• The Journal of the Acoustical Society of Korea
• /
• v.41 no.3
• /
• pp.342-350
• /
• 2022

In this paper, actual drone noise samples are collected for speech processing in disaster environments to build noise-corrupted speech database, and speech enhancement performance is evaluated by applying spectrum subtraction and mask-based speech enhancement techniques. To improve the performance of VoiceFilter (VF), an existing deep neural network-based speech enhancement model, we apply the Self-Attention operation and use the estimated noise information as input to the Attention model. Compared to existing VF model techniques, the experimental results show 3.77%, 1.66% and 0.32% improvements for Source to Distortion Ratio (SDR), Perceptual Evaluation of Speech Quality (PESQ), and Short-Time Objective Intelligence (STOI), respectively. When trained with a 75% mix of speech data with drone sounds collected from the Internet, the relative performance drop rates for SDR, PESQ, and STOI are 3.18%, 2.79% and 0.96%, respectively, compared to using only actual drone noise. This confirms that data similar to real data can be collected and effectively used for model training for speech enhancement in environments where real data is difficult to obtain.

• ETRI Journal
• /
• v.31 no.4
• /
• pp.408-418
• /
• 2009

Adopting an encryption function in voice over Wi-Fi service incurs problems such as additional power consumption and degradation of communication quality. To overcome these problems, a partial encryption (PE) algorithm for compressed speech was recently introduced. However, from the security point of view, the partial encryption sets (PESs) of the conventional PE algorithm still have much room for improvement. This paper proposes a new selection method for finding a smaller PES while maintaining the security level of encrypted speech. The proposed PES selection method employs the perceptual evaluation of the speech quality (PESQ) algorithm to objectively measure the distortion of speech. The proposed method is applied to the ITU-T G.729 speech codec, and content protection capability is verified by a range of tests and a reconstruction attack. The experimental results show that encrypting only 20% of the compressed bitstream is sufficient to effectively hide the entire content of speech.

• Proceedings of the KSPS conference
• /
• 2007.05a
• /
• pp.155-157
• /
• 2007

Objective : There are close relationship between intraoral abnormal structure and speech-functional problem. Patients with cleft palate & ankyloglossia are typical examples. Patients with abnormal structure can be repaired toward normal structure by operation. Ankyloglossia may cause functional limitation - for example, speech disorder - even if adequate surgical treatment were done. And, each individuals have each speech disorders. The objective of this study is to evaluate the speechs of childrens with ankyloglossia, and to determine whether ankyloglossia is associated with articulation problem. We wanted to present criteria for indication of frenectomy. Study design The experimental group is composed of 10 childrens who visited our department of oral and maxillofacial surgery, dental hospital, Chonbuk university, due to ankyloglossia and articulation problem,. The average age is 5 Y 7M, M : F ratio is 4 : 1 at the time of speech test. The VPI consonant discrimination degree, PPVT, PCAT, Nasometer II, Visi-Pitch test result were obtained from each group. Result : There was significant difference for 'language development' through PPVT. Except 3 members of experimental group, all remainder showed retardation for 'language development'. For 'errored consonant rate', data showed more higher scores in alveolar consonant. There 'consonant error' in experimental group, mostly showed 'alveolar consonant', also a major modality of 'consonant error' was mostly distortion. Conclusion : We can judge the severity of ankyloglossia patient by examinig language development degree & speech test of 'alveolar consonant' . And we can make a decision for frenulotomy using these results.

• Speech Sciences
• /
• v.15 no.2
• /
• pp.67-77
• /
• 2008

In this paper, we implemented a robust speech recognizer using the TMS320VC33 DSP. For this implementation, we had built speech and noise database suitable for the recognizer using spectral subtraction method for noise removal. The recognizer has an explicit structure in aspect that a speech signal is enhanced through spectral subtraction before endpoints detection and feature extraction. This helps make the operation of the recognizer clear and build HMM models which give minimum model-mismatch. Since the recognizer was developed for the purpose of controlling car facilities and voice dialing, it has two recognition engines, speaker independent one for controlling car facilities and speaker dependent one for voice dialing. We adopted a conventional DTW algorithm for the latter and a continuous HMM for the former. Though various off-line recognition test, we made a selection of optimal conditions of several recognition parameters for a resource-limited embedded recognizer, which led to HMM models of the three mixtures per state. The car noise added speech database is enhanced using spectral subtraction before HMM parameter estimation for reducing model-mismatch caused by nonlinear distortion from spectral subtraction. The hardware module developed includes a microcontroller for host interface which processes the protocol between the DSP and a host.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.3
• /
• pp.234-240
• /
• 2021

In this paper, the mask-based speech enhancement is improved for effective speech recognition in noise environments. In the mask-based speech enhancement, enhanced spectrum is obtained by multiplying the noisy speech spectrum by the mask. The VoiceFilter (VF) model is used as the mask estimation, and the Spectrogram Inpainting (SI) technique is used to remove residual noise of enhanced spectrum. In this paper, we propose a combined loss to further improve speech enhancement. In order to effectively remove the residual noise in the speech, the positive part of the Triplet loss is used with the component loss. For the experiment TIMIT database is re-constructed using NOISEX92 noise and background music samples with various Signal to Noise Ratio (SNR) conditions. Source to Distortion Ratio (SDR), Perceptual Evaluation of Speech Quality (PESQ), and Short-Time Objective Intelligibility (STOI) are used as the metrics of performance evaluation. When the VF was trained with the mean squared error and the SI model was trained with the combined loss, SDR, PESQ, and STOI were improved by 0.5, 0.06, and 0.002 respectively compared to the system trained only with the mean squared error.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.1
• /
• pp.38-44
• /
• 2022

Speech enhancement is performed to improve intelligibility and quality of the noise-corrupted speech. In this paper, speech enhancement performance was compared using different loss functions in time and frequency domains. This study proposes a combination of loss functions to utilize advantage of each domain by considering both the details of spectrum and the speech waveform. In our study, Scale Invariant-Source to Noise Ratio (SI-SNR) is used for the time domain loss function, and Mean Squared Error (MSE) is used for the frequency domain, which is calculated over the complex-valued spectrum and magnitude spectrum. The phase loss is obtained using the sin function. Speech enhancement result is evaluated using Source-to-Distortion Ratio (SDR), Perceptual Evaluation of Speech Quality (PESQ), and Short-Time Objective Intelligibility (STOI). In order to confirm the result of speech enhancement, resulting spectrograms are also compared. The experimental results over the TIMIT database show the highest performance when using combination of SI-SNR and magnitude loss functions.

• Proceedings of the IEEK Conference
• /
• 2000.09a
• /
• pp.7-10
• /
• 2000

This paper focuses on the development of speech enhancement techniques for hands-free audio terminals, including two major problems : noise cancellation and acoustic echo cancellation. The objective is to find a joint structure to get a near-end speech signal with minimum distortion and low levels of echo and noise. To solve the two problems, a new promising technique is studied and tested in computer simulation conditions.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.16 no.6
• /
• pp.509-516
• /
• 1991

In this paper, we propose on objective evaluation model of telephone transmission qulity in order to estimate a satisfaction score regarding speech quality in a relephone network. As the degradantion factors of telephone transmission quality, this model takes into account transmission loss, noise, distortion, talker echo and sidetone. A performance index[PI] is introduced for five psychological factors affecting telephone speech qualty, and a Mean Opinion Score(MOS) is estimated from the sum of all Pis. The simulation results indicate theat the MOS obtained from the objective evaluation model is in good agreement with that of subjective evaluation.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.8
• /
• pp.91-97
• /
• 2012

This paper first proposes the speech recognition algorithm by detection of the speech and noise sections at each frame, then proposes the reduction algorithm of environmental noise by multi-band filter which removes the background noises at each frame according to detection of the speech and noise sections. The proposed algorithm reduces the background noises using filter bank sub-band domain after extracting the features from the speech data. In this experiment, experimental results of the proposed noise reduction algorithm by the multi-band filter demonstrate using the speech and noise data, at each frame. Based on measuring the spectral distortion, experiments confirm that the proposed algorithm is effective for the speech by corrupted the noise.

• The Journal of the Korea Contents Association
• /
• v.5 no.3
• /
• pp.167-173
• /
• 2005

In a speech coding system using excitation source of voiced and unvoiced, it would be involved a distortion of speech quality in case coexist with a voiced and unvoiced consonants in a frame. So, I propose TSIUVC(Transition Segment Including Unvoiced Consonant) extraction method by using pitch pulses and Zero Crossing Rate in order to unexistent with a voiced and unvoiced consonants in a frame. And this paper present a TSIUVC approximate-synthesis method by using frequency band division. As a result, this method obtains a high quality approximation-synthesis waveform within TSIUVC by using frequency information of 0.547kHz below and 2.813kHz above. And the TSIUVC extraction rate was $91\%$ for female voice and $96.2\%$ for male voice respectively This method has the capability of being applied to a new speech coding of Voiced/Silence/TSIUVC, speech analysis, and speech synthesis.