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 15 of 15 for “"forced alignment"”.
-
The Variable Pronunciations of Word-final Consonant Clusters in a Force Aligned Corpus of Spoken French
… questions were addressed. Can a system of forced alignment reliably reproduce pronunciation judgements that closely match those of a human researcher? How do variables, such as speech style, following context, motivation for simplification and speech rate, affect the variable pronunciations …
-
Bayesian Alignment Prior to Connectionist Temporal Classification Loss
… Temporal Classification (CTC) loss and forced alignment to support longer input sequences. CTC loss is normally used for training in speech and handwriting recognition tasks when the labels are not fully aligned with the data, while forced alignment is a downstream task that finds the …
-
Temporal effects of word and song-level prominence in the vowels of Estonian regilaul folksongs
… is facilitated by beat tracking software and forced alignment of phonemic transcriptions. Text data is analyzed in Python using language-specific NLP tools and then aggregated with the acoustic signal and the corresponding interval annotations of beat strength and phonemic transcription. …
-
Investigating the Corpus Phonetics Pipeline Applied to Diverse Speech Data
… apply novel techniques to improve the phonetic forced alignment of low-resource field data, a challenging yet important process in language documentation. We encourage the research community to continue developing tools to aid in language documentation and cross-linguistic research. In doing so, …
-
The permeability of dialect boundaries: a case study of the region surrounding Erie, Pennsylvania
… the methodology of transcription and subsequent forced alignment was applied. In order to reduce error in the formant measurements, automatic techniques for measurement point selection and formant prediction were developed. The acoustic analysis focuses on aspects of the vowel system that …
-
Continuous Unsupervised Topic Adaptation for Morph-based Speech Recognition
… for mis-recognized words are recovered by using forced alignment and Viterbi decoding. A collection of recovered pronunciation rules can be used for the recognition of new speech data. Experiments showed some minor improvements in the recognition of foreign names using user feedback based lexicon …
-
Locating and interpreting factual association in Speech Language Models
… discrete speech tokens. We use a CTC-based forced alignment algorithm to locate targeted words in a spoken utterance, map discrete speech tokens to text equivalents, and visualize CMA results across speech and text modalities. We applied MultimodalCausalTracer to the Spirit LM model using a …
-
Sociophonetics and class differentiation: A study of working- and middle- class English in Cape Town's coloured community
… acoustic data were processed using methods of Forced Alignment and automatic formant extraction – methods applied for the first time to any variety of South African English. The results of the analysis were found generally to support the findings of scholars who have documented this variety …
-
Automatic analysis of magnetic resonance images of speech articulation
… acoustic segments and images is established by forced alignment of speech signals recorded during the articulation. We obtain speaker-specific typical phoneme articulations that represent general articulatory configurations in running speech. Articulation dynamics are parametrised by measuring …
-
Computational Approaches to the Syntax–Prosody Interface: Using Prosody to Improve Parsing
… native speaker judgment and automatic methods (forced alignment). Results demonstrate similar prosodic splitting behavior as in English in contradiction to the original study’s findings.</p> <p>Chapter 3 presents a number of studies examining whether syntactic ambiguity can yield different …
-
Automatic Speech Recognition for Documenting Endangered First Nations Languages
… acoustic model can also be used as a separate forced alignment tool for the automatic alignment of training data. The results show that the GMM-HMM methods outperform deep hybrid models in low-resource acoustic modeling. In our second approach, we propose using Domain-adapted Cross-lingual …
-
Engelbert Dollfuss and the destruction of Austrian democracy
… more out of necessity than desire. Dollfuss' forced alignment with the Heimwehr, a right-wing organization motivated by fascist principles, was the first clear indication that Austrian politics were henceforth to move in an anti-democratic direction. The refusal of the Social Democrats to join …
-
Selective silicon and germanium nanoparticle deposition on amorphous surfaces
… process known as graphoepitaxy. In graphoepitaxy forced alignment within microscopic features occurs provided certain dimensional constraints are satisfied. Graphoepitaxy was attempted to precisely locate 20 nm diameter features for selective Ge or Si deposition and initial studies are presented. …
-
Zobrazování uživatelských výslovností pro elektronické slovníky
Tato bakalářská práce se pokouší nalézt nový směr vývoje v oblasti učebních schopností elektronických slovníků. V první části je uvedeno představení základní myšlenky možnosti učení výslovnosti pomocí vizualizace fonémů. Následuje kapitola zabývající se obecným úvodem do metod zpracování řeči …
-
Ο Άγιος Νικηφόρος Πατριάρχης Κωνσταντινουπόλεως ο ομολογητής: βίος και έργα
… problems of the Church. First of all, he was forced to control many abuses in the monastic life due to the existence and operation of many "double monasteries" or "twins" that had a common spiritual leadership and property (although the Seventh Ecumenical Council of 787 with its 20th canon …