|
|
Exploring New Paths in Neural-Network-Based Speaker Recognition
Sova, Damián ; Matějka, Pavel (referee) ; Glembek, Ondřej (advisor)
Since the assignment of this work is very broad, it was necessary to focus only on a certain area. In the end, this work aims to apply the Stochastic Weight Averaging optimization method to the training process of the Deep Neural Network. After presenting the necessary theoretical knowledge in the first part of the work, the second part with the experiments courses follows. In the theoretical part, the main focus is on presenting the complete lifecycle of the training and evaluation process, including a description of each component. The practical part provides a detailed look at each experiment, intended to demonstrate the effectiveness of the overall speaker recognition system's performance enhancement. The overall performance improvement is achieved by gradually applying various training configurations where the experience from previous experiments is taken into account. The key ingredient to the successful Stochastic Weight Averaging in the experiments was a sufficiently high Learning Rate value with the successive transition applied or Cyclic course of the Learning Rate.
|
|
|
Unsupervised Evaluation of Speaker Recognition System
Odehnal, Ondřej ; Plchot, Oldřich (referee) ; Matějka, Pavel (advisor)
Tato práce je vystavěna nad moderním systémem pro rozpoznávání mluvčího (SID) založeného na x-vektorech. Cílem bakalářské práce je navrhnout a experimentálně vyhodnotit techniky pro evaluaci SID systému za použití audio nahrávek bez anotace tj. bez znalosti mluvčího. Pro tento účel je z každé nahrávky bez anotace vytvořen embedding. Ty se poté používají pro shlukování nahrávek a následné vytvoření pseudo-anotací. Na těchto anotacích se SID systém evaluuje pomocí equal error rate (EER) metriky. Za účelem vytvoření pseudo-anotací byly navrženy tyto shlukovací algoritmy učení bez učitele: K-means, Gaussian mixture models (GMM) a aglomerativní shlukování. Po testování vyšel jakožto nejlepší experimentální postup K-means se Silhouette metrikou, která používá kosinovou podobnost jako míru vzdálenosti. Nejlepší metoda dosáhla 5,72 % EER s referenčním EER = 5,15 %, které bylo spočítané se znalostí anotace na části datasetu SITW dev-core-core. Podobné výsledky byly získány na části datasetu SITW eval-core-core s odhadnutým EER = 5,86 % a referenčním 5,08 %. Rozdíl mezi hodnotami tvoří 0,57 % pro eval-core-core a 0, 78% pro dev-core-core. Další testy na NIST SRE16 a VoxCeleb1 datasetech byly provedeny za účelem ověření správnosti navrženého postupu. Obecně se dá říct, že navržený testovací postup měl chybu přibližně 1 %, což je poměrně dobrý výsledek pro algoritmus učení bez učitele.
|
|
|
Learning the Face Behind a Voice
Krušina, Josef ; Matějka, Pavel (referee) ; Plchot, Oldřich (advisor)
This work addresses the problem of mapping fixed representations (embeddings) of a speech signal to face embeddings and then generating a face from the mapped embedding using a generative adversarial network (GAN) that was trained for face generation. GANs are a type of neural networks that can generate data similar to the data they were trained on. The architecture of the proposed system is based on four components: a face embedding extractor, a voice embedding extractor, an algorithm on top of a GAN that can generate a face from a face embedding, and my mapping network used to map a voice embedding to a face embedding. The pre-trained neural networks FaceNet and SpeechBrain are adopted as embedding extractors. A model that uses a pre-trained StyleGAN2 is adopted for backward face generation. The contribution of this work is that it allows the extrapolation of a face from audio signal only.
|
|
| |
|
|
Magnetic circular dichroism and aromatic compounds
Štěpánek, Petr ; Bouř, Petr (advisor) ; Matějka, Pavel (referee) ; Srnec, Martin (referee)
Title: Magnetic circular dichroism and aromatic compounds Author: Petr Štěpánek Department/Institute: Institute of Organic Chemistry and Biochemistry AS CR, v.v.i. Supervisor: prof. RNDr. Petr Bouř, DSc., Institute of Organic Chemistry and Biochemistry AS CR, v.v.i. Abstract: The thesis presents a series of studies concerning magnetic circular dichroism (MCD), a spectroscopic method, which experienced an intense theo- retical development in the recent years. New computational codes opened possi- bilities to calculate MCD spectra of larger and more varied molecules than was possible in the past. In the presented studies, we took the advantage of the new computational codes to broaden the possible span of applications of the MCD technique. As an example, we present MCD as a method useful for obtaining information about the structure of fullerenes. We also studied the influence of the molecular conformation and the explicit and implicit solvent models on the MCD spectra of aromatic amino acids using the newly implemented alterna- tive computational protocol based on sum-over-states calculations. We have also theoretically predicted spectra of the nuclear spin circular dichroism (NSCD), a potential new high-resolution spectroscopy. Keywords: magnetic circular dichroism, quantum-chemical calculations, density...
|
|
| |
|
|
Learning the Face Behind a Voice
Kyjonka, Mojmír ; Matějka, Pavel (referee) ; Plchot, Oldřich (advisor)
This thesis deals with face reconstruction based on voice. The state of the art of this problem is investigated and model for such problem is trained. Model used in this thesis is based on the work "Reconstructing faces from voices" which architecture is based on Generative Adversarial Network (GAN). In this work, we used VGGFace and VoxCeleb datasets, and additionally, we created a small audiovisual dataset of Czech speakers. This work was implemented using the Python scripting language and PyTorch library.
|
|
|
Analysis of Interview Audio
Polok, Alexander ; Plchot, Oldřich (referee) ; Matějka, Pavel (advisor)
The aim of this thesis is the analysis of psychotherapeutic sessions. Classifiers describing the therapy are extracted from the audio recordings. These are then aggregated, compared with other sessions, and graphically presented in a report summarizing the conversation. In this way, therapists are provided with feedback that can serve for professional growth and better psychotherapy in the future.
|
|
|
Detection of Pre-Recorded Messages in Speech
Boboš, Dominik ; Matějka, Pavel (referee) ; Černocký, Jan (advisor)
Rozpoznání před-nahraných zpráv v řeči (tzv. plechové huby) je užitečné pro jakékoliv následující dolování informací v řečových datech. Tato práce shrnuje teorii hledání podobných promluv v řeči a efektivní přístupy k porovnání dvou sekvencí. Ke zkoumání identifikace opakujících se informací v audiu je nutné mít velké množství dat s přesně se opakujícími úseky. Takovou datovou sadu jsme vygenerovali smícháním předem nahraných zpráv s telefonními hovory se změnami rychlosti, hlasitosti a opakování. Náš systém řeší scénáře "známých zpráv a "neznámých zpráv pomocí shlukování nebo detekce v blocích. Porovnali jsme techniky dynamického borcení času (DTW), přibližné shody řetězců a rekurentní kvantifikační analýzy, a nakonec jsme všechny uvedené techniky zkombinovali a získali tak přesný a efektivně pracující systém.
|
|
|
Robust Speaker Verification with Deep Neural Networks
Profant, Ján ; Rohdin, Johan Andréas (referee) ; Matějka, Pavel (advisor)
The objective of this work is to study state-of-the-art deep neural networks based speaker verification systems called x-vectors on various conditions, such as wideband and narrowband data and to develop the system, which is robust to unseen language, specific noise or speech codec. This system takes variable length audio recording and maps it into fixed length embedding which is afterward used to represent the speaker. We compared our systems to BUT's submission to Speakers in the Wild Speaker Recognition Challenge (SITW) from 2016, which used previously popular statistical models - i-vectors. We observed, that when comparing single best systems, with recently published x-vectors we were able to obtain more than 4.38 times lower Equal Error Rate on SITW core-core condition compared to SITW submission from BUT. Moreover, we find that diarization substantially reduces error rate when there are multiple speakers for SITW core-multi condition but we could not see the same trend on NIST SRE 2018 VAST data.
|
guest ::
RSS feed.