Essays about: "spectral embedding"

Found 5 essays containing the words spectral embedding.

  1. 1. Experiments in speaker diarization using speaker vectors

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Ming Cui; [2021]
    Keywords : Speaker Diarization; Embedding Extraction Module; Deep Learning; Supervised method; Unsupervised method; Talardiarisering; inbäddning av extraktionsmodul; djupinlärning; övervakad metod; oövervakad metod;

    Abstract : Speaker Diarization is the task of determining ‘who spoke when?’ in an audio or video recording that contains an unknown amount of speech and also an unknown number of speakers. It has emerged as an increasingly important and dedicated domain of speech research. READ MORE

  2. 2. Efficient Discovery Of Binary Stars

    University essay from Lunds universitet/Astronomi; Lunds universitet/Institutionen för astronomi och teoretisk fysik

    Author : Pablo Navarro Barrachina; [2020]
    Keywords : Binary Stars; Spectroscopic binary stars; SB2; Machine Learning; Data Mining; Physics and Astronomy;

    Abstract : Purpose: even in the era of exponential increase in the amount of stellar data gathered, binaries are still often overlooked in observational data due to the special handling they require. The goal of this work is to develop a method capable of automatically and efficiently identifying and extract double-lined spectroscopic binaries (SB2) from a spectroscopic survey, while being scalable and technically successful, and to identify and optimize the parameters that influence their detection. READ MORE

  3. 3. A graph representation of event intervals for efficient clustering and classification

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Zed Heeje Lee; [2020]
    Keywords : event intervals; bipartite graph; spectral embedding; clustering; classification; händelsesintervall; bipartitgraf; spektral inbäddning; klustering; klassificering;

    Abstract : Sequences of event intervals occur in several application domains, while their inherent complexity hinders scalable solutions to tasks such as clustering and classification. In this thesis, we propose a novel spectral embedding representation of event interval sequences that relies on bipartite graphs. READ MORE

  4. 4. Low Supervision, Low Corpus size, Low Similarity! Challenges in cross-lingual alignment of word embeddings : An exploration of the limitations of cross-lingual word embedding alignment in truly low resource scenarios

    University essay from Uppsala universitet/Institutionen för lingvistik och filologi

    Author : Andrew Dyer; [2019]
    Keywords : word embeddings; cross-lingual; multilingual; low-resource; corpus size; Vecmap; FastText; alignment; orthogonal; eigenvalues; Laplacian; isospectral; isomorphic; bilingual lexicon induction;

    Abstract : Cross-lingual word embeddings are an increasingly important reseource in cross-lingual methods for NLP, particularly for their role in transfer learning and unsupervised machine translation, purportedly opening up the opportunity for NLP applications for low-resource languages.  However, most research in this area implicitly expects the availablility of vast monolingual corpora for training embeddings, a scenario which is not realistic for many of the world's languages. READ MORE

  5. 5. Plant Condition Measurement from Spectral Reflectance Data

    University essay from Linköpings universitet/Bildbehandling

    Author : Peter Johansson; [2010]
    Keywords : Leaf reflectance spectrum; Plant condition; PCA; PLS; MLR; CCA; Multidimensional signal analysis;

    Abstract : The thesis presents an investigation of the potential of measuring plant condition from hyperspectral reflectance data. To do this, some linear methods for embedding the high dimensional hyperspectral data and to perform regression to a plant condition space have been compared. READ MORE