A Comparison of Two Approaches to Bilingual HMM-Based Speech Synthesis

Pobar, Miran; Justin, Tadej; Žibert, Janez; Ipšić, Ivo

doi:10.1007/978-3-642-40585-3_7

Cited by 3 publications

(2 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Second, when data in different languages is collected from different speakers, a polyglot synthesiser can be developed by combining the data into a single average voice that can be transformed to bear the identity of one of the speakers using speaker adaptation [9,10]. Polyglot synthesiser can also be developed using voice conversion, where voice of the source speaker is modified to that of the target speaker [2].…”

Section: Introductionmentioning

confidence: 99%

Exploiting acoustic similarities between Tamil and Indian English in the development of an HMM‐based bilingual synthesiser

VijayaRajSolomon¹,

Parthasarathy²,

Nagarajan³

2017

IET signal process.

View full text Add to dashboard Cite

In this studʊ, an efficient hidden Markov model (HMM)-based bilingual speech sʊnthesiser for the Indian language Tamil and Indian English is developed. Initiallʊ, phone mapping approach is tried to sʊnthesise English text using Tamil corpus alone bʊ mapping English phonemes to the perceptuallʊ similar phonemes in Tamil, and is found that the approach is languagedependent and requires a large dictionarʊ for Indian pronunciation. Therefore, given the speech data for both languages, the straightforward approach to develop a bilingual sʊnthesiser is to build separate sʊnthesiser for each language and combine them or bʊ merging the perceptuallʊ similar phonemes. These approaches introduce language-switching/influence in the sʊnthesised speech. To minimise switching and influence, HMM-based bilingual sʊnthesisers are developed bʊ merging acousticallʊ similar phonemes, derived based on model parameters and likelihood Gaussian using various distance metrics. The performance of these sʊnthesisers are evaluated based on mean opinion score (MOS), language-switching and languageinfluence. Results reveal that the set of phonemes derived using product-of-likelihood Gaussians in the likelihood space is the optimum set of phonemes that can be merged and the sʊstem developed bʊ merging these phonemes outperforms the rest with an MOS of 3.66. Furthermore, onlʊ 8% and 23% of the sentences have language-switching/influence, respectivelʊ.

show abstract

Section: Introductionmentioning

confidence: 99%

Exploiting acoustic similarities between Tamil and Indian English in the development of an HMM‐based bilingual synthesiser

VijayaRajSolomon¹,

Parthasarathy²,

Nagarajan³

2017

IET signal process.

View full text Add to dashboard Cite

show abstract

“…It can be defined as a synthesis system, that is able to produce synthetic speech in multiple languages using the same target-speaker characteristics [17]. Commonly, such approaches are also tested with bilingual speech-synthesis systems [18]. Such an approach to multilingual speech synthesis requires the target language's data during training.…”

Section: Related Workmentioning

confidence: 99%

Towards automatic cross-lingual acoustic modelling applied to HMM-based speech synthesis for under-resourced languages

Justin

Žibert

2016

Automatika

Self Cite

View full text Add to dashboard Cite

Original scientific paperNowadays Human Computer Interaction (HCI) can also be achieved with voice user interfaces (VUIs). To enable devices to communicate with humans by speech in the user's own language, low-cost language portability is often discussed and analysed. One of the most time-consuming parts for the language-adaptation process of VUIcapable applications is the target-language speech-data acquisition. Such data is further used in the development of VUIs subsystems, especially of speech-recognition and speech-production systems. The tempting idea to bypass a long-term process of data acquisition is considering the design and development of an automatic algorithms, which can extract the similar target-language acoustic from different language speech databases. This paper focus on the cross-lingual phoneme mapping between an under-resourced and a well-resourced language. It proposes a novel automatic phoneme-mapping technique that is adopted from the speaker-verification field. Such a phoneme mapping is further used in the development of the HMM-based speech-synthesis system for the under-resourced language. The synthesised utterances are evaluated with a subjective evaluation and compared by the expert knowledge cross-language method against to the baseline speech synthesis based just from the under-resourced data. The results reveals, that combining data from well-resourced and under-resourced language with the use of the proposed phoneme-mapping technique, can improve the quality of under-resourced language speech synthesis.Key words: Voice user interfaces, Human language technologies, HMM-based speech synthesis, Cross-language synthesis, Under-resourced languages, UBM-MAP-GMM phoneme mapping Primjena automatskog medujezičnog akustičnog modeliranja na HMM sintezu govora za oskudne jezične baze. U današnje vrijeme interakcijačovjeka i računala (HCI) može se ostvariti i putem govornih sučelja (VUIs). Da bi se omogućila komunikacija uredaja i korisnika putem govora na vlastitom korisnikovom jeziku, cesto se raspravlja i analizira o jeftinom rješenju prijevoda govora na različite jezike. Jedan od vremenski najzahtjevnijih dijelova procesa prilagodbe jezika za aplikacije koje podržavaju VUI je prikupljanje govornih podataka za ciljani jezik. Ovakvi podaci dalje se koriste za razvoj VUI podsustava, posebice za prepoznavanje i produkciju govora. Primamljiva ideja za izbjegavanje dugotrajnog postupka prikupljanja podataka jeste razmatranje sinteze i razvoja automatskih algoritama koji su sposobni izvesti slična akustična svojstva za ciljani jezik iz postojećih baza različitih jezika. Ovaj rad fokusiran je na povezivanje medujezičnih fonema izmedu oskudnih i bogatih jezičnih baza. Predložena je nova tehnika automatskog povezivanja fonema, usvojena i prilagodena iz područja govorne autentikacije. Ovakvo povezivanje fonema kasnije se koristi za razvoj sustava za sintezu govora zasnovanom na HMM-u za manje poznate jezike. Načinjene govorne izjave ocijenjene su subjektivnim pristupom kroz usporedbu medujezičnih m...

show abstract