Cross-language use of acoustic information for automatic speech recognition

Nieuwoudt, C.; Botha, Elizabeth C.

doi:10.1016/s0167-6393(01)00046-2

Cited by 19 publications

(16 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Source acoustic models can originate from either a single language [29][30][31][32] or multiple languages. [27,[33][34][35][36] When it comes to selecting the mapping scheme, one major factor to consider is how much speech data is actually available in the target language.…”

Section: Abstractpotting In Under-resourced Languagesmentioning

confidence: 99%

“…When no target language speech data are available, a knowledge-based mapping can be generated. Knowledge-based mappings are produced manually and take into account known phonetic similarities between the source and target language phonemes, [29,31,32] as defined, for example, by the International Phonetic Alphabet (IPA). [37] A knowledge-based mapping can be avoided if phonetic transcriptions of all source and target languages use the same phoneme set (e.g.…”

Section: Abstractpotting In Under-resourced Languagesmentioning

confidence: 99%

See 1 more Smart Citation

Cross-language phoneme mapping for phonetic search keyword spotting in continuous speech of under-resourced languages

Tetariy

Bar-Yosef

Silber-Varod

et al. 2015

AIR

View full text Add to dashboard Cite

As automatic speech recognition-based applications become increasingly common in a wide variety of market segments, there is a growing need to support more languages. However, for many languages, the language resources needed to train speech recognition engines are either limited or completely non-existent, and the process of acquiring or constructing new language resources is both long and costly. This paper suggests a methodology that enables Phonetic Search Keyword Spotting to be implemented in a large speech database of any given under-resourced language using cross-language phoneme mappings to another language. The phoneme mapping enables a speech recognition engine from a sufficiently resourced and well-trained source language to be used for phoneme recognition in the new target language. The keyword search is then performed over a lattice of target language phonemes. Three cross-language phoneme mapping techniques are examined: knowledge-based, data-driven and phoneme recognition performance-based. The results suggest that Phonetic Search Keyword Spotting based on the cross-language phoneme mapping approach proposed herein can serve as a quick initial solution for validating keyword spotting applications in new, under-resourced languages.

show abstract

Section: Abstractpotting In Under-resourced Languagesmentioning

confidence: 99%

Section: Abstractpotting In Under-resourced Languagesmentioning

confidence: 99%

Cross-language phoneme mapping for phonetic search keyword spotting in continuous speech of under-resourced languages

Tetariy

Bar-Yosef

Silber-Varod

et al. 2015

AIR

View full text Add to dashboard Cite

show abstract

“…Number of words in the previous, current and next phrase 35 Number of words in this utterance Phrase 36 and 37 Position of the current phrase in utterance: forward and backward 38 TOBI end tone of the current phrase 39…”

Section: Segment-phonetic Label For Malaymentioning

confidence: 99%

Developing an HMM-Based Speech Synthesis System for Malay: A Comparison of Iterative and Isolated Unit Training

Mustafa

Don

Ainon

et al. 2014

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYThe development of an HMM-based speech synthesis system for a new language requires resources like speech database and segment-phonetic labels. As an under-resourced language, Malay lacks the necessary resources for the development of such a system, especially segment-phonetic labels. This research aims at developing an HMM-based speech synthesis system for Malay. We are proposing the use of two types of training HMMs, which are the benchmark iterative training incorporating the DAEM algorithm and isolated unit training applying segmentphonetic labels of Malay. The preferred method for preparing segmentphonetic labels is the automatic segmentation. The automatic segmentation of Malay speech database is performed using two approaches which are uniform segmentation that applies fixed phone duration, and a crosslingual approach that adopts the acoustic model of English. We have measured the segmentation error of the two segmentation approaches to ascertain their relative effectiveness. A listening test was used to evaluate the intelligibility and naturalness of the synthetic speech produced from the iterative and isolated unit training. We also compare the performance of the HMM-based speech synthesis system with existing Malay speech synthesis systems. key words: iterative training, isolated unit training, cross lingual approach, uniform segmentation, segment-phonetic labels

show abstract

“…It is well known in cross-lingual and multilingual studies [5], [6], [7] that using acoustic models from one language to decode speech from another leads to degraded performance. Given the already high error rate, the level of accuracy obtained by front-end decoders on other languages is likely to be very poor indeed.…”

Section: Phone Error Ratementioning

confidence: 99%

“…For Spanish these include the use of acute accents, and diaeresis, whilst in German the inclusion of Umlaut, namely a, 6, ii. Both of these are encoded using IS08859-1, and can be seamlessly incorporated in most computer based applications.…”

Section: Callhomementioning

confidence: 99%

Towards Improved Assessment of Phonotactic Information for Automatic Language Identification

Martin

Wong

Sridharan

2006

2006 IEEE Odyssey - The Speaker and Language Recognition Workshop

View full text Add to dashboard Cite

Phonotactic modelling, typically in the form of a PPRLM system, forms a key component in state-of-the-art Language Identification (LID) systems. Given the objective of PPRLM systems is to capture as accurately as possible the phonotactics which characterise a language, it is assumed that the minimisation of Phone Error Rate (PER) is a precursor to achieving this effectively. In this paper we examine the relevance of PER as a metric for determining eventual LID performance. In order to conduct this investigation we make use of the CallHome corpus, based on the premise it provides a better representation for the style of discourse and channel conditions encountered in the Conversational Telephone Speech (CTS), which is now the focus of current NIST LID evaluations. Using CallHome instead of the OGI-MLTS corpus to train phone recognisers, we obtained significantly improved results, with an average improvement of approximately 6% absolute across the 30, 10 and 3 seconds tasks for the NIST 1996 and 2003 evaluations. We also examine the impact of tuning the individual front-end recognisers, on both the resultant PER of other languages and against the resultant LID performance. We find that PER has a number of limitations in indicating both the degree and direction of changes to LID performance. Accordingly, we propose a new metric which is better suited for forecasting the impact on LID performance when the phone recogniser front-end is modified.

show abstract

Cross-language use of acoustic information for automatic speech recognition

Cited by 19 publications

References 21 publications

Cross-language phoneme mapping for phonetic search keyword spotting in continuous speech of under-resourced languages

Cross-language phoneme mapping for phonetic search keyword spotting in continuous speech of under-resourced languages

Developing an HMM-Based Speech Synthesis System for Malay: A Comparison of Iterative and Isolated Unit Training

Towards Improved Assessment of Phonotactic Information for Automatic Language Identification

Contact Info

Product

Resources

About