Towards using hierarchical posteriors for flexible automatic speech recognition systems
Graph Chatbot
Chat with Graph Search
Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.
DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.
In the last decade, i-vector and Joint Factor Analysis (JFA) approaches to speaker modeling have become ubiquitous in the area of automatic speaker recognition. Both of these techniques involve the computation of posterior probabilities, using either Gauss ...
Automatic speech recognition (ASR) is a fascinating area of research towards realizing humanmachine interactions. After more than 30 years of exploitation of Gaussian Mixture Models (GMMs), state-of-the-art systems currently rely on Deep Neural Network (DN ...
In i-vector based speaker recognition systems, back-end classifiers are trained to factor out nuisance information and retain only the speaker identity. As a result, variabilities arising due to gender, language and accent ( among many others) are suppress ...
Speaker diarization is the task of identifying ``who spoke when'' in an audio stream containing multiple speakers. This is an unsupervised task as there is no a priori information about the speakers. Diagnostical studies on state-of-the-art diarization sys ...
The development of an Automatic Speech Recognition (ASR) system for the bilingual MediaParl corpus is challenging for several reasons: (1) reverberant recordings, (2) accented speech, and (3) no prior information about the language. In that context, we emp ...
The development of an Automatic Speech Recognition (ASR) system for the bilingual MediaParl corpus is challenging for several reasons: (1) reverberant recordings, (2) accented speech, and (3) no prior information about the language. In that context, we emp ...
In i-vector based speaker recognition systems, back-end classifiers are trained to factor out nuisance information and retain only the speaker identity. As a result, variabilities arising due to gender, language and accent ( among many others) are suppress ...
We hypothesize that optimal deep neural networks (DNN) class-conditional posterior probabilities live in a union of low-dimensional subspaces. In real test conditions, DNN posteriors encode uncertainties which can be regarded as a superposition of unstruct ...
Overlapping speech has been identified as one of the main sources of errors in diarization of meeting room conversations. Therefore, overlap detection has become an important step prior to speaker diarization. Studies on conversational analysis have shown ...
Recent research has demonstrated the effectiveness of vocal tract length normalization (VTLN) as a rapid adaptation technique for statistical parametric speech synthesis. VTLN produces speech with naturalness preferable to that of MLLR-based adaptation tec ...
