Dissertation•
Using Deep Neural Networks for Speaker Diarisation
16 Dec 2016-
TL;DR: A method involving a pretrained Speaker Separation Deep Neural Network (ssDNN) is investigated which performs speaker clustering and speaker segmentation using DNNs successfully for meeting data and with mixed results for broadcast media.
Abstract: Speaker diarisation answers the question “who spoke when?” in an audio recording. The input may vary, but a system is required to output speaker labelled segments in time. Typical stages are Speech Activity Detection (SAD), speaker segmentation and speaker clustering. Early research focussed on Conversational Telephone Speech (CTS) and Broadcast News (BN) domains before the direction shifted to meetings and, more recently, broadcast media. The British Broadcasting Corporation (BBC) supplied data through the Multi-Genre Broadcast (MGB) Challenge in 2015 which showed the difficulties speaker diarisation systems have on broadcast media data.
Diarisation is typically an unsupervised task which does not use auxiliary data or information to enhance a system. However, methods which do involve supplementary data have shown promise. Five semi-supervised methods are investigated which use a combination of inputs: different channel types and transcripts. The methods involve Deep Neural Networks (DNNs) for SAD, DNNs trained for channel detection, transcript alignment, and combinations of these approaches. However, the methods are only applicable when datasets contain the required inputs. Therefore, a method involving a pretrained Speaker Separation Deep Neural Network (ssDNN) is investigated which is applicable to every dataset. This technique performs speaker clustering and speaker segmentation using DNNs successfully for meeting data and with mixed results for broadcast media.
The task of diarisation focuses on two aspects: accurate segments and speaker labels. The Diarisation Error Rate (DER) does not evaluate the segmentation quality as it does not measure the number of correctly detected segments. Other metrics exist, such as boundary and purity measures, but these also mask the segmentation quality. An alternative metric is presented based on the F-measure which considers the number of hypothesis segments correctly matched to reference segments. A deeper insight into the segment quality is shown through this metric.
Citations
More filters
Journal Article•
TL;DR: In this paper, a speaker attribution system using a complete-linkage clustering method was proposed and evaluated using diarization and speaker linking, which achieved a relative improvement of 40% and 68%, respectively.
Abstract: In this paper we propose and evaluate a speaker attribution system using a complete-linkage clustering method Speaker attribution refers to the annotation of a collection of spoken audio based on speaker identities This can be achieved using diarization and speaker linking The main challenge associated with attribution is achieving computational efficiency when dealing with large audio archives Traditional agglomerative clustering methods with model merging and retraining are not feasible for this purpose This has motivated the use of linkage clustering methods without retraining We first propose a diarization system using complete-linkage clustering and show that it outperforms traditional agglomerative and single-linkage clustering based diarization systems with a relative improvement of 40% and 68%, respectively We then propose a complete-linkage speaker linking system to achieve attribution and demonstrate a 26% relative improvement in attribution error rate (AER) over the single-linkage speaker linking approach
20 citations
08 Sep 2016
TL;DR: This paper presents a freely available and new extended corpus of English speech recordings in a natural setting, with moving speakers, recorded with diverse microphone arrays, and uniquely, with ground truth location tracking.
Abstract: Improving the performance of distant speech recognition is of considerable current interest, driven by a desire to bring speech recognition into people’s homes. Standard approaches to this task aim to enhance the signal prior to recognition, typically using beamforming techniques on multiple channels. Only few real-world recordings are available that allow experimentation with such techniques. This has become even more pertinent with recent works with deep neural networks aiming to learn beamforming from data. Such approaches require large multi-channel training sets, ideally with location annotation for moving speakers, which is scarce in existing corpora. This paper presents a freely available and new extended corpus of English speech recordings in a natural setting, with moving speakers. The data is recorded with diverse microphone arrays, and uniquely, with ground truth location tracking. It extends the 8.0 hour Sheffield Wargames Corpus released in Interspeech 2013, with a further 16.6 hours of fully annotated data, including 6.1 hours of female speech to improve gender bias. Additional blog-based language model data is provided alongside, as well as a Kaldi baseline system. Results are reported with a standard Kaldi configuration, and a baseline meeting recognition system.
5 citations
Proceedings Article•
IBM1
TL;DR: A novel framework for incorporating available a priori knowledge such as potential participating speakers, channels, background noise and gender, and integrating these knowledge sources into blind speaker diarization-type algorithms is proposed.
Abstract: Speaker diarization is usually performed in a blind manner without using a priori knowledge about the identity or acoustic characteristics of the participating speakers. In this paper we propose a novel framework for incorporating available a priori knowledge such as potential participating speakers, channels, background noise and gender, and integrating these knowledge sources into blind speaker diarization-type algorithms. We demonstrate this framework on two tasks. The first task is agent-customer speaker diarization for call-center phone calls and the second task is speaker-diarization for a PDA recorder which is part of an assistive living system for the elderly. For both of these tasks, incorporating the a priori information into our blind speaker diarization systems significantly improves diarization accuracy.
2 citations
01 Jan 2019
Abstract: This paper investigates the task of linking speakers across multiple recordings, which can be accomplished by speaker clustering. Various aspects are considered, such as computational complexity, on/offline approaches, and evaluation measures but also speaker recognition approaches. It has not been the aim of this study to optimize clustering performance, but as an experimental exercise, we perform speaker linking on all '1conv-4w' conversation sides of the NIST-2006 evaluation data set. This set contains 704 speakers in 3835 conversation sides. Using both on-line and off-line algorithms, equal-purity figures of about 86 % are obtained. © Odyssey 2010: Speaker and Language Recognition Workshop. All rights reserved.
2 citations
References
More filters
TL;DR: In this article, a class of prior distributions, called Dirichlet process priors, is proposed for nonparametric problems, for which treatment of many non-parametric statistical problems may be carried out, yielding results that are comparable to the classical theory.
Abstract: The Bayesian approach to statistical problems, though fruitful in many ways, has been rather unsuccessful in treating nonparametric problems. This is due primarily to the difficulty in finding workable prior distributions on the parameter space, which in nonparametric ploblems is taken to be a set of probability distributions on a given sample space. There are two desirable properties of a prior distribution for nonparametric problems. (I) The support of the prior distribution should be large--with respect to some suitable topology on the space of probability distributions on the sample space. (II) Posterior distributions given a sample of observations from the true probability distribution should be manageable analytically. These properties are antagonistic in the sense that one may be obtained at the expense of the other. This paper presents a class of prior distributions, called Dirichlet process priors, broad in the sense of (I), for which (II) is realized, and for which treatment of many nonparametric statistical problems may be carried out, yielding results that are comparable to the classical theory. In Section 2, we review the properties of the Dirichlet distribution needed for the description of the Dirichlet process given in Section 3. Briefly, this process may be described as follows. Let $\mathscr{X}$ be a space and $\mathscr{A}$ a $\sigma$-field of subsets, and let $\alpha$ be a finite non-null measure on $(\mathscr{X}, \mathscr{A})$. Then a stochastic process $P$ indexed by elements $A$ of $\mathscr{A}$, is said to be a Dirichlet process on $(\mathscr{X}, \mathscr{A})$ with parameter $\alpha$ if for any measurable partition $(A_1, \cdots, A_k)$ of $\mathscr{X}$, the random vector $(P(A_1), \cdots, P(A_k))$ has a Dirichlet distribution with parameter $(\alpha(A_1), \cdots, \alpha(A_k)). P$ may be considered a random probability measure on $(\mathscr{X}, \mathscr{A})$, The main theorem states that if $P$ is a Dirichlet process on $(\mathscr{X}, \mathscr{A})$ with parameter $\alpha$, and if $X_1, \cdots, X_n$ is a sample from $P$, then the posterior distribution of $P$ given $X_1, \cdots, X_n$ is also a Dirichlet process on $(\mathscr{X}, \mathscr{A})$ with a parameter $\alpha + \sum^n_1 \delta_{x_i}$, where $\delta_x$ denotes the measure giving mass one to the point $x$. In Section 4, an alternative definition of the Dirichlet process is given. This definition exhibits a version of the Dirichlet process that gives probability one to the set of discrete probability measures on $(\mathscr{X}, \mathscr{A})$. This is in contrast to Dubins and Freedman [2], whose methods for choosing a distribution function on the interval [0, 1] lead with probability one to singular continuous distributions. Methods of choosing a distribution function on [0, 1] that with probability one is absolutely continuous have been described by Kraft [7]. The general method of choosing a distribution function on [0, 1], described in Section 2 of Kraft and van Eeden [10], can of course be used to define the Dirichlet process on [0, 1]. Special mention must be made of the papers of Freedman and Fabius. Freedman [5] defines a notion of tailfree for a distribution on the set of all probability measures on a countable space $\mathscr{X}$. For a tailfree prior, posterior distribution given a sample from the true probability measure may be fairly easily computed. Fabius [3] extends the notion of tailfree to the case where $\mathscr{X}$ is the unit interval [0, 1], but it is clear his extension may be made to cover quite general $\mathscr{X}$. With such an extension, the Dirichlet process would be a special case of a tailfree distribution for which the posterior distribution has a particularly simple form. There are disadvantages to the fact that $P$ chosen by a Dirichlet process is discrete with probability one. These appear mainly because in sampling from a $P$ chosen by a Dirichlet process, we expect eventually to see one observation exactly equal to another. For example, consider the goodness-of-fit problem of testing the hypothesis $H_0$ that a distribution on the interval [0, 1] is uniform. If on the alternative hypothesis we place a Dirichlet process prior with parameter $\alpha$ itself a uniform measure on [0, 1], and if we are given a sample of size $n \geqq 2$, the only nontrivial nonrandomized Bayes rule is to reject $H_0$ if and only if two or more of the observations are exactly equal. This is really a test of the hypothesis that a distribution is continuous against the hypothesis that it is discrete. Thus, there is still a need for a prior that chooses a continuous distribution with probability one and yet satisfies properties (I) and (II). Some applications in which the possible doubling up of the values of the observations plays no essential role are presented in Section 5. These include the estimation of a distribution function, of a mean, of quantiles, of a variance and of a covariance. A two-sample problem is considered in which the Mann-Whitney statistic, equivalent to the rank-sum statistic, appears naturally. A decision theoretic upper tolerance limit for a quantile is also treated. Finally, a hypothesis testing problem concerning a quantile is shown to yield the sign test. In each of these problems, useful ways of combining prior information with the statistical observations appear. Other applications exist. In his Ph. D. dissertation [1], Charles Antoniak finds a need to consider mixtures of Dirichlet processes. He treats several problems, including the estimation of a mixing distribution, bio-assay, empirical Bayes problems, and discrimination problems.
5,033 citations
"Using Deep Neural Networks for Spea..." refers methods in this paper
...Systems can be converted into Bayesian and non-parametric systems using the Dirichlet process (Ferguson, 1973) and infinite Gaussian mixtures are produced by the Dirichlet process mixture model....
[...]
TL;DR: In this article, several parametric representations of the acoustic signal were compared with regard to word recognition performance in a syllable-oriented continuous speech recognition system, and the emphasis was on the ability to retain phonetically significant acoustic information in the face of syntactic and duration variations.
Abstract: Several parametric representations of the acoustic signal were compared with regard to word recognition performance in a syllable-oriented continuous speech recognition system. The vocabulary included many phonetically similar monosyllabic words, therefore the emphasis was on the ability to retain phonetically significant acoustic information in the face of syntactic and duration variations. For each parameter set (based on a mel-frequency cepstrum, a linear frequency cepstrum, a linear prediction cepstrum, a linear prediction spectrum, or a set of reflection coefficients), word templates were generated using an efficient dynamic warping method, and test data were time registered with the templates. A set of ten mel-frequency cepstrum coefficients computed every 6.4 ms resulted in the best performance, namely 96.5 percent and 95.0 percent recognition with each of two speakers. The superior performance of the mel-frequency cepstrum coefficients may be attributed to the fact that they better represent the perceptually relevant aspects of the short-term speech spectrum.
4,822 citations
TL;DR: The major elements of MIT Lincoln Laboratory's Gaussian mixture model (GMM)-based speaker verification system used successfully in several NIST Speaker Recognition Evaluations (SREs) are described.
4,673 citations
"Using Deep Neural Networks for Spea..." refers methods in this paper
...Using a 3 second region of S0, the new speaker model is trained so that the likelihood ratio between model S0 and a UBM (Reynolds et al., 2000) is maximised....
[...]
...UBM Universal Background Model....
[...]
TL;DR: This work considers problems involving groups of data where each observation within a group is a draw from a mixture model and where it is desirable to share mixture components between groups, and considers a hierarchical model, specifically one in which the base measure for the childDirichlet processes is itself distributed according to a Dirichlet process.
Abstract: We consider problems involving groups of data where each observation within a group is a draw from a mixture model and where it is desirable to share mixture components between groups. We assume that the number of mixture components is unknown a priori and is to be inferred from the data. In this setting it is natural to consider sets of Dirichlet processes, one for each group, where the well-known clustering property of the Dirichlet process provides a nonparametric prior for the number of mixture components within each group. Given our desire to tie the mixture models in the various groups, we consider a hierarchical model, specifically one in which the base measure for the child Dirichlet processes is itself distributed according to a Dirichlet process. Such a base measure being discrete, the child Dirichlet processes necessarily share atoms. Thus, as desired, the mixture models in the different groups necessarily share mixture components. We discuss representations of hierarchical Dirichlet processes ...
3,755 citations
TL;DR: A new technique for the analysis of speech, the perceptual linear predictive (PLP) technique, which uses three concepts from the psychophysics of hearing to derive an estimate of the auditory spectrum, and yields a low-dimensional representation of speech.
Abstract: A new technique for the analysis of speech, the perceptual linear predictive (PLP) technique, is presented and examined. This technique uses three concepts from the psychophysics of hearing to derive an estimate of the auditory spectrum: (1) the critical-band spectral resolution, (2) the equal-loudness curve, and (3) the intensity-loudness power law. The auditory spectrum is then approximated by an autoregressive all-pole model. A 5th-order all-pole model is effective in suppressing speaker-dependent details of the auditory spectrum. In comparison with conventional linear predictive (LP) analysis, PLP analysis is more consistent with human hearing. The effective second formant F2' and the 3.5-Bark spectral-peak integration theories of vowel perception are well accounted for. PLP analysis is computationally efficient and yields a low-dimensional representation of speech. These properties are found to be useful in speaker-independent automatic-speech recognition.
2,969 citations
"Using Deep Neural Networks for Spea..." refers methods in this paper
...Perceptual Linear Prediction Coefficients (PLPs) are calculated in a similar way to MFCCs and used as an alternative (Hermansky, 1990)....
[...]