{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T04:34:23Z","timestamp":1760243663361,"version":"build-2065373602"},"reference-count":27,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2013,12,2]],"date-time":"2013-12-02T00:00:00Z","timestamp":1385942400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/3.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>In order to develop a novel voice sensor to detect human voices, the use of features which are more robust to noise is an important issue. Voice sensor is also called voice activity detection (VAD). Due to that the inherent nature of the formant structure only occurred on the speech spectrogram (well-known as voiceprint), Wu et al. were the first to use band-spectral entropy (BSE) to describe the characteristics of voiceprints. However, the performance of VAD based on BSE feature was degraded in colored noise (or voiceprint-like noise) environments. In order to solve this problem, we propose the  two-dimensional part-band energy entropy (TD-PBEE) parameter based on two variables: part-band partition number upon frequency index and long-term window size upon time index to further improve the BSE-based VAD algorithm. The two variables can efficiently represent the characteristics of voiceprints on each critical frequency band and use  long-term information for noisy speech spectrograms, respectively. The TD-PBEE parameter can be regarded as a PBEE parameter over time. First, the strength of voiceprints can be partly enhanced by using four entropies applied to four part-bands. We can use the four part-band energy entropies for describing the voiceprints in detail. Due to the characteristics of non-stationary for speech and various noises, we will then use long-term information processing to refine the PBEE, so the voice-like noise can be distinguished from noisy speech through the concept of PBEE with long-term information. Our experiments show that the proposed feature extraction with the TD-PBEE parameter is quite insensitive to background noise. The proposed TD-PBEE-based VAD algorithm is evaluated for four types of noises and five signal-to-noise ratio (SNR) levels. We find that the accuracy of the proposed TD-PBEE-based VAD algorithm averaged over all noises and all SNR levels is better than that of other considered VAD algorithms.<\/jats:p>","DOI":"10.3390\/s131216533","type":"journal-article","created":{"date-parts":[[2013,12,3]],"date-time":"2013-12-03T03:18:09Z","timestamp":1386040689000},"page":"16533-16550","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Novel Voice Sensor for the Detection of Speech Signals"],"prefix":"10.3390","volume":"13","author":[{"given":"Kun-Ching","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Information Technology & Communication, Shih Chien University,  200 University Road, Neimen, Kaohsiung 84550, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2013,12,2]]},"reference":[{"key":"ref_1","unstructured":"Freeman, D.K., Cosier, G., Southcott, C.B., and Boyd, I. (1989, January 23\u201326). The Voice Activity Detector for the Pan-European Digital Cellular Mobile Telephone Service. Glasgow, UK."},{"key":"ref_2","unstructured":"Srinivasan, K., and Gersho, A. (1993, January 13\u201315). Voice Activity Detection for Cellular Networks. Sainte-Adele Quebec, Canada."},{"key":"ref_3","first-page":"948","article-title":"Voice activity detection and transmission error control for digital cordless telephone system","volume":"7","author":"Sasaki","year":"1994","journal-title":"IEICE Trans. Commun."},{"key":"ref_4","unstructured":"Rabiner, L.R., and Sambur, M.R. (1977, January 9\u201311). Voiced-Unvoiced-Silence Detection Using the Itakura LPC Distance Measure. Hartford, CT, USA."},{"key":"ref_5","unstructured":"Haigh, J.A., and Mason, J.S. (1993, January 19\u201321). Robust Voice Activity Detection Using Cepstral Features. In. Beijing, China."},{"key":"ref_6","unstructured":"Hoyt, J.D., and Wechsler, H. (1994, January 19\u201322). Detection of Human Speech in Structured Noise. Adelaide, SA, USA."},{"key":"ref_7","first-page":"377","article-title":"Voice activity detection using a periodicity measure","volume":"139","author":"Tucker","year":"1992","journal-title":"IEE Proc. I (Commun. Speech Vis.)"},{"key":"ref_8","unstructured":"Craciun, A., and Gabrea, M. (2004, January 2\u20135). Correlation Coefficient-Based Voice Activity Detector Algorithm. Ontario, Canada."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1594","DOI":"10.1093\/ietfec\/e89-a.6.1594","article-title":"Statistical model-based VAD algorithm with wavelet transform","volume":"E89-A","author":"Lee","year":"2006","journal-title":"IEICE Trans. Fundament."},{"key":"ref_10","unstructured":"Shen, J.L., Hung, J.W., and Lee, L.S. (December, January 30). Robust Entropy-Based Endpoint Detection for Speech Recognition in Noisy Environments. Sydney, Australia."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Soleimani, S.A., and Ahadi, S.M. (2008, January 7\u201311). Voice Activity Detection Based on Combination of Multiple Features Using Linear\/Kernel Discriminant Analyses. Damascus, Syria.","DOI":"10.1109\/ICTTA.2008.4530028"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"271","DOI":"10.1016\/j.specom.2003.10.002","article-title":"Efficient voice activity detection algorithms using long-term speech information","volume":"42","author":"Ramirez","year":"2004","journal-title":"Speech Commun."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Yanna, M., and Akinori, N. (2013). Efficient voice activity detection algorithm using long-term spectral flatness measure. EURASIP J. Audio Speech Music Process.","DOI":"10.1186\/1687-4722-2013-21"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/97.736233","article-title":"A statistical model-based voice activity detection","volume":"6","author":"Sohn","year":"1999","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_15","unstructured":"Cho, Y.D., Al-Naimi, K., and Kondoz, A. (2001, January 7\u201311). Improved Statistical Voice Activity Detection Based On a Smoothed Statistical Likelihood Ratio. USA."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Renevey, P., and Drygajlo, A. (2001, January 3\u20137). Entropy Based Voice Activity Detection in Very Noisy Conditions. Aalborg, Denmark.","DOI":"10.21437\/Eurospeech.2001-446"},{"key":"ref_17","unstructured":"Breithaupt, C., Gerkmann, T., and Martin, R. (April, January 30). A Novel A Priori SNR Estimation Approach Based on Selective Cepstro-Temporal Smoothing. Las Vegas, NV, USA."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"478","DOI":"10.1109\/89.848229","article-title":"Voice activity detection in nonstationary noise","volume":"8","author":"Tanyer","year":"2000","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"762","DOI":"10.1109\/TSA.2005.851909","article-title":"Robust endpoint detection algorithm based on the adaptive band-partitioning spectral entropy in adverse environments","volume":"13","author":"Wu","year":"2005","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"ref_20","unstructured":"Moore, B. (1995). Hearing, Academic Press Inc."},{"key":"ref_21","unstructured":"O'Shaughnessy, D. (1987). Speech Communication, Addision-Wesley."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1109\/89.928915","article-title":"Noise power spectral density estimation based on optimal smoothing and minimum statistics","volume":"9","author":"Martin","year":"2001","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1513","DOI":"10.21437\/Eurospeech.1995-370","article-title":"Computationally efficient speech enhancement by spectral minima tracking in subbands","volume":"2","author":"Doblinger","year":"1995","journal-title":"Proc. Eurospeech."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1095","DOI":"10.21437\/Eurospeech.1997-108","article-title":"A comparative study of speech detection methods","volume":"97","author":"Gerven","year":"1997","journal-title":"Eurospeech"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1109\/35.620527","article-title":"ITU-T recommendation G.729, annex B, a silence compression scheme for use with G.729 optimized for 70 digital simultaneous voice and data spplications","volume":"35","author":"Benyassine","year":"1997","journal-title":"IEEE Commun. Mag."},{"key":"ref_26","unstructured":"(1998). Digital Cellular Telecommunications System (Phase 2+), Adaptive Multi Rate (AMR) Speech, ANSI-C Code for AMR Speech Codec; ETSI TS 100 905 V7.0.0 (1999-08), ETSI."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"2024","DOI":"10.1109\/TASL.2006.872625","article-title":"Multiband modulation energy tracking for noisy speech detection","volume":"14","author":"Evangelopoulos","year":"2006","journal-title":"IEEE Trans. Audio Speech Lang. Process."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/13\/12\/16533\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T21:51:01Z","timestamp":1760219461000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/13\/12\/16533"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,12,2]]},"references-count":27,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2013,12]]}},"alternative-id":["s131216533"],"URL":"https:\/\/doi.org\/10.3390\/s131216533","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2013,12,2]]}}}