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.
Domain adaptation of a language model aims at re-estimating word sequence probabilities in order to better match the peculiarities of a given broad topic of interest. To achieve this task, a common strategy consists in retrieving adaptation texts from the ...
In this paper, we describe a low delay real-time multimodal cue detection engine for a living room environment. The system is designed to be used in open, unconstrained environments to allow multiple people to enter, interact and leave the observable world ...
Background work in various levels of speech coding is reviewed, including unconstrained coding and recognition-synthesis approaches that assume the signal is speech. A pilot project in HMM-TTS based speech coding is then described, in which a comparison wi ...
We describe the design of Kaldi, a free, open-source toolkit for speech recognition research. Kaldi provides a speech recognition system based on finite-state automata (using the freely available OpenFst), together with detailed documentation and a compreh ...
This paper investigates detection of English keywords in a conversational scenario using a combination of acoustic and LVCSR based keyword spotting systems. Acoustic KWS systems search predefined words in parameterized spoken data. Corresponding confidence ...
Recurrent neural network language models (RNNLMs) have recently shown to outperform the venerable n-gram language models (LMs). However, in automatic speech recognition (ASR), RNNLMs were not yet used to directly decode a speech signal. Instead, RNNLMs are ...
This paper presents a new database containing high-definition audio and video recordings in a rather unconstrained video-conferencing-like environment. The database consists of recordings of people sitting around a table in two separate rooms communicating ...
Recurrent neural network language models (RNNLMs) have recently shown to outperform the venerable n-gram language models (LMs). However, in automatic speech recognition (ASR), RNNLMs were not yet used to directly decode a speech signal. Instead, RNNLMs are ...
This paper investigates detection of English keywords in a conversational scenario using a combination of acoustic and LVCSR based keyword spotting systems. Acoustic KWS systems search predefined words in parameterized spoken data. Corresponding confidence ...
Modern social media systems are geared to serving weak ties: informal collections of individuals acting in relative isolation. But what about strong ties: the family and friends who form life's inner circle? More and more people are living apart. Can techn ...
