Filters








3,748 Hits in 9.2 sec

Linguistic-Acoustic Similarity Based Accent Shift for Accent Recognition [article]

Qijie Shao, Jinghao Yan, Jian Kang, Pengcheng Guo, Xian Shi, Pengfei Hu, Lei Xie
2022 arXiv   pre-print
But due to the lack of native utterance as an anchor, estimating the accent shift is difficult. In this paper, we propose linguistic-acoustic similarity based accent shift (LASAS) for AR tasks.  ...  For an accent speech utterance, after mapping the corresponding text vector to multiple accent-associated spaces as anchors, its accent shift could be estimated by the similarities between the acoustic  ...  Inspired by these works, in this paper, we propose linguistic-acoustic similarity based accent shift (LASAS) for AR tasks.  ... 
arXiv:2204.03398v2 fatcat:m76k6qdvrzdbrjjohr45bl7rz4

Detection-based accented speech recognition using articulatory features

Chao Zhang, Yi Liu, Chin-Hui Lee
2011 2011 IEEE Workshop on Automatic Speech Recognition & Understanding  
We propose an attribute-based approach to accented speech recognition based on automatic speech attribute transcription with high efficiency detection of articulatory features.  ...  Our method yields a significant absolute phone recognition accuracy improvement 5.04%, 4.68% and 6.06% for the corresponding three accent types over a conventional monophone HMM system.  ...  ACKNOWLEDGMENT The first author would like to thank Xuan Wang at Beijing Language and Culture University, advising the linguistic knowledge utilized and helping to improve the English writing.  ... 
doi:10.1109/asru.2011.6163982 dblp:conf/asru/ZhangLL11 fatcat:3wm7ir75izeupn26hyxzmwp23u

Fast accent identification and accented speech recognition

Liu Wai Kat, P. Fung
1999 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258)  
The use of this accent-adapted dictionary reduces recognition error rate by 13.5%, similar to the results obtained from a longer, data-driven process.  ...  We also present our ndings in acoustic features sensitive to a Cantonese accent, and possibly other Asian language accents.  ...  We propose a hybrid of using both feature-based and model-based discrimination. For fast accent classi cation using small amount of data, we do not use phoneme-based HMM for recognition.  ... 
doi:10.1109/icassp.1999.758102 dblp:conf/icassp/LiuF99 fatcat:aniay2unkvhwlajjnaucnekscq

Identification of British English regional accents using fusion of i-vector and multi-accent phonotactic systems

Maryam Najafian, Saeid Safavi, Phil Weber, Martin Russell
2016 Odyssey 2016  
For Accent Identification (AID), acoustic methods exploit differences between the distributions of sounds, while phonotactic approaches exploit the sequences in which these sounds occur.  ...  This paper is concerned with recognition of the 14 regional accents of British English.  ...  Related work Similar to LID, different approaches in AID can be partitioned into acoustic based methods, such as i-vectors [30, 31, 33] , and phonotactic based methods, such as Phone Recognition followed  ... 
doi:10.21437/odyssey.2016-19 dblp:conf/odyssey/Najafian0WR16 fatcat:ickejybi7zdgrem4mv6jy3duc4

The socially weighted encoding of spoken words: a dual-route approach to speech perception

Meghan Sumner, Seung Kyung Kim, Ed King, Kevin B. McGowan
2014 Frontiers in Psychology  
We propose that learned acoustic patterns are mapped simultaneously to linguistic representations and to social representations.  ...  Our proposal includes a dual-route approach to speech perception in which listeners map acoustic patterns in speech to linguistic and social representations in tandem.  ...  ACKNOWLEDGMENTS We are indebted to the Stanford Phonetics Community for helpful discussion. We are grateful to Annette D'Onofrio and Roey Gafter for valuable comments and feedback.  ... 
doi:10.3389/fpsyg.2013.01015 pmid:24550851 pmcid:PMC3913881 fatcat:3sxueyhm25awvdzisrg3xjasoq

Effects and modeling of phonetic and acoustic confusions in accented speech

Pascale Fung, Yi Liu
2005 Journal of the Acoustical Society of America  
Accented speech recognition is more challenging than standard speech recognition due to the effects of phonetic and acoustic confusions.  ...  Since low phonetic confusion units in accented speech do not give rise to automatic speech recognition errors, we focus on analyzing and reducing phonetic and acoustic confusability under high phonetic  ...  For example, the articulatory features of the retroflexed affricative /zh/ are similar to those of the dental velar /z/ for Cantonese-accented speakers.  ... 
doi:10.1121/1.2035588 pmid:16334699 fatcat:cfxfqh6lpncu3doxogz4omayaq

Combined Gesture-Speech Analysis and Speech Driven Gesture Synthesis

M.E. Sargin, O. Aran, A. Karpov, F. Ofli, Y. Yasinnik, S. Wilson, E. Erzin, Y. Yemez, A.M. Tekalp
2006 2006 IEEE International Conference on Multimedia and Expo  
The detection of gestures is based on discrete predesignated symbol sets, which are manually labeled during the training phase.  ...  A speech driven gesture animation example has been implemented for demonstration.  ...  The usage of HMMs for gesture recognition is motivated by the similarities between gesture and speech. Yang et. al., summarizes these similarities in [8] .  ... 
doi:10.1109/icme.2006.262663 dblp:conf/icmcs/SarginAKOYWEYT06 fatcat:if5kle7t3za5bcwfcslqxmvt6m

Reliable Accent-Specific Unit Generation With Discriminative Dynamic Gaussian Mixture Selection for Multi-Accent Chinese Speech Recognition

Chao Zhang, Yi Liu, Yunqing Xia, Xuan Wang, Chin-Hui Lee
2013 IEEE Transactions on Audio, Speech, and Language Processing  
In this paper, we propose a discriminative dynamic Gaussian mixture selection (DGMS) strategy to generate reliable accent-specific units (ASUs) for multi-accent speech recognition.  ...  Time-aligned phone recognition is used to generate the ASUs that model accent variations explicitly and accurately.  ...  Jilei Tian at Tsinghua University and Nokia Research Center respectively, for many useful discussions.  ... 
doi:10.1109/tasl.2013.2265087 fatcat:ejk3btlt75dgzn6r2ox6ez4tbe

Developing Objective Measures of Foreign-Accent Conversion

Daniel Felps, Ricardo Gutierrez-Osuna
2010 IEEE Transactions on Audio, Speech, and Language Processing  
Therefore, the acoustic quality in accent conversion cannot be evaluated with conventional measures of spectral distortion, which assume that a clean recording of the speech signal is available for comparison  ...  Finally, we propose a measure of speaker identity that projects acoustic vectors (e.g., Mel cepstral, F0) onto the linear discriminant that maximizes separability for a given pair of source and target  ...  ACKNOWLEDGMENT The authors would like to thank Hart Blanton for suggestions regarding the EGWA scale and for making his laboratory available for perceptual tests.  ... 
doi:10.1109/tasl.2009.2038818 fatcat:gf4utkywgfgnnj2wpnkhza5kzm

Prosodic Event Recognition using Convolutional Neural Networks with Context Information [article]

Sabrina Stehwien, Ngoc Thang Vu
2017 arXiv   pre-print
This paper demonstrates the potential of convolutional neural networks (CNN) for detecting and classifying prosodic events on words, specifically pitch accents and phrase boundary tones, from frame-based  ...  acoustic features.  ...  Phrase Boundaries The results for phrase boundary recognition appear to follow a similar pattern as for pitch accent recognition.  ... 
arXiv:1706.00741v1 fatcat:6hk3ncipbrbq3nhmyx6xhdufaq

Multi-accent acoustic modelling of South African English

Herman Kamper, Félicien Jeje Muamba Mukanya, Thomas Niesler
2012 Speech Communication  
Multi-accent modelling therefore offers a mechanism by which speech recognition performance can be optimised automatically, and for hard decisions regarding which data to pool and which to separate to  ...  Three acoustic modelling approaches are considered: separate accent-specific models, accentindependent models obtained by pooling training data across accents, and multi-accent models.  ...  Acknowledgements The authors would like to thank Febe de Wet for her helpful comments and suggestions.  ... 
doi:10.1016/j.specom.2012.01.008 fatcat:s6bmtr4icncy5pwofr2slapxw4

Accent based speech recognition: A critical overview

Rizwana Kallooravi Thandil, K. P. Mohamed Basheer
2020 Malaya Journal of Matematik  
This paper concentrates on the study of accent-based speech recognition techniques in various languages and the technologies used for the same.  ...  An incredible amount of research has been conducted in speech recognition and accent-based speech recognition during recent decades.  ...  Finally, the acoustic signals are recognized based on the classification to which they belong Several methods are adopted for accent-based speech recognition in ASR.  ... 
doi:10.26637/mjm0804/0070 fatcat:gryfrx5kt5exdp7c4ocyljo2ki

Introducing attribute features to foreign accent recognition

Hamid Behravan, Ville Hautamauki, Sabato Marco Siniscalchi, Tomi Kinnunen, Chin-Hui Lee
2014 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
We propose a hybrid approach to foreign accent recognition combining both phonotactic and spectral based systems by treating the problem as a spoken language recognition task.  ...  We extract speech attribute features that represent speech and acoustic cues reflecting foreign accents of a speaker to obtain feature streams that are modeled with the i-vector methodology.  ...  In this study we treat foreign accent recognition as a language recognition task typically accomplished via either acoustic or phonotactic modeling [5] .  ... 
doi:10.1109/icassp.2014.6854621 dblp:conf/icassp/BehravanHSKL14 fatcat:tdmcznz2z5bezdgozpkfjhv54u

Adaptation to novel accents by toddlers

Katherine S. White, Richard N. Aslin
2011 Developmental Science  
The present study explores whether toddlers can adapt to artificial accents in which there is a vowel category shift with respect to the native language.  ...  Word recognition is a balancing act: listeners must be sensitive to phonetic detail to avoid confusing similar words, yet, at the same time, be flexible enough to adapt to phonetically variable pronunciations  ...  We also thank Eiling Yee, Mohinish Shukla and two anonymous reviewers for comments on a previous draft.  ... 
doi:10.1111/j.1467-7687.2010.00986.x pmid:21479106 pmcid:PMC3071623 fatcat:vevj6wkgxvgezneyzvpa4cbtli

Indexical and linguistic processing by 12-month-olds: Discrimination of speaker, accent and vowel differences

Karen E. Mulak, Cory D. Bonn, Kateřina Chládková, Richard N. Aslin, Paola Escudero, Johan J Bolhuis
2017 PLoS ONE  
For infants to handle indexical variation in the same way, they must be sensitive to both linguistic and indexical cues.  ...  preference to trials containing a vowel category change produced by the same speaker (linguistic information), and the same vowel category produced by another speaker of the same or a different accent  ...  Both analyses find a similar pattern in infants' greater looking to Indexical-and Vowel-change trials relative to No-change trials.  ... 
doi:10.1371/journal.pone.0176762 pmid:28520762 pmcid:PMC5435166 fatcat:xocic27p6ze4bfufevfoqyjhhi
« Previous Showing results 1 — 15 out of 3,748 results