相关论文: On the calibration of powerset speaker diarization…

Speaker diarization systems segment a conversation recording based on the speakers' identity. Such systems can misclassify the speaker of a portion of audio due to a variety of factors, such as speech pattern variation, background noise,…

Since its introduction in 2019, the whole end-to-end neural diarization (EEND) line of work has been addressing speaker diarization as a frame-wise multi-label classification problem with permutation-invariant training. Despite EEND showing…

End-to-End Neural Diarization (EEND) systems produce frame-level probabilistic speaker activity estimates, yet since evaluation focuses primarily on Diarization Error Rate (DER), the reliability and calibration of these confidence scores…

For speech classification tasks, deep learning models often achieve high accuracy but exhibit shortcomings in calibration, manifesting as classifiers exhibiting overconfidence. The significance of calibration lies in its critical role in…

End-to-end speaker diarization enables accurate overlap-aware diarization by jointly estimating multiple speakers' speech activities in parallel. This approach is data-hungry, requiring a large amount of labeled conversational data, which…

Neural speaker diarization is widely used for overlap-aware speaker diarization, but it requires large multi-speaker datasets for training. To meet this data requirement, large datasets are often constructed by combining multiple corpora,…

Speaker diarization is a task to label audio or video recordings with classes that correspond to speaker identity, or in short, a task to identify "who spoke when". In the early years, speaker diarization algorithms were developed for…

Overlapping speech diarization is always treated as a multi-label classification problem. In this paper, we reformulate this task as a single-label prediction problem by encoding the multi-speaker labels with power set. Specifically, we…

We present an end-to-end deep network model that performs meeting diarization from single-channel audio recordings. End-to-end diarization models have the advantage of handling speaker overlap and enabling straightforward handling of…

Recently, hybrid systems of clustering and neural diarization models have been successfully applied in multi-party meeting analysis. However, current models always treat overlapped speaker diarization as a multi-label classification…

Over the last few years, deep learning has grown in popularity for speaker verification, identification, and diarization. Inarguably, a significant part of this success is due to the demonstrated effectiveness of their speaker…

Speaker diarization is a task to label an audio or video recording with the identity of the speaker at each given time stamp. In this work, we propose a novel machine learning framework to conduct real-time multi-speaker diarization and…

In large-scale domain classification, an utterance can be handled by multiple domains with overlapped capabilities. However, only a limited number of ground-truth domains are provided for each training utterance in practice while knowing as…

Overlapping speech diarization has been traditionally treated as a multi-label classification problem. In this paper, we reformulate this task as a single-label prediction problem by encoding multiple binary labels into a single label with…

Pre-trained Transformers are now ubiquitous in natural language processing, but despite their high end-task performance, little is known empirically about whether they are calibrated. Specifically, do these models' posterior probabilities…

Safety-critical applications require machine learning models that output accurate and calibrated probabilities. While uncalibrated deep networks are known to make over-confident predictions, it is unclear how model confidence is impacted by…

Speaker diarization relies on the assumption that speech segments corresponding to a particular speaker are concentrated in a specific region of the speaker space; a region which represents that speaker's identity. These identities are not…

In this paper, we address the problem of speaker verification in conditions unseen or unknown during development. A standard method for speaker verification consists of extracting speaker embeddings with a deep neural network and processing…

Recent studies on the memorization effects of deep neural networks on noisy labels show that the networks first fit the correctly-labeled training samples before memorizing the mislabeled samples. Motivated by this early-learning…

Deep speaker embeddings have become the leading method for encoding speaker identity in speaker recognition tasks. The embedding space should ideally capture the variations between all possible speakers, encoding the multiple acoustic…