相关论文: Graph-PIT: Generalized permutation invariant train…

We propose an approach for simultaneous diarization and separation of meeting data. It consists of a complex Angular Central Gaussian Mixture Model (cACGMM) for speech source separation, and a von-Mises-Fisher Mixture Model (VMFMM) for…

Detecting and segmenting dysfluencies is crucial for effective speech therapy and real-time feedback. However, most methods only classify dysfluencies at the utterance level. We introduce StutterCut, a semi-supervised framework that…

Existing multi-channel continuous speech separation (CSS) models are heavily dependent on supervised data - either simulated data which causes data mismatch between the training and real-data testing, or the real transcribed overlapping…

Continuous speech separation (CSS) is a recently proposed framework which aims at separating each speaker from an input mixture signal in a streaming fashion. Hereafter we perform an evaluation study on practical design considerations for a…

Speaker-independent speech separation has achieved remarkable performance in recent years with the development of deep neural network (DNN). Various network architectures, from traditional convolutional neural network (CNN) and recurrent…

Graph separation is a central tool in parameterized algorithm design, and important separators are among its most successful ingredients. They yield small, structured families of separators that can be enumerated efficiently, and underlie…

Transformer has shown advanced performance in speech separation, benefiting from its ability to capture global features. However, capturing local features and channel information of audio sequences in speech separation is equally important.…

The cocktail party problem comprises the challenging task of understanding a speech signal in a complex acoustic environment, where multiple speakers and background noise signals simultaneously interfere with the speech signal of interest.…

Dialogue topic segmentation is critical in several dialogue modeling problems. However, popular unsupervised approaches only exploit surface features in assessing topical coherence among utterances. In this work, we address this limitation…

Speech separation has been studied in time domain because of lower latency and higher performance compared to time-frequency domain. The masking-based method has been mostly used in time domain, and the other common method (mapping-based)…

The vast majority of speech separation methods assume that the number of speakers is known in advance, hence they are specific to the number of speakers. By contrast, a more realistic and challenging task is to separate a mixture in which…

Graph self-supervised learning typically relies on large-scale unlabeled datasets, heavily inflating computational costs. However, empirical evidence suggests that these datasets contain substantial redundancy-our analysis reveals that…

Since the first speech recognition systems were built more than 30 years ago, improvement in voice technology has enabled applications such as smart assistants and automated customer support. However, conversation intelligence of the future…

Automatic meeting analysis comprises the tasks of speaker counting, speaker diarization, and the separation of overlapped speech, followed by automatic speech recognition. This all has to be carried out on arbitrarily long sessions and,…

Many approaches can derive information about a single speaker's identity from the speech by learning to recognize consistent characteristics of acoustic parameters. However, it is challenging to determine identity information when there are…

Speech separation is a fundamental task in audio processing, typically addressed with fully supervised systems trained on paired mixtures. While effective, such systems typically rely on synthetic data pipelines, which may not reflect…

Permutation-invariant training (PIT) is a dominant approach for addressing the permutation ambiguity problem in talker-independent speaker separation. Leveraging spatial information afforded by microphone arrays, we propose a new training…

Topic segmentation of meetings is the task of dividing multi-person meeting transcripts into topic blocks. Supervised approaches to the problem have proven intractable due to the difficulties in collecting and accurately annotating large…

Guided source separation (GSS) is a type of target-speaker extraction method that relies on pre-computed speaker activities and blind source separation to perform front-end enhancement of overlapped speech signals. It was first proposed…

We propose multi-microphone complex spectral mapping, a simple way of applying deep learning for time-varying non-linear beamforming, for speaker separation in reverberant conditions. We aim at both speaker separation and dereverberation.…