|
|
Acoustic Detection of Speaker Position Using Microphone Array
Chu, Yen Nhi ; Žmolíková, Kateřina (referee) ; Szőke, Igor (advisor)
The purpose of this thesis is to create a system for detection of speaker position in a closed room equipped with microphone array. It deals with two algorithms for sound source localization, namely beamforming and time difference of arrival. The methods were implemented on the provided hardware, reliability of the methods was tested and results were evaluated. The results have shown that both used methods were relatively accurate if used in small space (approx. 3×3 m). Shortcomings of the solution were analyzed in detail, possible improvements were proposed. This work can be used as a basis for creating embedded systems for sound source localization.
|
|
|
Microphone arrays for spatial separation of acoustic signals
Grobelný, Petr ; Schimmel, Jiří (referee) ; Míča, Ivan (advisor)
The goal of this master’s thesis is to explore the possibilities of multichannel localization of acoustic signal sources and their following application on a real signal localization and separation, using Beamforming methods. During this thesis two beamforming methods were selected, namely Delay and Sum a Constant Directivity Beamforming - Circular Arrays, and were applicated on real environment signals using two microphone arrays’ geometries ULA (Uniform linear array) and UCA (Uniform Circular array).
|
|
|
Information Combination Analysis in Multi-Channel Speaker Verification
Procházka, Jan ; Plchot, Oldřich (referee) ; Mošner, Ladislav (advisor)
In this work, we deal with the analysis and comparison of information combinations of multi-channel speech data for a speaker verification task. Three levels/representations were chosen for data fusion: signal-level, embedding-level, and score-level. At the signal level, spatial filters (beamforming) are implemented. Speech recordings serve as input to a neural network (ECAPA-TDNN architecture) that extracts embeddings, vector representations of the speaker. The vectors are further compared by cosine similarity module that results in scores, real numbers. Score-level fusion achieves the best relative improvement against single-channel recordings (up to 70 %). Embedding-level fusion provides the most consistent results for different recording conditions.
|
|
|
Acoustic Detection of Speaker Position Using Microphone Array
Chu, Yen Nhi ; Žmolíková, Kateřina (referee) ; Szőke, Igor (advisor)
The purpose of this thesis is to create a system for detection of speaker position in a closed room equipped with microphone array. It deals with two algorithms for sound source localization, namely beamforming and time difference of arrival. The methods were implemented on the provided hardware, reliability of the methods was tested and results were evaluated. The results have shown that both used methods were relatively accurate if used in small space (approx. 3×3 m). Shortcomings of the solution were analyzed in detail, possible improvements were proposed. This work can be used as a basis for creating embedded systems for sound source localization.
|
|
|
Microphone arrays for spatial separation of acoustic signals
Grobelný, Petr ; Schimmel, Jiří (referee) ; Míča, Ivan (advisor)
The goal of this master’s thesis is to explore the possibilities of multichannel localization of acoustic signal sources and their following application on a real signal localization and separation, using Beamforming methods. During this thesis two beamforming methods were selected, namely Delay and Sum a Constant Directivity Beamforming - Circular Arrays, and were applicated on real environment signals using two microphone arrays’ geometries ULA (Uniform linear array) and UCA (Uniform Circular array).
|
guest ::
