs) enable high-quality image synthesis while avoiding excessive compute demands by training a diffusion model in a compressed lower-dimensional latent space. Here, we apply the LDM paradigm to high-resolution…

The human brain distinguishes speech sounds by mapping acoustic signals into a latent perceptual space. This space can be estimated via multidimensional scaling (MDS), preserving the similarity structure in lower dimensions. However,…

In this work, a novel deep neural network, designed to enhance the efficiency and effectiveness of unsupervised sound anomaly detection, is presented. The proposed model exploits an attention module and separable convolutions to identify…

Neural compression offers a domain-agnostic approach to creating codecs for lossy or lossless compression via deep generative models. For sequence compression, however, most deep sequence models have costs that scale with the sequence…

Localizing a moving sound source in the real world involves determining its direction-of-arrival (DOA) and distance relative to a microphone. Advancements in DOA estimation have been facilitated by data-driven methods optimized with large…

On-device directional hearing requires audio source separation from a given direction while achieving stringent human-imperceptible latency requirements. While neural nets can achieve significantly better performance than traditional…

General audio source separation is a key capability for multimodal AI systems that can perceive and reason about sound. Despite substantial progress in recent years, existing separation models are either domain-specific, designed for fixed…

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…

The task of manipulating the level and/or effects of individual instruments to recompose a mixture of recordings, or remixing, is common across a variety of applications such as music production, audio-visual post-production, podcasts, and…

Continuous speech separation for meeting pre-processing has recently become a focused research topic. Compared to the data in utterance-level speech separation, the meeting-style audio stream lasts longer, has an uncertain number of…

Speech separation has been very successful with deep learning techniques. Substantial effort has been reported based on approaches over spectrogram, which is well known as the standard time-and-frequency cross-domain representation for…

Singing voice separation attempts to separate the vocal and instrumental parts of a music recording, which is a fundamental problem in music information retrieval. Recent work on singing voice separation has shown that the low-rank…

Anomaly detection has many important applications, such as monitoring industrial equipment. Despite recent advances in anomaly detection with deep-learning methods, it is unclear how existing solutions would perform under…

This study introduces a biologically-inspired model designed to examine the role of coincidence detection cells in speech segregation tasks. The model consists of three stages: a time-domain cochlear model that generates instantaneous rates…