Experiments on Cross-Language Attribute Detection and Phone Recognition With Minimal Target-Specific Training Data

Siniscalchi, Sabato Marco; Lyu, Dau-Cheng; Svendsen, Torbjørn; Lee, Chin‐Hui

doi:10.1109/tasl.2011.2167610

Cited by 71 publications

(48 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Those attributes could be identified from a particular language and shared across many different languages, so they could also be used to derive a universal set of speech units. Furthermore, data-sharing across languages at the acoustic phonetic attribute level is naturally facilitated by using these attributes, so more reliable language-independent acoustic parameter estimation can be anticipated [21]. In [16], it was also shown that these attributes can be used to compactly characterize any spoken language along the same lines as in the automatic speech attribute transcription (ASAT) paradigm for automatic speech recognition (ASR) [20].…”

Section: Choice and Extraction Of Attribute Featuresmentioning

confidence: 99%

See 1 more Smart Citation

Introducing attribute features to foreign accent recognition

Behravan

Siniscalchi

Kinnunen

et al. 2014

2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

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. Testing on the Finnish Language Proficiency exam corpus, we find our proposed technique to achieve a significant performance improvement over the state-of-the-art systems using only spectral based features.

show abstract

Section: Choice and Extraction Of Attribute Featuresmentioning

confidence: 99%

“…To avoid over-fitting, the reduction in classification error on the development set was adopted as the stopping criterion. The attribute detectors employed in this work were actually just those used in [21].…”

Section: Attribute Detector Designmentioning

confidence: 99%

Introducing attribute features to foreign accent recognition

Behravan

Siniscalchi

Kinnunen

et al. 2014

2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

show abstract

“…The attribute questions performed a similar role to the articulatory features in e.g. [30] but without the explicit attribute detectors of these systems. The same phone symbol could correspond to different realisations of the associated phone across languages, especially when co-articulations are taken into account.…”

Section: Vowelmentioning

confidence: 93%

Investigation of multilingual deep neural networks for spoken term detection

Knill

Gales

Rath

et al. 2013

2013 IEEE Workshop on Automatic Speech Recognition and Understanding

View full text Add to dashboard Cite

The development of high-performance speech processing systems for low-resource languages is a challenging area. One approach to address the lack of resources is to make use of data from multiple languages. A popular direction in recent years is to use bottleneck features, or hybrid systems, trained on multilingual data for speechto-text (STT) systems. This paper presents an investigation into the application of these multilingual approaches to spoken term detection. Experiments were run using the IARPA Babel limited language pack corpora (∼10 hours/language) with 4 languages for initial multilingual system development and an additional held-out target language. STT gains achieved through using multilingual bottleneck features in a Tandem configuration are shown to also apply to keyword search (KWS). Further improvements in both STT and KWS were observed by incorporating language questions into the Tandem GMM-HMM decision trees for the training set languages. Adapted hybrid systems performed slightly worse on average than the adapted Tandem systems. A language independent acoustic model test on the target language showed that retraining or adapting of the acoustic models to the target language is currently minimally needed to achieve reasonable performance.

show abstract

“…the Government Phonology (GP) [15,16], 2. the Sound Pattern of English (SPE) [17], and 3. the extended SPE system (eSPE) [18,19], Implementation of PhonVoc depends on the SSP vocoder and the Kaldi speech recognition toolkit [20] that we used for DNN training of both analysis and synthesis modules.…”

Section: Methodsmentioning

confidence: 99%

PhonVoc: A Phonetic and Phonological Vocoding Toolkit

Cerňak¹,

Garner²

2016

Interspeech 2016

View full text Add to dashboard Cite

We present the PhonVoc toolkit, a cascaded deep neural network (DNN) composed of speech analyser and synthesizer that use a shared phonetic and/or phonological speech representation. The free toolkit is distributed as open-source software under a BSD 3-Clause License, available at https://github. com/idiap/phonvoc with the pre-trained US English analysis and synthesis DNNs, and thus it is ready for immediate use.In a broader context, the toolkit implements training and testing of the analysis by synthesis heuristic model. It is thus designed for the wider speech community working in acoustic phonetics, laboratory phonology, and parametric speech coding. The toolkit interprets the phonetic posterior probabilities as a sequential scheme, whereas the phonological posterior-class probabilities are considered as a parallel via K different phonological classes. A case study is presented on a LibriSpeech database and a LibriVox US English native female speaker. The phonetic and phonological vocoding yield comparable performance, improving speech quality by merging the phonetic and phonological speech representation.

show abstract

Experiments on Cross-Language Attribute Detection and Phone Recognition With Minimal Target-Specific Training Data

Cited by 71 publications

References 33 publications

Introducing attribute features to foreign accent recognition

Introducing attribute features to foreign accent recognition

Investigation of multilingual deep neural networks for spoken term detection

PhonVoc: A Phonetic and Phonological Vocoding Toolkit

Contact Info

Product

Resources

About