Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Handbook of the International Phonetic Association: A Guide to the Use of the International Phonetic Alphabet

Emotion recognition in human-computer interaction

Current automatic speech recognition systems make use of a single source of information about their input, viz a preprocessed form of the acoustic speech signal, which encodes the time-frequency distribution of signal energy The goal of this thesis is to investigate the benefits of integrating articulatory information into state-of-the art speech recognizers, either as a genuine alternative to standard acoustic representations, or as an additional source of information Articulatory information is represented in terms of abstract articulatory classes or "features", which are extracted from the speech signal by means of statistical classifiers A higher-level classifier then combines the scores for these features and maps them to standard subword unit probabilities
The main motivation for this approach is to improve the robustness of speech recognition systems in adverse acoustic environments, such as background noise Typically, recognition systems show a sharp decline of performance under these conditions We argue and demonstrate empirically that the articulatory feature approach can lead to greater robustness by enhancing the accuracy of the bottom-up acoustic modeling component in a speech recognition system
The second focus point of this thesis is to provide detailed analyses of the different types of information provided by the acoustic and the articulatory representations, respectively, and to develop strategies to optimally combine them To this effect we investigate combination methods at the levels of feature extraction, subword unit probability estimation, and word recognition
The feasibility of this approach is demonstrated with respect to two different speech recognition tasks The first of these is an American English corpus of telephone-bandwidth speech; the recognition domain is continuous numbers The second is a German database of studio-quality speech consisting of spontaneous dialogues In both cases recognition performance will be tested not only under clean acoustic conditions but also under deteriorated conditions

/pdf/robust-speech-recognition-using-articulatory-information-32o2izd983.pdf

Robust speech recognition using articulatory information

The rise of unstructured data (UD), propelled by novel technologies, is reshaping markets and the management of marketing activities. Yet these increased data remain mostly untapped by many firms, suggesting the potential for further research developments. The integrative framework proposed in this study addresses the nature of UD and pursues theoretical richness and computational advancements by integrating insights from other disciplines. This article makes three main contributions to the literature by (1) offering a unifying definition and conceptualization of UD in marketing; (2) bridging disjoint literature with an organizing framework that synthesizes various subsets of UD relevant for marketing management through an integrative review; and (3) identifying substantive, computational, and theoretical gaps in extant literature and ways to leverage interdisciplinary knowledge to advance marketing research by applying UD analyses to underdeveloped areas.

Unstructured data in marketing

A great challenge for text-to-speech synthesis is to produce ex- pressive speech. The main problem is that it is difficult to syn- thesise high-quality speech using expressive corpora. With the increasing interest in audiobook corpora for speech synthesis, there is a demand to synthesise speech which is rich in prosody, emotions and voice styles. In this work, Self-Organising Fea- ture Maps (SOFM) are used for clustering the speech data using voice quality parameters of the glottal source, in order to map out the variety of voice styles in the corpus. Subjective evalu- ation showed that this clustering method successfully separated the speech data into groups of utterances associated with dif- ferent voice characteristics. This work can be applied in unit- selection synthesis by selecting appropriate data sets to synthe- sise utterances with specific voice styles. It can also be used in parametric speech synthesis to model different voice styles separately.

/pdf/clustering-expressive-speech-styles-in-audiobooks-using-49d6fdzn1s.pdf

Clustering Expressive Speech Styles in Audiobooks Using Glottal Source Parameters.

From the Publisher:
Time Map Phonology addresses key areas of sound structure at which the two technologies of natural language processing and speech technology are beginning to converge. Solutions are presented to the problems of how to process words which have not been heard before and how to develop fine grained knowledge representation and processing techniques for linguistic units smaller than the word. The solutions are based on a careful comparison of linguistic theories and on the investigation of computational techniques for the next generation of flexible spoken language input and output devices. The approach has been fully implemented for the vocabulary of German and subjected to quantitative evaluation.

Time Map Phonology: Finite State Models and Event Logics in Speech Recognition

Audiobooks are known to contain a variety of expressive speaking styles that occur as a result of the narrator mimicking a character in a story, or expressing affect. An accurate modeling of this variety is essential for the purposes of speech synthesis from an audiobook. Voice quality differences are important features characterizing these different speaking styles, which are realized on a gradient and are often difficult to predict from the text. The present study uses a parameter characterizing breathy to tense voice qualities using features of the wavelet transform, and a measure for identifying creaky segments in an utterance. Based on these features, a combination of supervised and unsupervised classification is used to detect the regions in an audiobook, where the speaker changes his regular voice quality to a particular voice style. The target voice style candidates are selected based on the agreement of the supervised classifier ensemble output, and evaluated in a listening test.

/pdf/detecting-a-targeted-voice-style-in-an-audiobook-using-voice-14gdophjdb.pdf

Detecting a targeted voice style in an audiobook using voice quality features

Freely available audiobooks are a rich resource of expressive speech recordings that can be used for the purposes of speech synthesis. Natural sounding, expressive synthetic voices have previously been built from audiobooks that contained large amounts of highly expressive speech recorded from a professionally trained speaker. The majority of freely available audiobooks, however, are read by amateur speakers, are shorter and contain less expressive (less emphatic, less emotional, etc.) speech both in terms of quality and quantity. Synthesizing expressive speech from a typical online audiobook therefore poses many challenges. In this work we address these challenges by applying a method consisting of minimally supervised techniques to align the text with the recorded speech, select groups of expressive speech segments and build expressive voices for hidden Markov-model based synthesis using speaker adaptation. Subjective listening tests have shown that the expressive synthetic speech generated with this method is often able to produce utterances suited to an emotional message. We used a restricted amount of speech data in our experiment, in order to show that the method is generally applicable to most typical audiobooks widely available online.

/pdf/synthesizing-expressive-speech-from-amateur-audiobook-4rw9xz38tw.pdf

Julie Carson-Berndsen

Papers

Clustering Expressive Speech Styles in Audiobooks Using Glottal Source Parameters.

Time Map Phonology: Finite State Models and Event Logics in Speech Recognition

Detecting a targeted voice style in an audiobook using voice quality features

Synthesizing expressive speech from amateur audiobook recordings

Time Map Phonology