• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 한국신호처리시스템학회 2003년도 하계학술대회 논문집
• /
• pp.46-49
• /
• 2003

The use of confidence measures for word/utterance verification has become art essential component of any speech input application. Confidence measures have applications to a number of problems such as rejection of incorrect hypotheses, speaker adaptation, or adaptive modification of the hypothesis score during search in continuous speech recognition. In this paper, we present a new utterance verification method using vowel string. Using subword HMMs of VCCV unit, we create anti-models which include vowel string in hypothesis words. The experiment results show that the utterance verification rate of the proposed method is about 79.5%.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• 제35C권11호
• /
• pp.63-75
• /
• 1998

Since many co-articulation problems are occurring in continuous spoken Korean language, several researches use words as a basic recognition unit. Though the word unit can solve this problem, it requires much memory and has difficulty fitting an input speech in a word list. In this paper, we propose an hidden Markov model(HMM) based recognition model that is an interconnection network of word HMMs for a syntax of sentences. To match suitably the input sentence into the continuous word list in the network, we use a level building search algorithm. This system represents the large sentence set with a relatively small memory and also has good extensibility. The experimental result of an airplane reservation system shows that it is proper method for a practical recognition system.

• Proceedings of the KSPS conference
• /
• 대한음성학회 2007년도 한국음성과학회 공동학술대회 발표논문집
• /
• pp.327-329
• /
• 2007

This paper presents a FSN-based LVCSR system and it's application to the speech TV program guide. Unlike the most popular statistical language model-based system, we used FSN grammar based on the graph theory-based FSN optimization algorithm and knowledge-based advanced word boundary modeling. For the memory and latency efficiency, we implemented the dynamic pruning scheduling based on the histogram of active words and their likelihood distribution. We achieved a 10.7% word accuracy improvement with 57.3% speedup.

• Journal of Industrial Technology
• /
• 제29권A호
• /
• pp.95-100
• /
• 2009

In this paper, we implemented a speaker-independent speech recognizer using the TMS320F28335 DSP which is optimized for control applications. For this implementation, we used a small-sized commercial DSP module and developed a peripheral board including a codec, signal conditioning circuits and I/O interfaces. The speech signal digitized by the TLV320AIC23 codec is analyzed based on MFCC feature extraction methed and recognized using the continuous-density HMM. Thanks to the internal SRAM and flash memory on the TMS320F28335 DSP, we did not need any external memory devices. The internal flash memory contains ADPCM data for voice response as well as HMM data. Since the TMS320F28335 DSP is optimized for control applications, the recognizer may play a good role in the voice-activated control areas in aspect that it can integrate speech recognition capability and inherent control functions into the single DSP.

• The Journal of the Acoustical Society of Korea
• /
• 제15권2호
• /
• pp.85-89
• /
• 1996

In this paper, transition constrained Hidden Markov Model(HMM) in which the transition between states occur only within prescribed time slot is proposed and the performance is evaluated in the noisy environment. The transition constrained HMM can explicitly limit the state durations and accurately de scribe the temporal structure of speech signal simply and efficiently. The transition constrained HMM is not only superior to the conventional HMM but also require much less computation time. In order to evaluate the performance of the transition constrained HMM, speaker independent isolated word recognition experiments were conducted using semi-continuous HMM with the noisy speech for 20, 10, 0 dB SNR. Experiment results show that the proposed method is robust to the environmental noise. The 81.08% and 75.36% word recognition rates for conventional HMM was increased by 7.31% and 10.35%, respectively, by using transition constrained HMM when two kinds of noises are added with 10dB SNR.

• The Journal of the Acoustical Society of Korea
• /
• 제29권1호
• /
• pp.56-61
• /
• 2010

This paper describes optimization methods of acoustic models in HMM-based continuous speech recognition. Most of the conventional speech recognition systems use the same number of Gaussian mixture components for each HMM state. However, since the number of data samples available for each state is different from each other, it is possible to reduce the overall number of model parameters and the computational cost at the decoding step by optimizing the number of Gaussian mixture components. In this study, we introduced the Gaussian mixture weight term at the merging stage of Gaussian components in the minimum description length (MDL) based acoustic modeling optimization. Experimental results showed that the proposed method can obtain better ASR accuracy than the previous optimization method which does not consider the Gaussian mixture weight term.

• The Journal of the Acoustical Society of Korea
• /
• 제18권8호
• /
• pp.9-16
• /
• 1999

Generally, a speaker structures utterances very clearly by grouping words into phrases. This facilitates the listener's recovery of the meaning of the utterance and the speaker's intention. To this purpose, a speaker uses, among other things, prosodic information such as intonation pause, duration, intensity, etc. The research described here is concerned with the relationship between the strength of prosodic boundaries in spoken utterances as perceived by untrained listeners(Perceptual boundary strength, PBS)-In this paper, the preceptual boundary strength is used as the same meaning of the prosodic boundary strength-and prosodic information. We made a rule determinating the prosodic boundaries and verified the usefulness of the prosodic phrase as a recognition unit. Experiments results showed that the performance of speech recognition(SR) is improved in aspect of recognition rate and time compared with that using sentences as recognition unit. In the future we will suggest the methods that estimate more appropriate boundaries and study more various methods of prosody assisted SR.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 한국음향학회 1998년도 학술발표대회 논문집 제17권 1호
• /
• pp.91-94
• /
• 1998

우리만은 영어와는 달리 단어를 공백으로만 구분할 수 없다. 그러므로 대용량 어휘를 갖는 연속 음성을 인식하기 위한 언어모델을 만들기가 매우 어렵다. N-gram의 언어 모델을 우리말 문장에 적용하기 위해 하나의 문장을 한 단어로 구성하여 처리하였다. 우리의 인식시스템을 평가하기 위하여 시스템 공학 연구소에서 제공한 음성을 대상으로 인식률을 계산하였다. 단어의 종류는 452개이며 한명이 이 단어들을 2번씩 발음하고 총70명이 발음한 총 63,280개의 단어에 대하여 92.8%의 인식률을 얻었다. 일간지 사설로부터 추출한 단어를 대상으로 발음 사전을 10K 크기로 만들었다. 음성 모델은 uniphone을 사용하였다.

• Proceedings of the IEEK Conference
• /
• 대한전자공학회 1999년도 하계종합학술대회 논문집
• /
• pp.1107-1110
• /
• 1999

In speech signal processing, the accurate decision of the voiced/unvoiced sound is important for robust word recognition and analysis and a high coding efficiency. In this paper, we propose the mehod of the voiced/unvoiced decision using the LSP parameter which represents the spectrum characteristics of the speech signal. The voiced sound has many more LSP parameters in low frequency region. To the contrary, the unvoiced sound has many more LSP parameters in high frequency region. That is, the LSP parameter distribution of the voiced sound is different to that of the unvoiced sound. Also, the voiced sound has the minimun value of sequantial intervals of the LSP parameters in low frequency region. The unvoiced sound has it in high frequency region. we decide the voiced/unvoiced sound by using this charateristics. We used the proposed method to some continuous speech and then achieved good performance.

• MALSORI
• /
• 제67호
• /
• pp.149-166
• /
• 2008

In spoken document retrievals (SDR), subword (typically phonemes) indexing term is used to avoid the out-of-vocabulary (OOV) problem. It makes the indexing and retrieval process independent from any vocabulary. It also requires a small corpus to train the acoustic model. However, subword indexing term approach has a major drawback. It shows higher word error rates than the large vocabulary continuous speech recognition (LVCSR) system. In this paper, we propose an probabilistic slot detection and n-gram based string matching method for phone based spoken document retrievals to overcome high error rates of phone recognizer. Experimental results have shown 9.25% relative improvement in the mean average precision (mAP) with 1.7 times speed up in comparison with the baseline system.