检索结果-南通市图书馆

Language Model Score Regularization for Speech Recognition

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2019年第3期28卷 604-609页

作者： ZHANG Yike ZHANG Pengyuan yan yonghong Institute of Acoustics Chinese Academy of Sciences University of Chinese Academy of Sciences Xinjiang Technical Institute of Physics and Chemistry Chinese Academy of Sciences

Inspired by the fact that back-off and interpolated smoothing algorithms have significant effect on statistical language modeling, this paper proposes a sentence-level Language model(LM) score regularization algorithm to improve the fault-tolerance of LMs for recognition errors. The proposed algorithm is applicable to both count-based LMs and neural network LMs. Instead of predicting the occurrence of a sequence of words under a fixed order Markov assumption, we use a composite model consisting of different order models with either n-gram or skip-gram features to estimate the probability of the sequence of words. In order to simplify implementations,we derive a connection between bidirectional neural networks and the proposed algorithm. Experiments were carried out on the Switchboard corpus. Results on N-best lists re-scoring show that the proposed algorithm achieves consistent word error rate reduction when it is applied to count-based LMs, Feedforward neural network(FNN)LMs, and Recurrent neural network(RNN) LMs.

关键词： Speech recognition Language model score regularization Interpolation Bidirectional neural network

Using Highway Connections to Enable Deep Small-footprint LSTM-RNNs for Speech Recognition

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2019年第1期28卷 107-112页

作者： CHENG Gaofeng LI Xin yan yonghong Key Laboratory of Speech Acoustics and Content Understanding Institute of Acoustics University of Chinese Academy of Sciences

Long short-term memory RNNs(LSTMRNNs) have shown great success in the Automatic speech recognition(ASR) field and have become the state-ofthe-art acoustic model for time-sequence modeling ***, it is still difficult to train deep LSTM-RNNs while keeping the parameter number small. We use the highway connections between memory cells in adjacent layers to train a small-footprint highway LSTM-RNNs(HLSTM-RNNs), which are deeper and thinner compared to conventional LSTM-RNNs. The experiments on the Switchboard(SWBD) indicate that we can train thinner and deeper HLSTM-RNNs with a smaller parameter number than the conventional 3-layer LSTM-RNNs and a lower Word error rate(WER) than the conventional *** with the counterparts of small-footprint LSTMRNNs, the small-footprint HLSTM-RNNs show greater reduction in WER.

关键词： Long short-term memory Highway connections Small-footprint Speech recognition

Agglutinative Language Speech Recognition Using Automatic Allophone Deriving

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2016年第2期25卷 328-333页

作者： XU Ji PAN Jielin yan yonghong The Key Laboratory of Speech Acoustics and Content Understanding Chinese Academy of Sciences

Agglutinative language involves agglutination extensively, which results in the significant pronunciation variations in different contexts. Therefore, it is a problem to use phoneme sets translated from their written forms as basic units for acoustic modeling, due to the incapability to capture the pronunciation variations in Large-vocabulary continuous speech recognition(LVCSR).This paper presented a novel approach called Automatic allophone deriving(AAD) to create allophone candidates without any linguistic prior knowledge. Furthermore, an enhanced approach AAD-LT is proposed in which longtime features are used in AAD approach. Experiments are conducted on three languages which contains two agglutinative ones and an analytic one. The experiments suggest that AAD Long-time(AAD-LT) is very effective for the agglutinative languages in which more than 10% relative CER reduction is obtained.

关键词： Agglutinative language Large-vocabulary continuous speech recognition(LVCSR) Allophone Unsupervised

Vision-based bio-inspired guidance law for small aerial vehicle

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2015年第1期28卷 260-267页

作者： Wang Zhengjie Huang Weilin yan yonghong School of Mechatronical Engineering Beijing Institute of Technology Key Lab of Speech Acoustics and Content Understanding Institute of Acoustics Chinese Academy of Sciences

During predation, a flying insect can form a stealth flight path. This behavior is called motion camouflage. Based on the study results of this behavior, the perception and neurology of flying insects, a novel bio-inspired guidance law is proposed for the terminal guidance for small aerial vehicle with charge-coupled device imaging seekers. The kinematics relationship between a small aerial vehicle and target is analyzed, and a two-dimensional guidance law model is established by using artificial neural networks. To compare with the proportional guidance law, the numerical simulations are carried out in the vertical plane and in the horizontal plane respectively. The simulation results show that the ballistic of the small aerial vehicle is straighter and the normal acceleration is smaller by using the bio-inspired guidance law than by using the proportional guidance law. That is to say, the bio-inspired guidance law just uses the information of the target from the imaging seeker,but the performance of it can be better than that of the proportional guidance law.

关键词： guidance aerial inspired kinematics flying proportional retina acceleration capture trajectory

DNN-Based Speech Enhancement Using Soft Audible Noise Masking for Wind Noise Reduction

在线全文

学校读者我要写书评

暂无评论

China Communications 2018年第9期15卷 235-243页

作者： Haichuan Bai Fengpei Ge yonghong yan Key Laboratory of Speech Acoustics and Content Understanding Institute of Acoustics Chinese Academy of SciencesBeijing 100190 China University of Chinese Academy of Sciences Beijing 100049 China Xinjiang Laboratory of Minority Speech and Language Information Processing Xinjiang Technical Institute of Physics and ChemistryChinese Academy of Sciences Urumqi 830011 China

This paper presents a deep neural network(DNN)-based speech enhancement algorithm based on the soft audible noise masking for the single-channel wind noise reduction. To reduce the low-frequency residual noise, the psychoacoustic model is adopted to calculate the masking threshold from the estimated clean speech spectrum. The gain for noise suppression is obtained based on soft audible noise masking by comparing the estimated wind noise spectrum with the masking threshold. To deal with the abruptly time-varying noisy signals, two separate DNN models are utilized to estimate the spectra of clean speech and wind noise components. Experimental results on the subjective and objective quality tests show that the proposed algorithm achieves the better performance compared with the conventional DNN-based wind noise reduction method.

关键词： wind noise reduction speech enhancement soft audible noise masking psychoacoustic model deep neural network

Investigation of Knowledge Transfer Approaches to Improve the Acoustic Modeling of Vietnamese ASR System

在线全文

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2019年第5期6卷 1187-1195页

作者： Danyang Liu Ji Xu Pengyuan Zhang yonghong yan the Key Laboratory of Speech Acoustics and Content Understanding Institute of AcousticsChinese Academy of SciencesBeijing 100190China the School of Electronic Electrical and Communication EngineeringUniversity of Chinese Academy of SciencesBeijing 101408China with Xinjiang Laboratory of Minority Speech and Language Information Processing Xinjiang Technical Institute of Physics and ChemistryChinese Academy of SciencesUrumqi 830011China

It is well known that automatic speech recognition(ASR) is a resource consuming task. It takes sufficient amount of data to train a state-of-the-art deep neural network acoustic model. As for some low-resource languages where scripted speech is difficult to obtain, data sparsity is the main problem that limits the performance of speech recognition system. In this paper, several knowledge transfer methods are investigated to overcome the data sparsity problem with the help of high-resource *** first one is a pre-training and fine-tuning(PT/FT) method, in which the parameters of hidden layers are initialized with a welltrained neural network. Secondly, the progressive neural networks(Prognets) are investigated. With the help of lateral connections in the network architecture, Prognets are immune to forgetting effect and superior in knowledge transferring. Finally,bottleneck features(BNF) are extracted using cross-lingual deep neural networks and serves as an enhanced feature to improve the performance of ASR system. Experiments are conducted in a low-resource Vietnamese dataset. The results show that all three methods yield significant gains over the baseline system, and the Prognets acoustic model performs the best. Further improvements can be obtained by combining the Prognets model and bottleneck features.

关键词： Bottleneck feature (BNF) cross-lingual automatic speech recognition (ASR) progressive neural networks (Prognets) model transfer learning

Speech Enhancement Using Multi-channel Post-Filtering with Modified Signal Presence Probability in Reverberant Environment

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2016年第3期25卷 512-519页

作者： WANG Xiaofei GUO yanmeng FU Qiang yan yonghong Key Laboratory of Speech Acoustics and Content Understanding Institute of AcousticsChinese Academy of Sciences

In this paper, a multi-channel post-filtering approach in reverberant environment based on detection and estimation scheme is presented. A modified Signal presence probability(SPP), which is in consideration of reverberation, is proposed with a novel estimator Direct-toreverberate ratio(DRR) to adapt to distant-talking *** is known a key estimator to instruct the updating of transient noise or residual directional interference and form gain function in the time-frequency domain, consequently a new desired signal detection scheme is proposed to improve its accuracy. Appropriate spectral enhancement technique is applied to the noisy speech signal taking advantage of the modified SPP estimator. The proposed multi-channel post-filtering is tested in different nonstationary noisy and reverberant environments. Experimental results show that it achieves considerable improvement on signal preservation of the desired speech with more noise reduction over the comparative algorithms.

关键词： Speech enhancement Multi-channel post-filtering Reverberation robust Signal detection

Automatic Piano Music Transcription Using Audio-Visual Features

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2015年第3期24卷 596-603页

作者： WAN Yulong WANG Xianliang ZHOU Ruohua yan yonghong The Key Laboratory of Speech Acoustics and Content Understanding Chinese Academy of Sciences

The performance of automatic music transcription seems to have reached a limit over the last decade,and a promising direction of improvements could be to incorporate music instruments' specific parameters. We propose a novel piano-specific transcription system, using both audio and visual features for the first time. Contribution of the paper mainly includes two parts: A new onset detection method is proposed using a specific spectrum envelope matched filter on multiple frequency bands. A computer-vision method is proposed to enhance audio-only piano music transcription, through tracking the positions of the pianist's hands on the piano keyboard. Based on the MIDI Aligned piano sounds(MAPS) database and a selfrecorded video database, we carried out comparable experiments for audio-only onset detection and overall system,respectively. The performance was compared with the best piano transcription system in Music information retrieval evaluation exchange(MIREX), and the results showed that the proposed system outperforms the state-of-art method substantially.

关键词： Music transcription Polyphonic piano Onset detection Matched filtering Multimedia fusion

Cyclic Beam Direction of Arrival Estimation Method for Ship Propeller Noise

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Ocean University of China 2024年第4期23卷 883-896页

作者： ZHANG Xiaowei NIE Weihang XU Ji yan yonghong The Key Laboratory of Speech Acoustics and Content Understanding Institute of AcousticsChinese Academy of SciencesBeijing 100190China The Key Laboratory of Speech Acoustics and Content Understanding Institute of AcousticsUniversity of Chinese Academy of SciencesBeijing 100049China The State Key Laboratory of Acoustics Institute of AcousticsChinese Academy of SciencesBeijing 100190China

In underwater acoustic applications,the conventional cyclic direction of arrival algorithm faces challenges,including a low signal-to-noise ratio and high bandwidth when compared with modulated *** response to these issues,this paper introduces a novel,robust,and broadband cyclic beamforming *** proposed method substitutes the conventional cyclic covariance matrix with the variance of the cyclic covariance matrix as its primary *** that the same frequency band shares a common steering vector,the new algorithm achieves superior detection performance for targets with specific modulation frequencies while suppressing interference signals and background *** results demonstrate a significant enhancement in the directibity index by 81%and 181%when compared with the traditional Capon beamforming algorithm and the traditional extended wideband spectral cyclic MUSIC(EWSCM)algorithm,***,the proposed algorithm substantially reduces computational complexity to 1/40th of that of the EWSCM algorithm,employing frequency band statistical averaging and covariance matrix variance.

关键词： cyclostationarity direction of arrival extended wideband spectral cyclic music cyclic covariance matrix