Where are the challenges in speaker diarization?

Sinclair, Mark; King, Simon

doi:10.1109/icassp.2013.6639170

Cited by 17 publications

(9 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They report a diarization error rate of 27.6%. While fully automated diarization procedures are appealing, diarization error rates can substantially be improved when introducing a learning step into the procedure, based on a small quantity of pure data (Sinclair and King, 2013). This relates to the idea of supervised machine learning.…”

Section: Speaker Diarization In Psychotherapy Researchmentioning

confidence: 99%

Supervised Speaker Diarization Using Random Forests: A Tool for Psychotherapy Process Research

Fürer¹,

Schenk²,

Röth

et al. 2020

Front. Psychol.

View full text Add to dashboard Cite

Speaker diarization is the practice of determining who speaks when in audio recordings. Psychotherapy research often relies on labor intensive manual diarization. Unsupervised methods are available but yield higher error rates. We present a method for supervised speaker diarization based on random forests. It can be considered a compromise between commonly used labor-intensive manual coding and fully automated procedures. The method is validated using the EMRAI synthetic speech corpus and is made publicly available. It yields low diarization error rates (M: 5.61%, STD: 2.19). Supervised speaker diarization is a promising method for psychotherapy research and similar fields.

show abstract

Section: Speaker Diarization In Psychotherapy Researchmentioning

confidence: 99%

Supervised Speaker Diarization Using Random Forests: A Tool for Psychotherapy Process Research

Fürer¹,

Schenk²,

Röth

et al. 2020

Front. Psychol.

View full text Add to dashboard Cite

show abstract

“…A proper stopping criterion in diarization is crucial as it affects the final diarization error rate (DER) [7]. Stopping the clustering process at the number of clusters less than the actual number of speakers is termed as over-clustering, and the opposite is referred to as under-clustering [1].…”

Section: B Stopping Criterion For Tpib-lda and Vartpib-lda Systemsmentioning

confidence: 99%

“…In general, an approach to unsupervised diarization of a conversational speech includes speech segment initialization followed by the bottom-up agglomerative clustering of the segments [1]. The major challenges in building an unsupervised speaker diarization system lie in the initialization of segments for clustering, to obtain speaker discriminative features, deciding on the number of speakers, and detection of overlapped speaker segments [1], [7]. A good segment initialization and speaker discriminative features help to improve the performance of the diarization system.…”

Section: Introductionmentioning

confidence: 99%

Novel Architectures for Unsupervised Information Bottleneck based Speaker Diarization of Meetings

Dawalatabad,

Madikeri,

Sekhar

et al. 2020

Preprint

View full text Add to dashboard Cite

Speaker diarization is an important problem that is topical, and is especially useful as a preprocessor for conversational speech related applications. The objective of this paper is two-fold: (i) segment initialization by uniformly distributing speaker information across the initial segments, and (ii) incorporating speaker discriminative features within the unsupervised diarization framework. In the first part of the work, a varying length segment initialization technique for Information Bottleneck (IB) based speaker diarization system using phoneme rate as the side information is proposed. This initialization distributes speaker information uniformly across the segments and provides a better starting point for IB based clustering. In the second part of the work, we present a Two-Pass Information Bottleneck (TPIB) based speaker diarization system that incorporates speaker discriminative features during the process of diarization. The TPIB based speaker diarization system has shown improvement over the baseline IB based system. During the first pass of the TPIB system, a coarse segmentation is performed using IB based clustering. The alignments obtained are used to generate speaker discriminative features using a shallow feed-forward neural network and linear discriminant analysis. The discriminative features obtained are used in the second pass to obtain the final speaker boundaries. In the final part of the paper, variable segment initialization is combined with the TPIB framework. This leverages the advantages of better segment initialization and speaker discriminative features that results in an additional improvement in performance. An evaluation on standard meeting datasets shows that a significant absolute improvement of 3.9% and 4.7% is obtained on the NIST and AMI datasets, respectively.

show abstract

“…To extract Malay speech from the found data, we applied a speaker diarisation technique (Sinclair and King, 2013) as it is able to identify speaker homogenous regions throughout the speech data. First, feature extraction is performed on the data using HTK with the standard ASR features.…”

Section: Diarisationmentioning

confidence: 99%

Combining Lightly-supervised Learning and User Feedback to Construct Andimprove a Statistical Parametric Speech Synthesizer for Malay

Yong¹,

Watts²,

King

2015

RJASET

Self Cite

View full text Add to dashboard Cite

Abstract:In this study, we aim to reduce the human effort in preparing training data for synthesizing human speech and improve the quality of synthetic speech. In spite of the learning-from-data used to train the statistical models, the construction of a statistical parametric speech synthesizer involves substantial human effort, especially when using imperfect data or working on a new language. Here, we use lightly-supervised methods for preparing the data and constructing the text-processing front end. This initial system is then iteratively improved using active learning in which feedback from users is used to disambiguate the pronunciation system in our chosen language, Malay. The data are prepared using speaker diarisation and lightly-supervised text-speech alignment. In the front end, graphemebased units are used. The active learning used small amounts of feedback from a listener to train a classifier. We report evaluations of two systems built from high-quality studio data and lower-quality `found' data respectively and show that the intelligibility of each can be improved using active learning.

show abstract

Where are the challenges in speaker diarization?

Cited by 17 publications

References 10 publications

Supervised Speaker Diarization Using Random Forests: A Tool for Psychotherapy Process Research

Supervised Speaker Diarization Using Random Forests: A Tool for Psychotherapy Process Research

Novel Architectures for Unsupervised Information Bottleneck based Speaker Diarization of Meetings

Combining Lightly-supervised Learning and User Feedback to Construct Andimprove a Statistical Parametric Speech Synthesizer for Malay

Contact Info

Product

Resources

About