Minimising speaker verification utterance length through confidence based early verification decisions

This paper presents a novel approach of estimating the confidence interval of speaker verification scores. This approach is utilised to minimise the utterance lengths required in order to produce a confident verification decision. The confidence estimation method is also extended to address both the problem of high correlation in consecutive frame scores, and robustness with very limited training samples. The proposed technique achieves a drastic reduction in the typical data requirements for producing confident decisions in an automatic speaker verification system. When evaluated on the NIST 2005 SRE, the early verification decision method demonstrates that an average of 5–10 seconds of speech is sufficient to produce verification rates approaching those achieved previously using an average in excess of 100 seconds of speech.

Improving short utterance based I-vector speaker recognition using source and utterance-duration normalization techniques

A significant amount of speech is typically required for speaker verification system development and evaluation, especially in the presence of large intersession variability. This paper introduces a source and utterance duration normalized linear discriminant analysis (SUN-LDA) approaches to compensate session variability in short-utterance i-vector speaker verification systems. Two variations of SUN-LDA are proposed where normalization techniques are used to capture source variation from both short and full-length development i-vectors, one based upon pooling (SUN-LDA-pooled) and the other on concatenation (SUN-LDA-concat) across the duration and source-dependent session variation. Both the SUN-LDA-pooled and SUN-LDA-concat techniques are shown to provide improvement over traditional LDA on NIST 08 truncated 10sec-10sec evaluation conditions, with the highest improvement obtained with the SUN-LDA-concat technique achieving a relative improvement of 8% in EER for mis-matched conditions and over 3% for matched conditions over traditional LDA approaches.

Improving short utterance i-vector speaker verification using utterance variance modelling and compensation techniques

This paper proposes techniques to improve the performance of i-vector based speaker verification systems when only short utterances are available. Short-length utterance i-vectors vary with speaker, session variations, and the phonetic content of the utterance. Well established methods such as linear discriminant analysis (LDA), source-normalized LDA (SN-LDA) and within-class covariance normalisation (WCCN) exist for compensating the session variation but we have identified the variability introduced by phonetic content due to utterance variation as an additional source of degradation when short-duration utterances are used. To compensate for utterance variations in short i-vector speaker verification systems using cosine similarity scoring (CSS), we have introduced a short utterance variance normalization (SUVN) technique and a short utterance variance (SUV) modelling approach at the i-vector feature level. A combination of SUVN with LDA and SN-LDA is proposed to compensate the session and utterance variations and is shown to provide improvement in performance over the traditional approach of using LDA and/or SN-LDA followed by WCCN. An alternative approach is also introduced using probabilistic linear discriminant analysis (PLDA) approach to directly model the SUV. The combination of SUVN, LDA and SN-LDA followed by SUV PLDA modelling provides an improvement over the baseline PLDA approach. We also show that for this combination of techniques, the utterance variation information needs to be artificially added to full-length i-vectors for PLDA modelling.

Short utterance PLDA speaker verification using SN-WLDA and variance modelling techniques

This paper proposes a combination of source-normalized weighted linear discriminant analysis (SN-WLDA) and short utterance variance (SUV) PLDA modelling to improve the short utterance PLDA speaker verification. As short-length utterance i-vectors vary with the speaker, session variations and phonetic content of the utterance (utterance variation), a combined approach of SN-WLDA projection and SUV PLDA modelling is used to compensate the session and utterance variations. Experimental studies have found that a combination of SN-WLDA and SUV PLDA modelling approach shows an improvement over baseline system (WCCN[LDA]-projected Gaussian PLDA (GPLDA)) as this approach effectively compensates the session and utterance variations.

Within-session variability modelling for factor analysis speaker verification

This work presents an extended Joint Factor Analysis model including explicit modelling of unwanted within-session variability. The goals of the proposed extended JFA model are to improve verification performance with short utterances by compensating for the effects of limited or imbalanced phonetic coverage, and to produce a flexible JFA model that is effective over a wide range of utterance lengths without adjusting model parameters such as retraining session subspaces. Experimental results on the 2006 NIST SRE corpus demonstrate the flexibility of the proposed model by providing competitive results over a wide range of utterance lengths without retraining and also yielding modest improvements in a number of conditions over current state-of-the-art.

Acoustic keyword spotting in speech with applications to data mining

Keyword Spotting is the task of detecting keywords of interest within continu- ous speech. The applications of this technology range from call centre dialogue systems to covert speech surveillance devices. Keyword spotting is particularly well suited to data mining tasks such as real-time keyword monitoring and unre- stricted vocabulary audio document indexing. However, to date, many keyword spotting approaches have su®ered from poor detection rates, high false alarm rates, or slow execution times, thus reducing their commercial viability. This work investigates the application of keyword spotting to data mining tasks. The thesis makes a number of major contributions to the ¯eld of keyword spotting. The ¯rst major contribution is the development of a novel keyword veri¯cation method named Cohort Word Veri¯cation. This method combines high level lin- guistic information with cohort-based veri¯cation techniques to obtain dramatic improvements in veri¯cation performance, in particular for the problematic short duration target word class. The second major contribution is the development of a novel audio document indexing technique named Dynamic Match Lattice Spotting. This technique aug- ments lattice-based audio indexing principles with dynamic sequence matching techniques to provide robustness to erroneous lattice realisations. The resulting algorithm obtains signi¯cant improvement in detection rate over lattice-based audio document indexing while still maintaining extremely fast search speeds. The third major contribution is the study of multiple veri¯er fusion for the task of keyword veri¯cation. The reported experiments demonstrate that substantial improvements in veri¯cation performance can be obtained through the fusion of multiple keyword veri¯ers. The research focuses on combinations of speech background model based veri¯ers and cohort word veri¯ers. The ¯nal major contribution is a comprehensive study of the e®ects of limited training data for keyword spotting. This study is performed with consideration as to how these e®ects impact the immediate development and deployment of speech technologies for non-English languages.

Automatic spoken language identification utilizing acoustic and phonetic speech information

Automatic spoken Language Identi¯cation (LID) is the process of identifying the language spoken within an utterance. The challenge that this task presents is that no prior information is available indicating the content of the utterance or the identity of the speaker. The trend of globalization and the pervasive popularity of the Internet will amplify the need for the capabilities spoken language identi¯ca- tion systems provide. A prominent application arises in call centers dealing with speakers speaking di®erent languages. Another important application is to index or search huge speech data archives and corpora that contain multiple languages. The aim of this research is to develop techniques targeted at producing a fast and more accurate automatic spoken LID system compared to the previous National Institute of Standards and Technology (NIST) Language Recognition Evaluation. Acoustic and phonetic speech information are targeted as the most suitable fea- tures for representing the characteristics of a language. To model the acoustic speech features a Gaussian Mixture Model based approach is employed. Pho- netic speech information is extracted using existing speech recognition technol- ogy. Various techniques to improve LID accuracy are also studied. One approach examined is the employment of Vocal Tract Length Normalization to reduce the speech variation caused by di®erent speakers. A linear data fusion technique is adopted to combine the various aspects of information extracted from speech. As a result of this research, a LID system was implemented and presented for evaluation in the 2003 Language Recognition Evaluation conducted by the NIST.

Dynamic visual features for audio-visual speaker verification

The cascading appearance-based (CAB) feature extraction technique has established itself as the state-of-the-art in extracting dynamic visual speech features for speech recognition. In this paper, we will focus on investigating the effectiveness of this technique for the related speaker verification application. By investigating the speaker verification ability of each stage of the cascade we will demonstrate that the same steps taken to reduce static speaker and environmental information for the visual speech recognition application also provide similar improvements for visual speaker recognition. A further study is conducted comparing synchronous HMM (SHMM) based fusion of CAB visual features and traditional perceptual linear predictive (PLP) acoustic features to show that higher complexity inherit in the SHMM approach does not appear to provide any improvement in the final audio-visual speaker verification system over simpler utterance level score fusion.

Script proposals: a device for empowering clients in counselling

Much of the research on the delivery of advice by professionals such as physicians, health workers and counsellors, both on the telephone and in face to face interaction more generally, has focused on the theme of client resistance and the consequent need for professionals to adopt particular formats to assist in the uptake of the advice. In this paper we consider one setting, Kid’s Helpline, the national Australian counselling service for children and young people, where there is an institutional mandate not to give explicit advice in accordance with the values of self-direction and empowerment. The paper examines one practice, the use of script proposals by counsellors, which appears to offer a way of providing support which is consistent with these values. Script proposals entail the counsellors packaging their advice as something that the caller might say – at some future time – to a third party such as a friend, teacher, parent, or partner, and involve the counsellor adopting the speaking position of the caller in what appears as a rehearsal of a forthcoming strip of interaction. Although the core feature of a script proposal is the counsellor’s use of direct reported speech they appear to be delivered, not so much as exact words to be followed, but as the type of conversation that the client needs to have with the 3rd party. Script proposals, in short, provide models of what to say as well as alluding to how these could be emulated by the client. In their design script proposals invariably incorporate one or more of the most common rhetorical formats for maximising the persuasive force of an utterance such as a three part list or a contrastive pair. Script proposals, moreover, stand in a complex relation to the prior talk and one of their functions appears to be to summarise, respecify or expand upon the client’s own ideas or suggestions for problem solving that have emerged in these preceding sequences.

i-vector based speaker recognition on short utterances

Robust speaker verification on short utterances remains a key consideration when deploying automatic speaker recognition, as many real world applications often have access to only limited duration speech data. This paper explores how the recent technologies focused around total variability modeling behave when training and testing utterance lengths are reduced. Results are presented which provide a comparison of Joint Factor Analysis (JFA) and i-vector based systems including various compensation techniques; Within-Class Covariance Normalization (WCCN), LDA, Scatter Difference Nuisance Attribute Projection (SDNAP) and Gaussian Probabilistic Linear Discriminant Analysis (GPLDA). Speaker verification performance for utterances with as little as 2 sec of data taken from the NIST Speaker Recognition Evaluations are presented to provide a clearer picture of the current performance characteristics of these techniques in short utterance conditions.

PLDA based speaker recognition on short utterances

This paper investigates the effects of limited speech data in the context of speaker verification using a probabilistic linear discriminant analysis (PLDA) approach. Being able to reduce the length of required speech data is important to the development of automatic speaker verification system in real world applications. When sufficient speech is available, previous research has shown that heavy-tailed PLDA (HTPLDA) modeling of speakers in the i-vector space provides state-of-the-art performance, however, the robustness of HTPLDA to the limited speech resources in development, enrolment and verification is an important issue that has not yet been investigated. In this paper, we analyze the speaker verification performance with regards to the duration of utterances used for both speaker evaluation (enrolment and verification) and score normalization and PLDA modeling during development. Two different approaches to total-variability representation are analyzed within the PLDA approach to show improved performance in short-utterance mismatched evaluation conditions and conditions for which insufficient speech resources are available for adequate system development. The results presented within this paper using the NIST 2008 Speaker Recognition Evaluation dataset suggest that the HTPLDA system can continue to achieve better performance than Gaussian PLDA (GPLDA) as evaluation utterance lengths are decreased. We also highlight the importance of matching durations for score normalization and PLDA modeling to the expected evaluation conditions. Finally, we found that a pooled total-variability approach to PLDA modeling can achieve better performance than the traditional concatenated total-variability approach for short utterances in mismatched evaluation conditions and conditions for which insufficient speech resources are available for adequate system development.

Sequential decision fusion of multibiometrics applied to text-dependent speaker verification for controlled errors

Reliability of the performance of biometric identity verification systems remains a significant challenge. Individual biometric samples of the same person (identity class) are not identical at each presentation and performance degradation arises from intra-class variability and inter-class similarity. These limitations lead to false accepts and false rejects that are dependent. It is therefore difficult to reduce the rate of one type of error without increasing the other. The focus of this dissertation is to investigate a method based on classifier fusion techniques to better control the trade-off between the verification errors using text-dependent speaker verification as the test platform. A sequential classifier fusion architecture that integrates multi-instance and multisample fusion schemes is proposed. This fusion method enables a controlled trade-off between false alarms and false rejects. For statistically independent classifier decisions, analytical expressions for each type of verification error are derived using base classifier performances. As this assumption may not be always valid, these expressions are modified to incorporate the correlation between statistically dependent decisions from clients and impostors. The architecture is empirically evaluated by applying the proposed architecture for text dependent speaker verification using the Hidden Markov Model based digit dependent speaker models in each stage with multiple attempts for each digit utterance. The trade-off between the verification errors is controlled using the parameters, number of decision stages (instances) and the number of attempts at each decision stage (samples), fine-tuned on evaluation/tune set. The statistical validation of the derived expressions for error estimates is evaluated on test data. The performance of the sequential method is further demonstrated to depend on the order of the combination of digits (instances) and the nature of repetitive attempts (samples). The false rejection and false acceptance rates for proposed fusion are estimated using the base classifier performances, the variance in correlation between classifier decisions and the sequence of classifiers with favourable dependence selected using the 'Sequential Error Ratio' criteria. The error rates are better estimated by incorporating user-dependent (such as speaker-dependent thresholds and speaker-specific digit combinations) and class-dependent (such as clientimpostor dependent favourable combinations and class-error based threshold estimation) information. The proposed architecture is desirable in most of the speaker verification applications such as remote authentication, telephone and internet shopping applications. The tuning of parameters - the number of instances and samples - serve both the security and user convenience requirements of speaker-specific verification. The architecture investigated here is applicable to verification using other biometric modalities such as handwriting, fingerprints and key strokes.

On Chinese Modal Particle A (啊) : A Pragmatic and Semantic Study

Chinese modal particles feature prominently in Chinese people’s daily use of the language, but their pragmatic and semantic functions are elusive as commonly recognised by Chinese linguists and teachers of Chinese as a foreign language. This book originates from an extensive and intensive empirical study of the Chinese modal particle a (啊), one of the most frequently used modal particles in Mandarin Chinese. In order to capture all the uses and the underlying meanings of the particle, the author transcribed the first 20 episodes, about 20 hours in length, of the popular Chinese TV drama series Kewang ‘Expectations’, which yielded a corpus data of more than 142’000 Chinese characters with a total of 1829 instances of the particle all used in meaningful communicative situations. Within its context of use, every single occurrence of the particle was analysed in terms of its pragmatic and semantic contributions to the hosting utterance. Upon this basis the core meanings were identified which were seen as constituting the modal nature of the particle.

Speaker verification using I-vector features

This PhD research has provided novel solutions to three major challenges which have prevented the wide spread deployment of speaker recognition technology: (1) combating enrolment/ verification mismatch, (2) reducing the large amount of development and training data that is required and (3) reducing the duration of speech required to verify a speaker. A range of applications of speaker recognition technology from forensics in criminal investigations to secure access in banking will benefit from the research outcomes.

Notes on the future of critical discourse studies

In How to Do Things with Words, Austin (1975) described marriages, sentencings and ship launchings as prototypes of performative utterance. What’s the appropriate speech act for launching an academic journal? First editions of journals tend to take a field as formed a priori, as having “come of age”, and state good intents to capture its best or most innovative work.