Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 13 of 13 for “"Spoken language processing"”.
-
Phonological prediction in spoken language processing
Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2024-12-01
-
Transfer Learning For Spoken Language Processing
… thesis develops transfer learning paradigms for spoken language processing applications. In particular, we tackle domain adaptation in the context of Automatic Speech Recognition (ASR) and Cross-Lingual Learning in Automatic Speech Translation (AST). The first part of the thesis develops an …
-
Improving Cascaded Systems in Spoken Language Processing
Spoken language processing encompasses a broad range of speech production and perception tasks. One of the central challenges in building spoken language systems is the lack of end-to-end training corpora. For example in spoken language translation, there is little annotated data that directly …
-
Spoken Language Processing and Modeling for Aviation Communications
… aviation-specific corpora, applying natural language processing technologies, especially those based on transformer neural networks, to aviation communications is becoming increasingly feasible. Previous work has focused on machine learning applications to natural language processing, such as …
-
The Use of Language Models in End-to-End Spoken Language Processing
… modelling approach has achieved great success in spoken language processing including automatic speech recognition (ASR) and speech translation (ST). E2E spoken language processing systems have many advantages compared to cascaded systems, including global optimisation, a simplified pipeline, and …
-
Language Modeling from Visually Grounded Speech
Recent advancements in spoken language processing have significantly reduced automatic speech recognition (ASR) error rates, driven by large-scale supervised training on paired speech–text data and, more recently, self-supervised pre-training on unpaired speech and audio. These methods have …
-
A Study of Semantic Association and Reference in the Visual World Paradigm
… provides an in-depth look at how the memory and language systems interact during spoken language comprehension. Experiment 1 examines how the strength of associative relationships in memory, as measured by lexical co-occurrence based corpus-derived scores (Mutual Information), affects spoken …
-
Self-Supervised Learning for Speech Processing
… have achieved remarkable performance on various spoken language processing applications, often being the state of the arts on the corresponding leaderboards. However, the fact that training these systems relies on large amounts of annotated speech poses a scalability bottleneck for the continued …
-
Prosodic phrase boundary perception in adults and infants
… rich source of information that heavily supports spoken language comprehension. In particular, prosodic phrase boundaries divide the continuous speech stream into chunks reflecting the semantic and syntactic structure of an utterance. This chunking or prosodic phrasing plays a critical role in …
-
Understanding language and attention: brain-based model and neurophysiological experiments
… of the neuronal mechanisms at the basis of language acquisition and processing, and the complex interactions of language and attention processes in the human brain. In particular, this research was motivated by two sets of existing neurophysiological data which cannot be reconciled on the …
-
Adversarial Attacks on Natural Language and Speech Processing Models
… of applications in computer vision, natural language processing, and speech processing. Despite their high performance, deep learning models are vulnerable to adversarial attacks. A deliberate and specific perturbation of a clean input sample can create an adversarial example, which, when …
-
Speech Foundation Models for Audio Processing
… significantly shaped the development of natural language and speech technologies. Foundation speech models such as Whisper have shown strong performance across a variety of audio processing tasks, including automatic speech recognition (ASR) and speech translation. Unlike traditional systems that …
-
One of a kind. The processing of indefinite one-anaphora in spoken Danish
It is a hallmark of natural language use that the way we talk about something reflects how it is represented in the mind of our conversation partner. This thesis studies the use and cognitive processing of referring expressions like one in comparison with other expression types in spoken Danish. …