An integrated approach to the detection and classification of accents/dialects for a spoken document retrieval system

Gray, Sharmistha; Hansen, John H. L.

doi:10.1109/asru.2005.1566480

Cited by 16 publications

(11 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several studies have shown This work is supported by NSF and DoD. prosodic information like energy, duration, pitch, and formant based functionals to be effective features [2][3][4]. The native language identification task was found to be particularly difficult for spontaneous speech [3].…”

Section: Introductionmentioning

confidence: 99%

Multimodal Fusion of Multirate Acoustic, Prosodic, and Lexical Speaker Characteristics for Native Language Identification

2016

View full text Add to dashboard Cite

Native language identification from acoustic signals of L2 speakers can be useful in a range of applications such as informing automatic speech recognition (ASR), speaker recognition, and speech biometrics. In this paper we follow a multistream and multi-rate approach, for native language identification, in feature extraction, classification, and fusion. On the feature front we employ acoustic features such as MFCC and PLP features, at different time scales and different transformations; we evaluate speaker normalization as a feature and as a transform; investigate phonemic confusability and its interplay with paralinguistic cues at both the frame and phone-level temporal scales; and automatically extract lexical features; in addition to baseline features. On the classification side we employ SVM, i-Vector, DNN and bottleneck features, and maximum-likelihood models. Finally we employ fusion for system combination and analyze the complementarity of the individual systems. Our proposed system significantly outperforms the baseline system on both development and test sets.

show abstract

Section: Introductionmentioning

confidence: 99%

Multimodal Fusion of Multirate Acoustic, Prosodic, and Lexical Speaker Characteristics for Native Language Identification

2016

View full text Add to dashboard Cite

show abstract

“…A number of studies have considered automatic speech processing and/or acoustic/phonetic based analysis approaches to accent classification Hansen, 1996, 1997;Berkling, 2002;Das (Gray) and Hansen, 2004;Ghesquiere and Compernolle, 2002;Gray, 2005;Gray and Hansen, 2005;King, 1996, 1997). Work has also been focused on human perception of accent (Flege, 1984(Flege, , 1988, as well as the perception of accent (McGory et al, 2001) and language structure based on intonation characteristics (Grover et al, 1987), and phonetic differences in early language differentiation (Johnson and Wilson, 2002).…”

Section: Experimental Evaluationmentioning

confidence: 98%

Automatic voice onset time detection for unvoiced stops (/p/,/t/,/k/) with application to accent classification

Hansen

Gray

Kim

2010

Speech Communication

View full text Add to dashboard Cite

“…It is different from a dialect of a given language which refers to the speaking style of that language due to geographical and ethnic differences [16]. Accent knowledge can be used for selection of alternative pronunciations or provide information for biasing a language model for speech recognition.…”

Section: Accent Classification Techniquementioning

confidence: 99%

Enhanced speaker recognition based on intra-modal fusion and accent modeling

Mangayyagari

Islam

Sankar

2008

2008 19th International Conference on Pattern Recognition

View full text Add to dashboard Cite

Speaker recognition systems, even though they have been around for four decades, have not been widely considered as standalone systems for biometric security because of their unacceptably low performance, i.e., high false acceptance and rejection. Research has shown that speaker recognition performance can be enhanced through hybrid fusion (HF) of likelihood scores generated by arithmetic harmonic sphericity (AHS) and hidden Markov model (HMM) techniques [1]. Performance improvements of 22% and 6% true acceptance rate (TAR) at 5% false acceptance rate (FAR) were observed, when evaluated on two different datasets -YOHO and USF multi-modal biometric dataset respectively. In this paper, we present a model that combines accent information from an accent classification (AC) system with HF system in order to further increase the speaker recognition rate. The proposed system achieved performance improvements of 17% and 15% TAR at an FAR of 3% when evaluated on SAA and USF datasets. The accent incorporation method discussed in this work can also be applied to any other speaker recognition system.

show abstract

An integrated approach to the detection and classification of accents/dialects for a spoken document retrieval system

Cited by 16 publications

References 2 publications

Multimodal Fusion of Multirate Acoustic, Prosodic, and Lexical Speaker Characteristics for Native Language Identification

Multimodal Fusion of Multirate Acoustic, Prosodic, and Lexical Speaker Characteristics for Native Language Identification

Automatic voice onset time detection for unvoiced stops (/p/,/t/,/k/) with application to accent classification

Enhanced speaker recognition based on intra-modal fusion and accent modeling

Contact Info

Product

Resources

About