|
Lexical Association Measures Collocation Extraction
Pecina, Pavel ; Hajič, Jan (advisor)
Lexical Association Measures: Collocation Extraction Pavel Pecina Abstract of Doctoral Thesis This thesis is devoted to an empirical study of lexical association measures and their application for collocation extraction. We focus on two-word (bigram) collocations only. We compiled a comprehensive inventory of 82 lexical association measures and present their empirical evaluation on four reference data sets: dependency bigrams from the manually annotated Prague Dependency Trcebank, surface bigrams from the same source, instances of the previous from the Czech National Corpus provided with automatically assigned lemmas and part-of-speech tags, and distance verb-noun bigrams from the automatically part-of-spcech tagged Swedish Parole Corpus. Collocation candidates in the reference data sets were manually annotated and identified as collocations and non-collocations. The evaluation scheme is based on measuring the quality of ranking collocation candidates according to their chance to form collocations. The methods are compared by precision-recall curves and mean average precision scores adopted from the field of information retrieval. Tests of statistical significance were also performed. Further, we study the possibility of combining lexical association measures and present empirical results of several...
|
|
Pojmenované entity a ontologie metodami hlubokého učení
Rafaj, Filip ; Hajič, Jan (advisor) ; Žabokrtský, Zdeněk (referee)
In this master thesis we describe a method for linking named entities in a given text to a knowledge base - Named Entity Linking. Using a deep neural architecture together with BERT contextualized word embeddings we created a semi-supervised model that jointly performs Named Entity Recognition and Named Entity Disambiguation. The model outputs a Wikipedia ID for each entity detected in an input text. To compute contextualized word embeddings we used pre-trained BERT without making any changes to it (no fine-tuning). We experimented with components of our model and various versions of BERT embeddings. Moreover, we tested several different ways of using the contextual embeddings. Our model is evaluated using standard metrics and surpasses scores of models that were establishing the state of the art before the expansion of pre-trained contextualized models. The scores of our model are comparable to current state-of-the-art models.
|
|
Music Visualization in 3D
Vincena, Petr ; Rittig, Tobias (advisor) ; Hajič, Jan (referee)
Music is an important part of our lives and music emotion recognition is an important field of study with many applications. In this work, we focus on music features extraction and subsequent creation of music emotion recognition system. We extend the work of Hun at al. [2009] in order to create a feed-forward neural network model that predicts emotions from music which we can use in visualization. We confirm the results and discuss their impact. We also provide a C# project to extract several features from music that can be used in Unity together with the demonstration scene that visualize these features. 1
|
|
Automatic recognition of musical notation from audio data
Čermák, Marek ; Lokoč, Jakub (advisor) ; Hajič, Jan (referee)
Title: Automatic recognition of musical notation from audio data Author: Marek Čermák Department: Department of Software Engineering Supervisor: doc. RNDr. Jakub Lokoč, Ph.D. Abstract: The goal of this thesis is the design and implementation of an application using convolutional neural networks to generate musical notation from audio data. The application is able to train a neural network using input files in the MIDI (Musical Instrument Digital Interface) format and pair all sections of the music with their audio form. The training of the neural network can be performed on a user- specified collection of MIDI files or on randomly generated music. Each instrument in the MIDI standard can be assigned a network whose output are the notes playing in the given time section. Continuously iterating over the audio data, the network generates sections of active notes which are then concatenated into the output file. The application is also capable of recognizing words from audio using an external service. Keywords: musical notation, neural network, deep learning, audio recognition, MIDI
|
|
Efficient neural speech synthesis
Vainer, Jan ; Dušek, Ondřej (advisor) ; Hajič, Jan (referee)
While recent neural sequence-to-sequence models have greatly improved the quality of speech synthesis, there has not been a system capable of fast training, fast inference and high-quality audio synthesis at the same time. In this the- sis, we present a neural speech synthesis system capable of high-quality faster- than-real-time spectrogram synthesis, with low requirements on computational resources and fast training time. Our system consists of a teacher and a student network. The teacher model is used to extract alignment between the text to synthesize and the corresponding spectrogram. The student uses the alignments from the teacher model to synthesize mel-scale spectrograms from a phonemic representation of the input text efficiently. Both systems utilize simple convo- lutional layers. We train both systems on the english LJSpeech dataset. The quality of samples synthesized by our model was rated significantly higher than baseline models. Our model can be efficiently trained on a single GPU and can run in real time even on a CPU. 1
|
|
Optical Music Recognition using Deep Neural Networks
Mayer, Jiří ; Pecina, Pavel (advisor) ; Hajič, Jan (referee)
Optical music recognition is a challenging field similar in many ways to optical text recognition. It brings, however, many challenges that traditional pipeline-based recog- nition systems struggle with. The end-to-end approach has proven to be superior in the domain of handwritten text recognition. We tried to apply this approach to the field of OMR. Specifically, we focused on handwritten music recognition. To resolve the lack of training data, we developed an engraving system for handwritten music called Mashcima. This engraving system is successful at mimicking the style of the CVC- MUSCIMA dataset. We evaluated our model on a portion of the CVC-MUSCIMA dataset and the approach seems to be promising. 1
|
|
Controlled Music Generation with Deep Learning
Židek, Marek ; Hajič, Jan (advisor) ; Matzner, Filip (referee)
Generation of musical compositions is one of the hardest tasks for artificial intelligence where most of the current approaches struggle with long term coherence of the generated compositions. This work aims to demonstrate how deep learning models for generating music can be externally controlled to produce compositions with long term coherence, polyphony, and multiple instruments. We work with classical music ranging from compositions for piano through string quartet and up to symphonic orchestral compositions. To control the generation process, we take inspiration from the abstract notion of musical form: normally a high-level description of how similar and dissimilar passages are arranged throughout a composition, we use it as a recipe for generating a coherent composition. To this end, we (1) design a sufficiently general music similarity pseudometric from existing methods, (2) extract musical form from the training data by applying a clustering algorithm over the similarity values, (3) train three models that generate similar and locally coherent dissimilar musical fragments, and (4) design a way how to use the musical forms during the generation process to orchestrate the inference of the three models to generate whole compositions from musical fragments. We show what is the performance of the...
|
|
Optical Recognition of Handwritten Music Notation
Hajič, Jan ; Pecina, Pavel (advisor) ; Fujinaga, Ichiro (referee) ; Černocký, Jan (referee)
Optical Music Recognition (OMR) is the field of computationally reading music notation. This thesis presents, in the form of dissertation by publication, contributions to the theory, resources, and methods of OMR especially for handwritten notation. The main contributions are (1) the Music Notation Graph (MuNG) formalism for describing arbitrarily complex music notation using an oriented graph that can be unambiguously interpreted in terms of musical semantics, (2) the MUSCIMA++ dataset of musical manuscripts with MuNG as ground truth that can be used to train and evaluate OMR systems and subsystems from the image all the way to extracting the musical semantics encoded therein, and (3) a pipeline for performing OMR on musical manuscripts that relies on machine learning both for notation symbol detection and the notation assembly stage, and on properties of the inferred MuNG representation to deterministically extract the musical semantics. While the the OMR pipeline does not perform flawlessly, this is the first OMR system to perform at basic useful tasks over musical semantics extracted from handwritten music notation of arbitrary complexity.
|
|
Automatický expresivní čtený projev
Výkruta, Jan ; Hajič, Jan (advisor) ; Libovický, Jindřich (referee)
Expressive reading is one of possible oral presentations. The text being read is usually prose or poetry. Little has been done in research of what affects expressiveness and whether it can be generated by computers. LibriSpeech, a large scale corpus of read prose and poetry allows us to test generation of expressive reading using machine learning methods. We have focused on poetry as it is generally more expressive. We have prepared methods, that can be used to train more models as well as to prepare different data that could be fed in our learning methods. Moreover, we have developed an extendable application that takes a poem, predicts the reading, visualizes it and plays an audio record generated from the reading using a TTS system. 1
|
|
Využití syntaktické informace pro identifikaci hodnocených entit
Glončák, Vladan ; Hajič, Jan (advisor) ; Helcl, Jindřich (referee)
Opinion Target Extraction (OTE) is a well-established subtask of sentiment analysis. While detecting sentiment polarity is useful in itself, the ability to extract the targets of the opinions allows for more thorough decision making. For example, an owner of a restaurant needs to know whether the guests are complaining about the food, or the ambience, or any other aspect of their establishment, etc. Despite the lexical information being crucial for the task, syntactic structures have potential in being used to correctly decide among multiple candidate entities. Rules based on such structures have been used previously for the task. The objective of this thesis is to investigate, whether syntactic information influences the behavior of the state-of-the-art models such as recurrent neural networks for the OTE task. We did not find any substantial evidence to suggest that adding the syntactic information influences the behavior of the models.
|