• MALSORI
• /
• v.55
• /
• pp.77-91
• /
• 2005

In this paper, we propose an XML based meta-data specification for industrial speech databases. Building speech databases is very time-consuming and expensive. Recently, by the government supports, huge amount of speech corpus has been collected as speech databases. However, the formats and meta-data for speech databases are different depending on the constructing institutions. In order to advance the reusability and portability of speech databases, a standard representation scheme should be adopted by all speech database construction institutions. ETRI proposed a XML based annotation scheme [51 for speech databases, but the scheme has too simple and flat modeling structure, and may cause duplicated information. In order to overcome such disadvantages in this previous scheme, we first define the speech database more formally and then identify object appearing in speech databases. We then design the data model for speech databases in an object-oriented way. Based on the designed data model, we develop the meta-data specification for industrial speech databases.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.5
• /
• pp.2588-2609
• /
• 2019

Speech homomorphic encryption has become one of the key components in secure speech storing in the public cloud computing. The major problem of speech homomorphic encryption is the huge data expansion of speech cipher-text. To address the issue, this paper presents a speech homomorphic encryption scheme with less data expansion, which is a probabilistic statistics and addition homomorphic cryptosystem. In the proposed scheme, the original digital speech with some random numbers selected is firstly grouped to form a series of speech matrix. Then, a proposed matrix encryption method is employed to encrypt that speech matrix. After that, mutual information in sample speech cipher-texts is reduced to limit the data expansion. Performance analysis and experimental results show that the proposed scheme is addition homomorphic, and it not only resists statistical analysis attacks but also eliminates some signal characteristics of original speech. In addition, comparing with Paillier homomorphic cryptosystem, the proposed scheme has less data expansion and lower computational complexity. Furthermore, the time consumption of the proposed scheme is almost the same on the smartphone and the PC. Thus, the proposed scheme is extremely suitable for secure speech storing in public cloud computing.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.6
• /
• pp.2612-2633
• /
• 2020

Due to the explosive growth of multimedia speech data, how to protect the privacy of speech data and how to efficiently retrieve speech data have become a hot spot for researchers in recent years. In this paper, we proposed an encrypted speech retrieval scheme based on long short-term memory (LSTM) neural network and deep hashing. This scheme not only achieves efficient retrieval of massive speech in cloud environment, but also effectively avoids the risk of sensitive information leakage. Firstly, a novel speech encryption algorithm based on 4D quadratic autonomous hyperchaotic system is proposed to realize the privacy and security of speech data in the cloud. Secondly, the integrated LSTM network model and deep hashing algorithm are used to extract high-level features of speech data. It is used to solve the high dimensional and temporality problems of speech data, and increase the retrieval efficiency and retrieval accuracy of the proposed scheme. Finally, the normalized Hamming distance algorithm is used to achieve matching. Compared with the existing algorithms, the proposed scheme has good discrimination and robustness and it has high recall, precision and retrieval efficiency under various content preserving operations. Meanwhile, the proposed speech encryption algorithm has high key space and can effectively resist exhaustive attacks.

• MALSORI
• /
• no.43
• /
• pp.89-99
• /
• 2002

Recently, researches into ways of improving large vocabulary continuous speech recognition and speech synthesis are being carried out intensively as the field of speech information technology is progressing rapidly. In the field of speech recognition, developments of stochastic methods such as HMM require large amount of speech data for training, and also in the field of speech synthesis, recent practices show that synthesis of better quality can be produced by selecting and connecting only the variable size of speech data from the large amount of speech data. In this paper we design and discuss linguistic contents for speech copora for speech recognition and synthesis to be shared in common.

• ETRI Journal
• /
• v.34 no.4
• /
• pp.583-590
• /
• 2012

In this paper, we present a new approach for speaker diarization. First, we use the prosodic information calculated on the original speech to resynthesize the new speech data utilizing the spectrum modeling technique. The resynthesized data is modeled with sinusoids based on pitch, vibration amplitude, and phase bias. Then, we use the resynthesized speech data to extract cepstral features and integrate them with the cepstral features from original speech for speaker diarization. At last, we show how the two streams of cepstral features can be combined to improve the robustness of speaker diarization. Experiments carried out on the standardized datasets (the US National Institute of Standards and Technology Rich Transcription 04-S multiple distant microphone conditions) show a significant improvement in diarization error rate compared to the system based on only the feature stream from original speech.

• Proceedings of the IEEK Conference
• /
• 2002.07a
• /
• pp.466-469
• /
• 2002

Using intelligent information contained within the speech to identify the specific hidden data in the watermarked multimedia data is considered to be an efficient method to achieve the speech digital watermarking. This paper presents the performance comparison between various types of speech codec in order to determine an appropriate one to be used in digital watermarking applications. In the experiments, the speech signal encoded by four different types of speech codec, namely CELP, GSM, SBC and G.723.1codecs is embedded into a grayscale image, and theirs performance in term of speech recognition are compared. The method for embedding the speech signal into the host data is borrowed from a watermarking method based on the zerotrees of wavelet packet coefficients. To evaluate efficiency of the speech codec used in watermarking applications, the speech signal after being extracted from the attacked watermarked image will be played back to the listeners, and then be justified whether its content is intelligible or not.

• Phonetics and Speech Sciences
• /
• v.12 no.4
• /
• pp.63-71
• /
• 2020

Speech recognition is one of the areas actively commercialized using deep learning and machine learning techniques. However, the majority of speech recognition systems on the market are developed on data with limited diversity of speakers and tend to perform well on typical adult speakers only. This is because most of the speech recognition models are generally learned using a speech database obtained from adult males and females. This tends to cause problems in recognizing the speech of the elderly, children and people with dialects well. To solve these problems, it may be necessary to retain big database or to collect a data for applying a speaker adaptation. However, this paper proposes that a new end-to-end speech recognition method consists of an acoustic augmented recurrent encoder and a transformer decoder with linguistic prediction. The proposed method can bring about the reliable performance of acoustic and language models in limited data conditions. The proposed method was evaluated to recognize Korean elderly and children speech with limited amount of training data and showed the better performance compared of a conventional method.

• Journal of Korea Multimedia Society
• /
• v.22 no.7
• /
• pp.749-758
• /
• 2019

This paper proposes a data augmentation algorithm to improve the performance of DNN(Deep Neural Network) based speech enhancement. Many deep learning models are exploring algorithms to maximize the performance in limited amount of data. The most commonly used algorithm is the data augmentation which is the technique artificially increases the amount of data. For the effective data augmentation algorithm, we used a formant enhancement method that assign the different weights to the formant frequencies. The DNN model which is trained using the proposed data augmentation algorithm was evaluated in various noise environments. The speech enhancement performance of the DNN model with the proposed data augmentation algorithm was compared with the algorithms which are the DNN model with the conventional data augmentation and without the data augmentation. As a result, the proposed data augmentation algorithm showed the higher speech enhancement performance than the other algorithms.

• MALSORI
• /
• no.47
• /
• pp.51-72
• /
• 2003

The purpose of this paper is to design Speech Database for Korean pronunciation education. For this purpose, I investigated types of speech errors of Korean-learners, made texts for recording, which involves all types of speech errors, and showed how to gather speech data and how to tag their informations. It's natural that speech data should include Korean-learners' speech and Korean people's speech, because Speech DB that I try to develop is for teaching Korean pronunciation to foreigners. So this DB should have informations about speakers and phonetic informations, which are about phonetic value of segments and intonation of sentences. The intonation of sentence varies with the type of sentence, the structure of prosodic units, the length of a prosodic unit and so on. For this reason, Speech DB must involve tags about these informations.

• ETRI Journal
• /
• v.45 no.1
• /
• pp.18-27
• /
• 2023

We present an English-Korean speech translation corpus, named EnKoST-C. End-to-end model training for speech translation tasks often suffers from a lack of parallel data, such as speech data in the source language and equivalent text data in the target language. Most available public speech translation corpora were developed for European languages, and there is currently no public corpus for English-Korean end-to-end speech translation. Thus, we created an EnKoST-C centered on TED Talks. In this process, we enhance the sentence alignment approach using the subtitle time information and bilingual sentence embedding information. As a result, we built a 559-h English-Korean speech translation corpus. The proposed sentence alignment approach showed excellent performance of 0.96 f-measure score. We also show the baseline performance of an English-Korean speech translation model trained with EnKoST-C. The EnKoST-C is freely available on a Korean government open data hub site.