東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁 到查詢結果 [ null ]

切換: 標籤 | MARC模式 | ISBD

Towards Understanding and Improving ...

Yasmin, Sonia,

FindBook

Google Book

Amazon

博客來

Towards Understanding and Improving Speech Processing /

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Towards Understanding and Improving Speech Processing // Sonia Yasmin.
作者:	Yasmin, Sonia,
面頁冊數:	1 electronic resource (145 pages)
附註:	Source: Dissertations Abstracts International, Volume: 86-03, Section: A.
Contained By:	Dissertations Abstracts International86-03A.
標題:	Deep learning. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31465227
ISBN:	9798384345152

Towards Understanding and Improving Speech Processing /
Yasmin, Sonia,

Towards Understanding and Improving Speech Processing /Sonia Yasmin. - 1 electronic resource (145 pages)

Source: Dissertations Abstracts International, Volume: 86-03, Section: A.

This dissertation explores mechanisms for understanding and improving speech processing. First, I used EEG to investigate the acoustic and semantic processing of continuous naturalistic speech masked by multi-talker babble. I found that different features of the same speech signal are reflected in different aspects of the neural tracking response, which are themselves differentially affected by noise. These findings point to a complex relationship between speech intelligibility and neural speech encoding.Next, I systematically reviewed the current advancements in speech enhancement technologies. I find that speech enhancement algorithms are limited in their generalizability to speech-noise (i.e., babble). I demonstrate that, for the few studies that do consider babble in their algorithm training, the employed babble sounds reflect extremely high talker-densities, with little variability between babble exemplars. These babble samples do not exhaustively capture the complexities of the natural acoustic environments, hindering the generalizability of speech enhancement algorithms to real-word settings.Finally, I explored novel approaches to speech denoising, including one that incorporates the principles of redundancy reduction. Additionally, I leveraged complex and varying noise types (i.e., babble with variable spectral density) to address the complexity of auditory processing as well as the limited generalizability of other speech enhancement algorithms. A comparison between the redundancy reduction model and a standard denoising model, trained with the same data, demonstrated that the redundancy reduction model performs worse. Nevertheless, both models were able to significantly enhance speech masked by high-variability, low-density babble, an important noise type which had not been explored previously. This study presents the first application, to my knowledge, that considers low-talker density babble (i.e., few number of talkers) sounds for speech masking, which is a complex task for speech enhancement algorithms.This dissertation advanced our understanding of acoustic and semantic speech processing, specifically their complex relationships to masker level. It also identified critical gaps in existing speech denoising methodologies that have important roles in generalizability of speech denoising. Finally, this dissertation introduced novel approaches to speech enhancement that are capable of attenuating challenging and realistic noise types that have previously been neglected in speech enhancement work.

English

ISBN: 9798384345152Subjects--Topical Terms:

3554982
Deep learning.

Towards Understanding and Improving Speech Processing /
LDR:03893nmm a22004333i 4500 001 2429039
005 20250428055551.5
006 m o d
007 cr|nu||||||||
008 261011s2024 miu||||||m |||||||eng d
020 $a 9798384345152
035 $a (MiAaPQD)AAI31465227
035 $a (MiAaPQD)oaiirlibuwocaetd12889
035 $a AAI31465227
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Yasmin, Sonia, $e author. $3 3816645
245 1 0 $a Towards Understanding and Improving Speech Processing / $c Sonia Yasmin.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (145 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 86-03, Section: A.
500 $a Advisors: Johnsrude, Ingrid.
502 $b Ph.D. $c The University of Western Ontario (Canada) $d 2024.
520 $a This dissertation explores mechanisms for understanding and improving speech processing. First, I used EEG to investigate the acoustic and semantic processing of continuous naturalistic speech masked by multi-talker babble. I found that different features of the same speech signal are reflected in different aspects of the neural tracking response, which are themselves differentially affected by noise. These findings point to a complex relationship between speech intelligibility and neural speech encoding.Next, I systematically reviewed the current advancements in speech enhancement technologies. I find that speech enhancement algorithms are limited in their generalizability to speech-noise (i.e., babble). I demonstrate that, for the few studies that do consider babble in their algorithm training, the employed babble sounds reflect extremely high talker-densities, with little variability between babble exemplars. These babble samples do not exhaustively capture the complexities of the natural acoustic environments, hindering the generalizability of speech enhancement algorithms to real-word settings.Finally, I explored novel approaches to speech denoising, including one that incorporates the principles of redundancy reduction. Additionally, I leveraged complex and varying noise types (i.e., babble with variable spectral density) to address the complexity of auditory processing as well as the limited generalizability of other speech enhancement algorithms. A comparison between the redundancy reduction model and a standard denoising model, trained with the same data, demonstrated that the redundancy reduction model performs worse. Nevertheless, both models were able to significantly enhance speech masked by high-variability, low-density babble, an important noise type which had not been explored previously. This study presents the first application, to my knowledge, that considers low-talker density babble (i.e., few number of talkers) sounds for speech masking, which is a complex task for speech enhancement algorithms.This dissertation advanced our understanding of acoustic and semantic speech processing, specifically their complex relationships to masker level. It also identified critical gaps in existing speech denoising methodologies that have important roles in generalizability of speech denoising. Finally, this dissertation introduced novel approaches to speech enhancement that are capable of attenuating challenging and realistic noise types that have previously been neglected in speech enhancement work.
546 $a English
590 $a School code: 0784
650 4 $a Deep learning. $3 3554982
650 4 $a Electrodes. $3 629151
650 4 $a Neural networks. $3 677449
650 4 $a Hearing loss. $3 3697149
650 4 $a Podcasts. $3 1016547
650 4 $a Natural language processing. $3 1073412
650 4 $a Electroencephalography. $3 543293
650 4 $a Digital broadcasting. $3 3560842
650 4 $a Acoustics. $3 879105
650 4 $a Speech. $3 530580
650 4 $a Hearing aids. $3 634669
650 4 $a Ears & hearing. $3 3685904
650 4 $a Cognition & reasoning. $3 3556293
650 4 $a Semantics. $3 520060
650 4 $a Sound. $3 542298
650 4 $a Audiology. $3 537237
650 4 $a Cognitive psychology. $3 523881
650 4 $a Film studies. $3 2122736
650 4 $a Logic. $3 529544
650 4 $a Neurosciences. $3 588700
690 $a 0800
690 $a 0986
690 $a 0300
690 $a 0633
690 $a 0900
690 $a 0395
690 $a 0317
710 2 $a The University of Western Ontario (Canada). $e degree granting institution. $3 3759225
720 1 $a Johnsrude, Ingrid $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-03A.
790 $a 0784
791 $a Ph.D.
792 $a 2024
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31465227