東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Towards Human-Level Speech Synthesis...

Li, Yinghao Aaron,

Linked to FindBook

Google Book

Amazon

博客來

Towards Human-Level Speech Synthesis: Bridging Generative Models and Computational Neuroscience /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Towards Human-Level Speech Synthesis: Bridging Generative Models and Computational Neuroscience // Yinghao Aaron Li.
Author:	Li, Yinghao Aaron,
Description:	1 electronic resource (150 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 86-10, Section: A.
Contained By:	Dissertations Abstracts International86-10A.
Subject:	Computer science. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31843803
ISBN:	9798310373365

Towards Human-Level Speech Synthesis: Bridging Generative Models and Computational Neuroscience /
Li, Yinghao Aaron,

Towards Human-Level Speech Synthesis: Bridging Generative Models and Computational Neuroscience /Yinghao Aaron Li. - 1 electronic resource (150 pages)

Source: Dissertations Abstracts International, Volume: 86-10, Section: A.

Recent advancements in speech synthesis technology have made significant strides, but achieving truly human-like speech remains a fundamental challenge. This dissertation presents a unified framework for decomposing speech into interpretable components - text content and speaking style - while preserving natural prosody and speaker characteristics. Through a series of innovative models and techniques, I demonstrate how this disentangled representation approach, informed by principles of human speech processing, can generate speech that is more natural, expressive, and perceptually aligned with human listeners, advancing one step further to human-level speech synthesis.The thesis traces the evolution of style-based speech generation, from the foundations laid by StarGANv2-VC for unsupervised voice conversion to the development of StyleTTS, the first text-to-speech system to achieve human-level naturalness on public benchmark datasets. Throughout the chapters, I introduce various advanced techniques, such as transferable monotonic aligners for improved prosody, adversarial training with large speech language models, and direct optimization of perceptually relevant metrics.A central theme that emerges is the convergence between successful AI architectures and patterns of human neural processing. Analysis of intracranial recordings and language model representations reveals that modern AI models naturally develop hierarchical feature extraction pathways for contextual information mirroring those in the auditory cortex. Leveraging this insight, innovations such as phoneme-level self-supervised pre-training (PL-BERT) and time-varying style modeling (StyleTTS-ZS) demonstrate the benefits of incorporating neural-inspired processing principles. The culmination of this research is Style-Talker, an end-to-end speech-to-speech interaction framework that seamlessly integrates text understanding, style generation, and neural-aligned fine-tuning. By teaching language models to jointly generate what to say and how to say it, Style-Talker achieves highly efficient dialogue generation with context-appropriate prosody and emotional delivery.The technical contributions of this dissertation include: (1) an unsupervised voice conversion framework that generalizes across languages and speaking styles, (2) the first text-to-speech system to achieve human-level performance on public benchmark datasets through style-based generation, (3) an efficient zero-shot speaker adaptation technique using distilled diffusion models, and (4) empirical evidence linking successful generative model architectures to human cognitive processing mechanisms. My models achieve state-of-the-art performance across multiple tasks while maintaining computational efficiency, as demonstrated through extensive evaluations on standard benchmarks. Beyond advancing the state-of-the-art, this dissertation establishes a new paradigm for speech synthesis research at the intersection of generative modeling, computational neuroscience, and human perception. The models developed not only demonstrate superior performance and efficiency, but also illuminate fundamental principles for bridging artificial and biological speech processing. In laying this groundwork, the thesis opens pathways toward next-generation speech technologies that think, understand, and communicate in increasingly human-like ways.

English

ISBN: 9798310373365Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

Speech synthesis

Towards Human-Level Speech Synthesis: Bridging Generative Models and Computational Neuroscience /
LDR:04881nmm a22004453i 4500 001 2433242
005 20250825104031.5
006 m o d
007 cr|nu||||||||
008 261011s2025 miu||||||m |||||||eng d
020 $a 9798310373365
035 $a (MiAaPQD)AAI31843803
035 $a AAI31843803
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Li, Yinghao Aaron, $e author. $3 3822774
245 1 0 $a Towards Human-Level Speech Synthesis: Bridging Generative Models and Computational Neuroscience / $c Yinghao Aaron Li.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2025
300 $a 1 electronic resource (150 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: 86-10, Section: A.
500 $a Advisors: Mesgarani, Nima Committee members: Wright, John; Hirschberg, Julia; Paisley, John; Chen, Zhuo.
502 $b Ph.D. $c Columbia University $d 2025.
520 $a Recent advancements in speech synthesis technology have made significant strides, but achieving truly human-like speech remains a fundamental challenge. This dissertation presents a unified framework for decomposing speech into interpretable components - text content and speaking style - while preserving natural prosody and speaker characteristics. Through a series of innovative models and techniques, I demonstrate how this disentangled representation approach, informed by principles of human speech processing, can generate speech that is more natural, expressive, and perceptually aligned with human listeners, advancing one step further to human-level speech synthesis.The thesis traces the evolution of style-based speech generation, from the foundations laid by StarGANv2-VC for unsupervised voice conversion to the development of StyleTTS, the first text-to-speech system to achieve human-level naturalness on public benchmark datasets. Throughout the chapters, I introduce various advanced techniques, such as transferable monotonic aligners for improved prosody, adversarial training with large speech language models, and direct optimization of perceptually relevant metrics.A central theme that emerges is the convergence between successful AI architectures and patterns of human neural processing. Analysis of intracranial recordings and language model representations reveals that modern AI models naturally develop hierarchical feature extraction pathways for contextual information mirroring those in the auditory cortex. Leveraging this insight, innovations such as phoneme-level self-supervised pre-training (PL-BERT) and time-varying style modeling (StyleTTS-ZS) demonstrate the benefits of incorporating neural-inspired processing principles. The culmination of this research is Style-Talker, an end-to-end speech-to-speech interaction framework that seamlessly integrates text understanding, style generation, and neural-aligned fine-tuning. By teaching language models to jointly generate what to say and how to say it, Style-Talker achieves highly efficient dialogue generation with context-appropriate prosody and emotional delivery.The technical contributions of this dissertation include: (1) an unsupervised voice conversion framework that generalizes across languages and speaking styles, (2) the first text-to-speech system to achieve human-level performance on public benchmark datasets through style-based generation, (3) an efficient zero-shot speaker adaptation technique using distilled diffusion models, and (4) empirical evidence linking successful generative model architectures to human cognitive processing mechanisms. My models achieve state-of-the-art performance across multiple tasks while maintaining computational efficiency, as demonstrated through extensive evaluations on standard benchmarks. Beyond advancing the state-of-the-art, this dissertation establishes a new paradigm for speech synthesis research at the intersection of generative modeling, computational neuroscience, and human perception. The models developed not only demonstrate superior performance and efficiency, but also illuminate fundamental principles for bridging artificial and biological speech processing. In laying this groundwork, the thesis opens pathways toward next-generation speech technologies that think, understand, and communicate in increasingly human-like ways.
546 $a English
590 $a School code: 0054
650 4 $a Computer science. $3 523869
650 4 $a Nanoscience. $3 587832
650 4 $a Language. $3 643551
650 4 $a Communication. $3 524709
653 $a Speech synthesis
653 $a StarGANv2-VC
653 $a Computational neuroscience
653 $a AI models
690 $a 0800
690 $a 0984
690 $a 0565
690 $a 0679
690 $a 0459
710 2 $a Columbia University. $b Electrical Engineering. $e degree granting institution. $3 3816024
720 1 $a Mesgarani, Nima $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-10A.
790 $a 0054
791 $a Ph.D.
792 $a 2025
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31843803