Odyssey 2012: The Speaker and Language Recognition Workshop, Singapore, June 25-28, 2012
نویسندگان
چکیده
Welcome to Odyssey 2012: The Speaker and Language Recognition Workshop, hosted by COLIPS (Chinese and Oriental Languages Information Processing Society) in Singapore, on 25-28 June 2012. Odyssey 2012 received overwhelming response from the speaker and language recognition community. We accepted 51 papers out of 65 submissions, which we organized into a 4-day technical program consisting of 11 sessions. Researchers will present their latest endeavours and insights from multiple aspects, covering speaker and language characterization, modelling, evaluation, and applications. In addition, Odyssey 2012 also features 3 invited speakers: Dr. Li Deng (Microsoft Research) will share with us how new generation models such as deep belief networks and dynamic Bayesian networks can revamp the traditional framework of Gaussian mixture model and hidden Markov model in speech technology; Dr. Niko Brümmer (Agnitio Corporation) will discuss how Organizers:
منابع مشابه
I4u submission to NIST SRE 2012: a large-scale collaborative effort for noise-robust speaker verification
I4U is a joint entry of nine research Institutes and Universities across 4 continents to NIST SRE 2012. It started with a brief discussion during the Odyssey 2012 workshop in Singapore. An online discussion group was soon set up, providing a discussion platform for different issues surrounding NIST SRE’12. Noisy test segments, uneven multi-session training, variable enrollment duration, and the...
متن کاملSource normalization for language-independent speaker recognition using i-vectors
Source-normalization (SN) is an effective means of improving the robustness of i-vector-based speaker recognition for under-resourced and unseen cross-speech-source evaluation conditions. The technique of source-normalization estimates directions of undesired within-speaker variation more accurately than traditional methods when cross-source variation is not explicitly observed from each speake...
متن کاملSpeaker vectors from subspace Gaussian mixture model as complementary features for language identification
In this paper, we explore new high-level features for language identification. The recently introduced Subspace Gaussian Mixture Models (SGMM) provide an elegant and efficient way for GMM acoustic modelling, with mean supervectors represented in a low-dimensional representative subspace. SGMMs also provide an efficient way of speaker adaptation by means of lowdimensional vectors. In our framewo...
متن کاملA unified approach for audio characterization and its application to speaker recognition
Systems designed to solve speech processing tasks like speech or speaker recognition, language identification, or emotion detection are known to be affected by the recording conditions of the acoustic signal, like the channel, background noise, reverberation, and so on. Knowledge of the nuisance characteristics present in the signal can be used to improve performance of the system. In some case...
متن کاملPreliminary investigation of Boltzmann machine classifiers for speaker recognition
We propose a novel generative approach to speaker recognition using Boltzmann machines, a fledgeling non-Gaussian probabilistic framework that is increasingly gaining attention in several machine learning fields. We show how a modified i-vector representation of speech utterances enables the development of several Boltzmann machine architectures for speaker verification and we report some preli...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2012