Speaker Diarization based on Bayesian HMM with Eigenvoice Priors

Díez, Mireia; Burget, Lukáš; Matějka, Pavel

doi:10.21437/odyssey.2018-21

Cited by 55 publications

(49 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Depicted in Figure 4, our proposed approach relies heavily on the i-vector-based Variational Bayes Hidden Markov Model (VB-HMM) introduced for speaker diarization in [14], and applied to resegmentation in [15]. We use the output of the speaker diarization baseline as the binary initialization of the per-frame speaker posterior matrix: Q st is initialized to 1 if speaker s is responsible for the speech at the voiced frame t, and 0 otherwise.…”

Section: Principlementioning

confidence: 99%

See 1 more Smart Citation

Overlap-Aware Diarization: Resegmentation Using Neural End-to-End Overlapped Speech Detection

Bullock

Bredin

García-Perera

2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

We address the problem of effectively handling overlapping speech in a diarization system. First, we detail a neural Long Short-Term Memory-based architecture for overlap detection. Secondly, detected overlap regions are exploited in conjunction with a frame-level speaker posterior matrix to make two-speaker assignments for overlapped frames in the resegmentation step. The overlap detection module achieves state-of-the-art performance on the AMI, DIHARD, and ETAPE corpora. We apply overlap-aware resegmentation on AMI, resulting in a 20% relative DER reduction over the baseline system. While this approach is by no means an endall solution to overlap-aware diarization, it reveals promising directions for handling overlap.

show abstract

Section: Principlementioning

confidence: 99%

“…We first perform resegmentation using [14]'s VB-HMM module. Feature vectors for the module are length-60 MFCCs with deltas and double deltas, extracted in 10ms steps with a 25ms window.…”

Section: Implementation Detailsmentioning

confidence: 99%

Overlap-Aware Diarization: Resegmentation Using Neural End-to-End Overlapped Speech Detection

Bullock

Bredin

García-Perera

2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

show abstract

“…At a high level, the system performs diarization by dividing each recording into short overlapping segments, extracting x-vectors [33,34], scoring with probabilistic linear discriminant analysis (PLDA) [35], and clustering using agglomerative hierarchical clustering (AHC) [36]. In contrast to the original JHU system, we omit the Variational Bayes resegmentation step [37]. The trained models are distributed through GitHub 8 .…”

Section: Diarizationmentioning

confidence: 99%

The Second DIHARD Diarization Challenge: Dataset, Task, and Baselines

Ryant¹,

Church²,

Cieri³

et al. 2019

Interspeech 2019

140

117

View full text Add to dashboard Cite

This paper introduces the second DIHARD challenge, the second in a series of speaker diarization challenges intended to improve the robustness of diarization systems to variation in recording equipment, noise conditions, and conversational domain. The challenge comprises four tracks evaluating diarization performance under two input conditions (single channel vs. multi-channel) and two segmentation conditions (diarization from a reference speech segmentation vs. diarization from scratch). In order to prevent participants from overtuning to a particular combination of recording conditions and conversational domain, recordings are drawn from a variety of sources ranging from read audiobooks to meeting speech, to child language acquisition recordings, to dinner parties, to web video. We describe the task and metrics, challenge design, datasets, and baseline systems for speech enhancement, speech activity detection, and diarization. 1 See, for instance, the release of IBM's diarization API in 2017. The feature worked well for simple cases, but when run by users on real inputs, the performance was found to be lacking, especially for overlaps, back-channels, and short turns.

show abstract

“…In most of the approaches, this stage is still based on the Agglomerative Hierachical Clustering (AHC) [10] in combination with Probabilistic Linear Discriminat Analysis (PLDA) scoring [11]. Recently, spectral clustering [12] [13], and variatioanl bayesian clustering [14,15] have been introduced, showing promising result. Also, alternatives to the PLDA scoring have been introduced using neural networks that learn how to score two speech segments [16], using siamese networks [17] or Bi-LSTMs [18].…”

Section: Introductionmentioning

confidence: 99%

Supervised Online Diarization with Sample Mean Loss for Multi-Domain Data

Fini

Brutti

2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Recently, a fully supervised speaker diarization approach was proposed (UIS-RNN) which models speakers using multiple instances of a parameter-sharing recurrent neural network. In this paper we propose qualitative modifications to the model that significantly improve the learning efficiency and the overall diarization performance. In particular, we introduce a novel loss function, we called Sample Mean Loss and we present a better modelling of the speaker turn behaviour, by devising an analytical expression to compute the probability of a new speaker joining the conversation. In addition, we demonstrate that our model can be trained on fixed-length speech segments, removing the need for speaker change information in inference. Using x-vectors as input features, we evaluate our proposed approach on the multi-domain dataset employed in the DIHARD II challenge: our online method improves with respect to the original UIS-RNN and achieves similar performance to an offline agglomerative clustering baseline using PLDA scoring.

show abstract

Speaker Diarization based on Bayesian HMM with Eigenvoice Priors

Cited by 55 publications

References 0 publications

Overlap-Aware Diarization: Resegmentation Using Neural End-to-End Overlapped Speech Detection

Overlap-Aware Diarization: Resegmentation Using Neural End-to-End Overlapped Speech Detection

The Second DIHARD Diarization Challenge: Dataset, Task, and Baselines

Supervised Online Diarization with Sample Mean Loss for Multi-Domain Data

Contact Info

Product

Resources

About