When exposed to noise, speakers will modify the way they speak in an effort to maintain intelligible communication. This process, which is referred to as Lombard effect (LE), involves a combination of both conscious and subconscious articulatory adjustment. Speech production variations due to LE can cause considerable degradation in automatic speech recognition (ASR) since they introduce a mismatch between parameters of the speech to be recognized and the ASR system’s acoustic models, which are usually trained on neutral speech. The main objective of this thesis is to analyze the impact of LE on speech production and to propose methods that increase ASR system performance in LE. All presented experiments were conducted on the Czech spoken language, yet, the proposed concepts are assumed applicable to other languages. The first part of the thesis focuses on the design and acquisition of a ...

The subject of this PhD thesis is the efficient and robust processing and analysis of the audio recordings that are derived from a call center. The thesis is comprised of two parts. The first part is dedicated to dialogue/non-dialogue detection and to speaker segmentation. The systems that are developed are prerequisite for detecting (i) the audio segments that actually contain a dialogue between the system and the call center customer and (ii) the change points between the system and the customer. This way the volume of the audio recordings that need to be processed is significantly reduced, while the system is automated. To detect the presence of a dialogue several systems are developed. This is the first effort found in the international literature that the audio channel is exclusively exploited. Also, it is the first time that the speaker utterance ...

This dissertation introduces interactive designs in the context of statistical parametric synthesis. The objective is to develop methods and designs that enrich the Human-Computer Interaction by enabling computers (or other devices) to have more expressive and adjustable voices. First, we tackle the problem of interactive controls and present a novel method for performative HMM-based synthesis (pHTS). Second, we apply interpolation methods, initially developed for the traditional HMM-based speech synthesis system, in the interactive framework of pHTS. Third, we integrate articulatory control in our interactive approach. Fourth, we present a collection of interactive applications based on our work. Finally, we unify our research into an open source library, Mage. To our current knowledge Mage is the first system for interactive programming of HMM-based synthesis that allows realtime manipulation of all speech production levels. It has been used also in cases that ...

Cross-lingual voice conversion refers to the automatic transformation of a source speaker’s voice to a target speaker’s voice in a language that the target speaker can not speak. It involves a set of statistical analysis, pattern recognition, machine learning, and signal processing techniques. This study focuses on the problems related to cross-lingual voice conversion by discussing open research questions, presenting new methods, and performing comparisons with the state-of-the-art techniques. In the training stage, a Phonetic Hidden Markov Model based automatic segmentation and alignment method is developed for cross-lingual applications which support textindependent and text-dependent modes. Vocal tract transformation function is estimated using weighted speech frame mapping in more detail. Adjusting the weights, similarity to target voice and output quality can be balanced depending on the requirements of the cross- lingual voice conversion application. A context-matching algorithm is developed to reduce ...

In the early days of speech synthesis research, understanding voice production has attracted the attention of scientists with the goal of producing intelligible speech. Later, the need to produce more natural voices led researchers to use prerecorded voice databases, containing speech units, reassembled by a concatenation algorithm. With the outgrowth of computer capacities, the length of units increased, going from diphones to non-uniform units, in the so-called unit selection framework, using a strategy referred to as 'take the best, modify the least'. Today the new challenge in voice synthesis is the production of expressive speech or singing. The mainstream solution to this problem is based on the “there is no data like more data” paradigm: emotionspecific databases are recorded and emotion-specific units are segmented. In this thesis, we propose to restart the expressive speech synthesis problem, from its original voice ...

Speech, consisting of an auditory and a visual signal, has always been the most important means of communication between humans. It is well known that an optimal conveyance of the message requires that both the auditory and the visual speech signal can be perceived by the receiver. Nowadays people interact countless times with computer systems in every-day situations. Since the ultimate goal is to make this interaction feel completely natural and familiar, the most optimal way to interact with a computer system is by means of speech. Similar to the speech communication between humans, the most appropriate human-machine interaction consists of audiovisual speech signals. In order to allow the computer system to transfer a spoken message towards its users, an audiovisual speech synthesizer is needed to generate novel audiovisual speech signals based on a given text. This dissertation focuses on ...

Speech is at the core of human communication. Speaking and listing comes so natural to us that we do not have to think about it at all. The underlying cognitive processes are very rapid and almost completely subconscious. It is hard, if not impossible not to understand speech. For computers on the other hand, recognising speech is a daunting task. It has to deal with a large number of different voices "influenced, among other things, by emotion, moods and fatigue" the acoustic properties of different environments, dialects, a huge vocabulary and an unlimited creativity of speakers to combine words and to break the rules of grammar. Almost all existing automatic speech recognisers use statistics over speech sounds "what is the probability that a piece of audio is an a-sound" and statistics over word combinations to deal with this complexity. The ...

Above 20% European citizens speak in Russian therefore the task of automatic recognition of Russian continuous speech has a key significance. The main problems of ASR are connected with the complex mechanism of Russian word-formation. Totally there exist above 3 million diverse valid word-forms that is very large vocabulary ASR task. The thesis presents the novel HMM-based ASR model of Russian that has morphemic levels of speech and language representation. The model includes the developed methods for decomposition of the word vocabulary into morphemes and acoustical and statistical language modelling at the training stage and the method for word synthesis at the last stage of speech decoding. The presented results of application of the ASR model for voice access to the Yellow Pages directory have shown the essential improvement (above 75%) of the real-time factor saving acceptable word recognition rate ...

Voice disorders need to be better understood because they may lead to reduced job chances and social isolation. Correct treatment indication and treatment effect measurements are needed to tackle these problems. They must rely on robust outcome measures for clinical intervention studies. Diplophonia is a severe and often misunderstood sign of voice disorders. Depending on its underlying etiology, diplophonic patients typically receive treatment such as logopedic therapy or phonosurgery. In the current clinical practice diplophonia is determined auditively by the medical doctor, which is problematic from the viewpoints of evidence-based medicine and scientific methodology. The aim of this thesis is to work towards objective (i.e., automatic) detection of diplophonia. A database of 40 euphonic, 40 diplophonic and 40 dysphonic subjects has been acquired. The collected material consists of laryngeal high-speed videos and simultaneous high-quality audio recordings. All material has been ...

Parametric modelling of speech signals finds its use in various speech processing applications. Recently, publications concerning sinusoidal speech modelling have been increasingly appeared in scientific literature. The thesis is mainly devoted to the sinusoidal model with harmonically related component sine waves, i.e. the harmonic model. The main objective is to find new approaches to synthetic speech quality improvement. A novel method for speech spectrum envelope determination is introduced. This method uses a staircase envelope considering the spectral behaviour in voiced as well as unvoiced speech frames. The staircase envelope is smoothed by weighted moving average. The determined envelope is parametrized using autoregressive (AR) model or cepstral coefficients. It has been shown that the new method is of most importance in high-pitch speakers. Besides, new methods or modifications of known methods can be found in pitch synchronization, AR model order selection ...

The process of ageing causes changes to the voice over time. There have been significant research efforts in the automatic speaker recognition community towards improving performance in the presence of everyday variability. The influence of long-term variability, due to vocal ageing, has received only marginal attention however. In this Thesis, the impact of vocal ageing on speaker verification and forensic speaker recognition is assessed, and novel methods are proposed to counteract its effect. The Trinity College Dublin Speaker Ageing (TCDSA) database, compiled for this study, is first introduced. Containing 26 speakers, with recordings spanning an age difference of between 28 and 58 years per speaker, it is the largest longitudinal speech database in the public domain. A Gaussian Mixture Model-Universal Background Model (GMM-UBM) speaker verification experiment demonstrates a progressive decline in the scores of genuine-speakers as the age difference between ...

A method is presented to improve speech recognition for pluricentric languages. Both the effect of adaptation of acoustic data and phonetic transcriptions for several subregions of the German speaking area are investigated and discussed. All experiments were carried out for German spoken in Germany and Austria using large telephone databases (Speech-Dat). In the first part triphone-based acoustic models (AMOs) were trained for several regions and their word error rates (WERs) were compared. The WERs vary between 9.89% and 21.78% and demonstrate the importance of regional variety adaptation. In the pronunciation modeling part narrow phonetic transcriptions for a subset of the Austrian database were carried out to derive pronunciation rules for Austrian German and to generate phonetic lexica for Austrian German which are the first of their kind. These lexica were used for both triphone-based and monophone-based AMOs with German and ...

The topic of this thesis is methods of pre-processing speech signals for robust estimation of model parameters in models of these signals. Here, there is a special focus on the situation where the desired signal is contaminated by colored noise. In order to estimate the speech signal, or its voiced and unvoiced components, from a noisy observation, it is important to have robust estimators that can handle colored and non-stationary noise. Two important aspects are investigated. The first one is a robust estimation of the speech signal parameters, such as the fundamental frequency, which is required in many contexts. For this purpose, fast estimation methods based on a simple white Gaussian noise (WGN) assumption are often used. To keep using those methods, the noisy signal can be pre-processed using a filter. If the colored noise is modelled as an autoregressive ...

Speech synthesis technology plays an important role in many aspects of man–machine interaction, particularly in telephony applications. In order to be widely accepted, the synthesised speech quality should be as human–like as possible. This thesis investigates novel techniques for the speech signal generation stage in a speech synthesiser, based on concepts from nonlinear dynamical theory. It focuses on natural–sounding synthesis for voiced speech, coupled with the ability to generate the sound at the required pitch. The one–dimensional voiced speech time–domain signals are embedded into an appropriate higher dimensional space, using Takens’ method of delays. These reconstructed state space representations have approximately the same dynamical properties as the original speech generating system and are thus effective models. A new technique for marking epoch points in voiced speech that operates in the state space domain is proposed. Using the fact that one ...

Con dence measures for the results of speech/speaker recognition make the systems more useful in the real time applications. Con dence measures provide a test statistic for accepting or rejecting the recognition hypothesis of the speech/speaker recognition system. Speech/speaker recognition systems are usually based on statistical modeling techniques. In this thesis we de ned con dence measures for statistical modeling techniques used in speech/speaker recognition systems. For speech recognition we tested available con dence measures and the newly de ned acoustic prior information based con dence measure in two di erent conditions which cause errors: the out-of-vocabulary words and presence of additive noise. We showed that the newly de ned con dence measure performs better in both tests. Review of speech recognition and speaker recognition techniques and some related statistical methods is given through the thesis. We de ned also ...