The Romanian speech synthesis (RSS) corpus: Building a high quality HMM-based speech synthesis system using a high sampling rate

Stan, Adriana; Yamagishi, Junichi; King, Simon; Aylett, Matthew P.

doi:10.1016/j.specom.2010.12.002

Cited by 52 publications

(18 citation statements)

References 20 publications

(22 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• The LTS lexicon used in our validation process contains two sub-datasets: the CMUDictionary (Weide, 2005) and the Romanian Speech Synthesis Database (Stan et al, 2011);…”

Section: Corpora Descriptionmentioning

confidence: 99%

Fast and Accurate Decision Trees for Natural Language Processing Tasks

Boroş

Dumitrescu

Pipa³

2017

RANLP 2017 - Recent Advances in Natural Language Processing Meet Deep Learning

View full text Add to dashboard Cite

Decision trees have long been used in many machine-learning tasks; they have a clear structure that provides insight into the training data and are simple to conceptually understand and implement. We present an optimized tree-computation algorithm based on the original ID3 algorithm. We introduce a tree-pruning method that uses the development set to delete nodes from overfitted models, as well as a result-caching method for speedup. Our algorithm is 1 to 3 orders of magnitude faster than a naive implementation and yields accurate results on our test datasets.

show abstract

“…• The LTS lexicon used in our validation process contains two sub-datasets: the CMUDictionary (Weide, 2005) and the Romanian Speech Synthesis Database (Stan et al, 2011);…”

Section: Corpora Descriptionmentioning

confidence: 99%

Fast and Accurate Decision Trees for Natural Language Processing Tasks

Boroş

Dumitrescu

Pipa³

2017

RANLP 2017 - Recent Advances in Natural Language Processing Meet Deep Learning

View full text Add to dashboard Cite

show abstract

“…Statistical parametric speech synthesis system (Zen et al, 2009) has been widely studied recently. Its flexibility in generating speech in other languages like Korean (Sang-Jin et al, 2006) and Romanian (Stan et al, 2011) becomes the preference of most researchers. Moreover, the quality of speech generated from this method has reached a satisfactory level if compared with unit selection method (Karaiskos et al, 2008).…”

Section: Comparison Of State-of-the-art Speech Synthesis Systemmentioning

confidence: 99%

“…By reviewing works done by other researchers (Stan et al, 2011), database was created by randomly collect the words from articles, story books, newspapers and online resources. This might possess risks because not all diphonewould exist in the database.…”

Section: Comparison Of State-of-the-art Speech Synthesis Systemmentioning

confidence: 99%

Low Footprint High Intelligibility Malay Speech Synthesizer Based on Statistical Data

Yong

Swee²

2014

Journal of Computer Science

View full text Add to dashboard Cite

Speech synthesis plays a pivotal role nowadays. It can be found in various daily applications such as in mobile phones, navigation systems, languages learning software and so on. In this study, a Malay language speech synthesizer was designed using hidden Markov model to improve the performance of current Malay speech synthesizer and also extend Malay speech technology. Statistical parametric method was utilized in this study. The database was constructed to be balanced with all the phonetic sample appeared in Malay language. The results were rated by 48 listeners and obtained a moderate high rating ranging from 3.79 to 4.23 out of 5. The computed Word Error Rate is 7.1%. The total file size is less than 2 Megabytes which means it is suitable to be embedded into daily application. In conclusion, a Malay language speech synthesizer was designed using statistical parametric method with hidden Markov model. The output speech was verified to be good in quality. The file size is small indicates the feasibility to be used in embedded system.

show abstract

“…The intelligibility test was based on [8], and evaluators listened to the given set of utterances as many times as they wanted before typing in what they had heard. The intelligibility of the utterances was evaluated at word level, each correct word being given a score of 1 and incorrect words a score of 0.…”

Section: Evaluation Of Hmm-based Synthetic Speechmentioning

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

The Romanian speech synthesis (RSS) corpus: Building a high quality HMM-based speech synthesis system using a high sampling rate

Cited by 52 publications

References 20 publications

Fast and Accurate Decision Trees for Natural Language Processing Tasks

Fast and Accurate Decision Trees for Natural Language Processing Tasks

Low Footprint High Intelligibility Malay Speech Synthesizer Based on Statistical Data

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

Contact Info

Product

Resources

About