检索结果-内蒙古大学图书馆

32nd IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Motlicek, Petr Uallal, Vijay Hermansky, Hynek IDIAP Res Inst Martigny Switzerland Int Comp Sci Inst Berkeley CA USA Ecole Polytech Fed Lausanne Lausanne Switzerland

ISBN: (纸本)9781424407286

In this paper we propose an extension of the very low bit-rate speech coding technique, exploiting predictability of the temporal evolution of spectral envelopes, for wide-band audio coding applications. Temporal envelopes in critically band-sized sub-bands are estimated using frequency domain linear prediction applied on relatively long time segments. The sub-band residual signals, which play an important role in acquiring high quality reconstruction, are processed using a heterodyning-based signal analysis technique. For reconstruction, their optimal parameters are estimated using a closed-loop analysis-by-synthesis technique driven by a perceptual model emulating simultaneous masking properties of the human auditory system. We discuss the advantages of the approach and show some properties on challenging audio recordings. The proposed technique is capable of encoding high quality, variable rate audio signals on bit-rates below 1bit/sample.

关键词： audio signal processing data compression linear predictive coding Hilbert transform

来源：评论

学校读者我要写书评

暂无评论

On the use of dynamic spectral parameters in speech recognition 3

On the use of dynamic spectral parameters in speech recognit...

引用

3rd IEEE International Symposium on Signal Processing and Information Technology

作者： Ahadi, SM Sheikhzadeh, H Brennan, RL Freeman, GH Chau, E Amirkabir Univ Technol EE Dept Tehran Iran

ISBN: (纸本)0780382927

Spectral dynamics have attracted the attention of researchers in speech recognition for a long time. As part of the speech feature vector they are found to be useful and hence are almost part of any feature extraction algorithm for speech recognition. However, the usual cepstral dynamics do not directly reflect the dynamics of the speech spectrum, as they are extracted from cepstral parameters. In this paper we show that dynamic parameters obtained directly from the speech spectrum can perform better under low-SNR noisy speech conditions, in comparison to the conventional dynamic cepstral parameters. Results on a compact set of the Aurora task have been reported.

关键词： Additive noise Cepstral analysis Data mining Feature extraction Fourier transforms linear predictive coding Mel frequency cepstral coefficient Noise robustness Speech processing Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Performance analysis of Enhanced Noisy Compressed Speech Signal Corrupted by Gaussian and Real World Noise Using Recursive Filter 4

Performance analysis of Enhanced Noisy Compressed Speech Sig...

引用

2015 International Conference on Signal Processing And Communication Engineering Systems (SPACES)

作者： Suman, M. Khan, Habibulla Latha, M. Madhavi Kumari, D. Aruna KL Univ Guntur Andhra Pradesh India JNTU Coll Engn Hyderabad Telangana India

ISBN: (纸本)9781479961085

Speech Enhancement refers to the improvement in the intelligibility and or the quality of the degraded speech signal using signal processing techniques. Till recent days speech enhancement is a very difficult problem because the noise content in the speech signals varies its nature and characteristics with time and application to application. Using speech enhancement techniques the quality and intelligibility of a speech signal can't be preserved simultaneously. So generally a trade off is maintained between these two. In speech communication there are number of applications where speech enhancement is required for Example: VoIP, hands free communication, hearing aids, answering machines, speech recognition, teleconferencing systems, car and mobile phones In this work the main focus is on the development of speech enhancement algorithm that maintains a proper tradeoff between quality and intelligibility in the speech signal. This can be made possible using the time and spectral information in the speech signal. This work also focus on the problem of enhancing the compressed version of the speech signal, to improve the intelligibility of the speech signal. The performance measures like Signal to Noise Ratio (SNR), Mean opinion Score (MOS), Pitch and Formants used to find the performance of a speech enhancement algorithm which varies from application to application.

关键词： linear predictive coding Multi stage vector quantization Line Spectral Frequencies (LSF)

来源：评论

学校读者我要写书评

暂无评论

Packet loss concealment based on sinusoidal extrapolation

Packet loss concealment based on sinusoidal extrapolation

引用

IEEE International Conference on Acoustics, Speech, and Signal Processing

作者： Lindblom, J Hedelin, P Chalmers Univ Technol Informat Theory Lab SE-41296 Gothenburg Sweden

ISBN: (纸本)0780374029

In this paper, a packet loss concealment scheme based on sinusoidal extrapolation is proposed. It is to be implemented at the receiver end of a packetized speech transmission system and conceals frame-erasures in a PCM waveform. The scheme operates on the source-filter components of the speech signal, which are obtained through linear Prediction (LP) analysis. When one or more speech frames are missing, the LP residual and filter coefficients are extrapolated separately. The residual is extrapolated based on sinusoidal modeling of the last correct residual frame, whereas the latest filter is repeated and bandwidth expanded. The proposed scheme is compared to two benchmark systems by means of subjective testing. The benchmark systems are based on repetitions of the last pitch period;one operates on the source-filter components, the other directly on the speech signal. It is noted that the systems operating on the source-filter components are preferred by the listeners, and that the proposed system is clearly superior to both benchmark systems.

关键词： speech coding extrapolation pulse code modulation linear predictive coding filtering theory voice communication packet loss concealment sinusoidal extrapolation packetized speech transmission system frame-erasures concealment PCM waveform source-filter components linear prediction analysis filter coefficients LP residual subjective testing last pitch period repetitions source filter components packet voice communication

来源：评论

学校读者我要写书评

暂无评论

Speech enhancement based on double RBF networks

Speech enhancement based on double RBF networks

引用

1st International Congress on Image and Signal Processing

作者： Guo, Jichang Guo, Libin Tianjin Univ Sch Elect Informat Engn Tianjin 300072 Peoples R China

ISBN: (纸本)9780769531199

In this paper, a non-linear spectral estimation for noise reduction is present which is approximated and implemented by double Radial Basis Function (RBF) networks. The simulation results indicate that the method can greatly improve the quality and the intelligibility of speech, and have other advantages such as the widely applicable Signal-to-Noise Ratio (SNR) range, less computation load Particularly the method may maintain the preferable accurate of signal in speech waveform, and the quality of speech signals have been improved obviously.

关键词： Speech enhancement Radial basis function networks linear predictive coding Neural networks Signal processing Noise reduction Signal to noise ratio Flowcharts Frequency Electronic mail

来源：评论

学校读者我要写书评

暂无评论

Efficient parameter quantisation for 2.4/1.2 kb/s split-band LPC coding

Efficient parameter quantisation for 2.4/1.2 kb/s split-band...

引用

7th IEEE Workshop on Speech coding

作者： Villette, S Cho, YD Kondoz, AM Univ Surrey Ctr Commun Syst Res Guildford GU2 7XH Surrey England

ISBN: (纸本)0780364163

Speech coding at very low bit rates has many applications such as answering machines, IP telephony, mobile communications, military communications etc. Most low bit rate coders operate at around 2.4 kb/s, as the speech quality degrades too much below this bit rate. In this paper we describe a frequency domain speech coder capable of operating at both 2.4 and 1.2kb/s, and produces good quality synthesised speech. Both rates use the same analysis and synthesis building blocks over 20ms, but the 1.2 kb/s coder jointly quantises three sets of parameters every 60 ms to reduce the bit rate while maintaining speech quality. We also describe the quantisation methods used to lower the bit rate from 2.4 kb/s to 1.2 kb/s while retaining most of the quality of the higher bit rate version.

关键词： Bit rate Degradation linear predictive coding Military communication Mobile communication Quantization Speech analysis Speech coding Speech synthesis Telephony

来源：评论

学校读者我要写书评

暂无评论

A Low-Rate Digital Formant Vocoder

引用

IEEE Transactions on Communications 1978年第3期26卷 344-355页

作者： Un, Chong Kwan Korea Advanced Institute of Science Seoul South Korea SRI International Menlo Park CA 94025 United States

A complete algorithm of a 1200-bits/s digital formant vocoder system is described. This vocoder algorithm draws heavily on the results of recent research in linear predictive coding. The transmitting parameters are frequencies and amplitudes of the first three formants, the pitch period, voiced/unvoiced decision, and the gain. Formant bandwidths are estimated at the synthesizer by using the amplitude information. The synthesizer structure is in the parallel form. The synthetic speech quality at 1200 bits/s is reasonably good;most of the speech is intelligible and speaker-recognizable. Copyright © 1978 by The Institute of Electrical and Electronics Engineers, Inc.

关键词： Vocoders linear predictive coding Synthesizers Hardware Speech analysis Large scale integration Marine vehicles US Government Electrical engineering Physics

来源：评论

学校读者我要写书评

暂无评论

ACELP-based compression of multi-channel surface EMG signals

ACELP-based compression of multi-channel surface EMG signals

引用

32nd IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Carotti, Elias S. G. De Martin, Juan C. Merletti, Roberto Farina, Dario Politecn Torino DAUIN Corso Duca Abruzzi 24 I-10129 Turin Italy Aalborg Univ Ctr Sensory Motor Interact Aalborg Denmark

ISBN: (纸本)1424407281

In this paper we extend a lossy compression technique for surface EMG signals, which is based on the Algebraic Code Excited linear Prediction (ACELP) paradigm, to compress multi-channel surface EMG recordings by exploiting the correlation between the Line Spectral Frequencies (LSF). Experimental results show that the LSFs of the inner signals in a multi-channel recording can be efficiently represented with 13 bit/frame, versus the 38 bit/frame needed by independent ACELP coding of each signal, thus saving 66% of the bandwidth needed to transmit these coefficients while maintaining comparable performance in terms of the SNR, Average Rectified Value and Root Mean Square of the waveform, and mean and median frequencies of the power spectrum.

关键词： data compression linear predictive coding

来源：评论

学校读者我要写书评

暂无评论

Delay-free lossy audio coding using shelving pre- and post-filters

Delay-free lossy audio coding using shelving pre- and post-f...

引用

33rd IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Holters, Martin Zoelzer, Udo Helmut Schmidt Univ Hamburg Germany

ISBN: (纸本)9781424414833

A delay-free audio coding scheme based on ADPCM with adaptive pre- and post-filtering is presented. The pre-/post-filters are realized as a cascade of shelving filters, designed to match the characteristics of human perception. The pre- and post-filters are adapted by dynamic compression of the respective sub-bands. The adaption is backward-adaptive, i.e. is fed by the reconstructed signal, which eliminates the need to transmit the filter coefficients and allows delay-free operation. This pre- and post-filtering significantly improves the audio quality compared to a plain ADPCM codec, as underlined by objective measurements. Since the base ADPCM used is also delay-free, the resulting coding system works without any algorithmic delay.

关键词： audio coding linear predictive coding adaptive filters

来源：评论

学校读者我要写书评

暂无评论

Alveolar Consonant Recognition of Malay Children Using Neural Networks

引用

11th International Congress of the IUPESM/World Congress on Medical Physics and Biomedical Engineering

作者： Ting, H. N. Lee, J. X. Univ Malaya Fac Engn Dept Biomed Engieering Jalan Pantai Baharu Kuala Lumpur 50603 Malaysia

ISBN: (纸本)9783642038815

This paper presents the speech recognition of Malay Alveolar consonants of Malay children using neural networks in a speaker-independent manner. The Alveolar consonants consist of /d/, /t/, /l/, /r/, /s/, /z/ and /n/. The Alveolar consonants are combined with six Malay vowels to form the consonant-vowel (CV) syllable sounds. 100 children are involved in the speech recording with a total of 4200 speech sounds. The speech sounds are recorded at a sampling rate of 20 KHz with 16-bit resolution. linear predictive coding (LPC) is used to extract the speech feature extraction. Multi-layer Perceptron (MLP), which is one of the most popular neural networks, is used to classify the Alveolar consonants. Experiments are conducted to determine the optimal signal length of the consonants, and hidden neuron number of MLP. A maximum recognition rate of 62.14% is obtained at signal lengths of 150ms and 160ms.

关键词： Alveolar linear predictive coding Malay Multi-layer Perceptron Speaker-independent

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：