Section: Application Domains
Keywords : speaker recognition, user authentication, voice signature, normalisation, scalability, speaker elicitation, representation and adaptation (representation, adaptation), spoken document, speech modeling, speech recognition, rich transcription, beam-search, broadcast news indexing.
Speaker characterisation and speech recognition
A number of audio signals contain speech, which conveys important information concerning the document origin, content and semantics. The field of speaker characterisation and verification covers a variety of tasks that consist in using a speech signal to determine some information concerning the identity of the speaker who uttered it. Indeed, even though the voice characteristics of a person are not unique  , many factors (morphological, physiological, psychological, sociological, ...) have an influence on a person's voice. One focus of the METISS group in this domain is speaker verification, i.e the task of accepting or rejecting an identity claim made by the user of a service with access control. We also dedicate some effort to the more general problem of speaker characterisation. In parallel, METISS maintains some know-how and develops new research in the area of acoustic modeling of speech signals and automatic speech transcription, mainly in the framework of the semantic analysis of audio and multimedia documents.
Robustness issues in speaker recognition
Speaker recognition and verification has made significant progress with the systematical use of probabilistic models, in particular Hidden Markov Models (for text-dependent applications) and Gaussian Mixture Models (for text-independent applications). As presented in the fundamentals of this report, the current state-of-the-art approaches rely on bayesian decision theory.
However, robustness issues are still pending : when speaker characteristics are learned on small quantities of data, the trained model has very poor performance, because it lacks generalisation capabilities. This problem can partly be overcome by adaptation techniques (following the MAP viewpoint), using either a speaker-independent model as general knowledge, or some structural information, for instance a dependency model between local distributions.
Speaker model and test normalisation
A key issue, in many practical applications, is the non-controlable deviation of speaker models from the exact probability density functions. This requires a step of normalisation before comparing the verification score to a decision threshold. This issue has been a particular focus for our recent efforts in the domain of speaker verification and has led to the design and evaluation of various strategies of model and test normalisation.
Speaker representation, selection and adaptation
METISS also adresses a number of other topics related to speaker characterisation, in particular speaker selection (i.e. how to select a representative subset of speakers from a larger population), speaker representation (namely how to represent a new speaker in reference to a given speaker population), speaker adaptation for speech recognition, and more recently, speaker's emotion detection.
Scalability and complexity reduction for speaker recognition
In order to address needs related to the implementation of speaker verification technology on personal devices, specific algorithmic approaches have to be developed to contribute to the scalability, the complexity reduction and the process distribution. In this context, speaker modelling approaches and classification procedures need to be designed, simulated and tested.
Speech modeling and recognition
Speech modeling and recognition is complementary with other speech related activities in the group, in particular, speaker recognition and audio description. In the first case, detecting speech segments in a continuous audio stream and segmenting the speech portions into pseudo-sentences is a preliminary step to automatic transcription. Detecting speaker changes and grouping together segments from the same speaker is also a crucial step for segmentation as for speaker adaptation, and can rely on acoustic as well as lexical and linguistic features. Last, in speaker recognition for secured transactions over the telephone, recognizing the linguistic content of the message might be useful, for example to hypothesize an identity, to recognize a spoken password or to extract linguistic parameters that can benefit to the speaker models.