Redundant Hash Addressing for Large-Scale Query by Example Spoken Query Detection
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.
Transformers achieve remarkable performance in several tasks but due to their quadratic complexity, with respect to the input’s length, they are prohibitively slow for very long sequences. To address this limitation, we express the self-attention as a line ...
Language independent query-by-example spoken term detection (QbE-STD) is the problem of retrieving audio documents from an archive, which contain a spoken query provided by a user. This is usually casted as a hypothesis testing and pattern matching problem ...
In hidden Markov model (HMM) based automatic speech recognition (ASR) system, modeling the statistical relationship between the acoustic speech signal and the HMM states that represent linguistically motivated subword units such as phonemes is a crucial st ...
Increasing concerns with privacy have stimulated interests in Session-based Recommendation (SR) using no personal data other than what is observed in the current browser session. Existing methods are evaluated in static settings which rarely occur in real- ...
This thesis deals with exploiting the low-dimensional multi-subspace structure of speech towards the goal of improving acoustic modeling for automatic speech recognition (ASR). Leveraging the parsimonious hierarchical nature of speech, we hypothesize that ...
Increasing concerns with privacy have stimulated interests in Session-based Recommendation (SR) using no personal data other than what is observed in the current browser session. Existing methods are evaluated in static settings which rarely occur in real- ...
We introduce a method for automated grading of handwritten essays written by foreign language learners of French. The handwriting recognition system allows digitising the essays for further processing and functions at a low character error rate. The transc ...
To address the open vocabulary problem in the context of end-to-end automatic speech recognition (ASR), we experiment with subword segmentation approaches, specifically byte-pair encoding and unigram language model. Such approaches are attractive in genera ...
We propose regression networks for the problem of few-shot classification, where a classifier must generalize to new classes not seen in the training set, given only a small number of examples of each class. In high dimensional embedding spaces the directi ...
Vocal tract length normalisation (VTLN) is well established as a speaker adaptation technique that can work with very little adaptation data. It is also well known that VTLN can be cast as a linear transform in the cepstral domain. Building on this latter ...
