Del i serien Synthesis Lectures on Speech and Audio Processing

Acoustic Cues in the Disambiguation of Polysemous Strings

Inbunden, Engelska, 2024

AvMaja Gwóźdź

719 kr

Beställningsvara. Skickas inom 10-15 vardagar. Fri frakt för medlemmar vid köp för minst 249 kr.

Finns i fler format (1)

Häftad

719 kr

Skickas inom 10-15 vardagar

This book provides an analysis of acoustic features of polysemous strings and an implementation of a speech disambiguation program based on the phonetic information. Throughout the book, the term ‘polysemous string’ refers to idioms with plausible literal interpretations, restrictive and non–restrictive relative clauses, and the same expressions used as quotations and appearing in a non–quotational context. The author explains how, typically, context is sufficient to determine the intended meaning. But there is enough evidence in psycholinguistic and phonetic literature to suspect that these superficially identical strings exhibit different acoustic features. In the experiment presented in the book, the participants were asked to read short excerpts containing corresponding elements of polysemous strings placed in the same intonational position. The acoustic analyses of ditropic pairs and subsequent statistical tests revealed that there is almost no difference in the duration, pitch, or intensity in literal and figurative interpretations. However, the analysis of relative clauses and quotations demonstrated that speakers are more likely to use acoustic cues to differentiate between the two possible readings. The book argues that the acoustic analysis of polysemous phrases could be successfully implemented in designing automatic speech recognition systems in order to improve their performance in disambiguating polysemous phrases.Analyzes acoustic features of polysemous strings and an implementation of a speech disambiguation programIncludes evidence that superficially identical strings exhibit different acoustic featuresArgues that acoustic analysis of polysemous phrases can be successfully implemented in automatic speech recognition

Produktinformation

Utgivningsdatum2024-01-05
Mått168 x 240 x 13 mm
Vikt385 g
FormatInbunden
SpråkEngelska
SerieSynthesis Lectures on Speech and Audio Processing
Antal sidor99
FörlagSpringer International Publishing AG
ISBN9783031466793

Tillhör följande kategorier

Maja Gwozdz studied diverse areas of Linguistics, with a particular interest in logical approaches to semantics, phraseology, and semiotics, before pursuing a graduate degree in Theoretical Computer Science. Her current interests include the (broadly defined) intersection of pure mathematics and computational approaches. She also enjoys analysing the properties of non-standard models of computation and inventing new ones.

Mer från samma serie

Articulation and Intelligibility

Jont B. Allen

Häftad, 2007

409 kr

Dynamic Speech Models

Li Deng

Häftad, 2007

479 kr

Latent Semantic Mapping

Jerome R. Bellegarda

Häftad, 2007

479 kr

Discriminative Learning for Speech Recognition

Xiadong He, Li Deng

Häftad, 2008

479 kr

Multi-Pitch Estimation

Mads Christensen, Andreas Jakobsson

Häftad, 2009

479 kr

Sparse Adaptive Filters for Echo Cancellation

Constantin Paleologu, Jacob Benesty, Silviu Ciochina

Häftad, 2010

409 kr

Speech Enhancement in the Karhunen-Loeve Expansion Domain

Jacob Benesty, Jingdong Chen, Yiteng Huang

Häftad, 2011

479 kr

Perspective on Single-Channel Frequency-Domain Speech Enhancement

Jacob Benesty, Yiteng Huang

Häftad, 2011

479 kr

Speech Recognition Algorithms Using Weighted Finite-State Transducers

Takaaki Hori, Atsushi Nakamura

Häftad, 2012

509 kr

Articulatory Speech Synthesis from the Fluid Dynamics of the Vocal Apparatus

Stephen Levinson, Don Davis, Scott Slimon, Jun Huang

Häftad, 2012

479 kr

Du kanske också är intresserad av