Noise Immunity

14,000,000 Leading Edge Experts on the ideXlab platform

Scan Science and Technology

Contact Leading Edge Experts & Companies

Scan Science and Technology

Contact Leading Edge Experts & Companies

The Experts below are selected from a list of 13305 Experts worldwide ranked by ideXlab platform

Hiroshi Kanazawa - One of the best experts on this subject based on the ideXlab platform.

  • keyword spotting in noisy continuous speech using word pattern vector subabstraction and Noise Immunity learning
    International Conference on Acoustics Speech and Signal Processing, 1992
    Co-Authors: Yoichi Takebayashi, Hiroyuki Tsuboi, Hiroshi Kanazawa
    Abstract:

    Noise Immunity learning, previously proposed by the authors (1991) for isolated word recognition in noisy environments, is extended to keyword spotting in noisy continuous speech. The powerful features of the Noise Immunity keyword-spotting method are keyword spotting based on the multiple similarity (MS) method for reliable keyword detection, Noise Immunity learning for greater robustness in recognition of spontaneous or noisy speech, and word pattern vector subabstraction to represent noisy keyword patterns from different viewpoints. Integrating the spotting results obtained by different kinds of subabstracted word pattern vectors significantly improved the performance of the keyword spotting. A system to spot 30 keywords currently runs in real-time on a workstation with two accelerators. The spotted keywords are fed into a keyword sequence LR parser for spontaneous speech understanding. >

  • ICASSP - Keyword-spotting in noisy continuous speech using word pattern vector subabstraction and Noise Immunity learning
    [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics Speech and Signal Processing, 1992
    Co-Authors: Yoichi Takebayashi, Hiroyuki Tsuboi, Hiroshi Kanazawa
    Abstract:

    Noise Immunity learning, previously proposed by the authors (1991) for isolated word recognition in noisy environments, is extended to keyword spotting in noisy continuous speech. The powerful features of the Noise Immunity keyword-spotting method are keyword spotting based on the multiple similarity (MS) method for reliable keyword detection, Noise Immunity learning for greater robustness in recognition of spontaneous or noisy speech, and word pattern vector subabstraction to represent noisy keyword patterns from different viewpoints. Integrating the spotting results obtained by different kinds of subabstracted word pattern vectors significantly improved the performance of the keyword spotting. A system to spot 30 keywords currently runs in real-time on a workstation with two accelerators. The spotted keywords are fed into a keyword sequence LR parser for spontaneous speech understanding. >

  • Noise Immunity learning for word-spotting speech recognition
    Systems and Computers in Japan, 1992
    Co-Authors: Yoichi Takebayashi, Hiroshi Kanazawa
    Abstract:

    This paper discusses Noise Immunity learning in speech recognition by word-spotting. In the proposed method, the learning speech data with superposed Noise is constructed by adding the Noise data to the clean speech data collected beforehand. Then the recognition dictionary for word-spotting is trained to improve Noise Immunity. In the learning, the recognition by word-spotting is attempted for the artificially synthesized learning data while gradually increasing the ratio of the contained Noise. The recognition is executed using the learning word feature vector automatically extracted based on the similarity. The Noise Immunity is realized by the simulation in the noisy environment and the automatic learning. The recognition and learning use the word as the unit and the multiple similarity method, which can cope with a wide range of pattern deformation. An evaluation experiment is executed using 13-word speech data (plus Noise in a railway station). For the case of 96-dimensional word feature vector (eight dimensions for frequency and 12 dimensions for time), and S/N ratio of 10 dB, the recognition rate is improved from 85.5 percent in the word-spotting method without learning to 94.1 percent with learning. This indicates the usefulness of the proposed method.

  • a robust speech recognition system using word spotting with Noise Immunity learning
    International Conference on Acoustics Speech and Signal Processing, 1991
    Co-Authors: Yoichi Takebayashi, Hiroyuki Tsuboi, Hiroshi Kanazawa
    Abstract:

    A speech recognition system using word-spotting with Noise Immunity learning has been developed to achieve robust performance under noisy environments. The system employs word-spotting based on the multiple similarity (MS) method for eliminating word boundary detection errors, Noise Immunity learning for improving Noise robustness, and an accelerator for reducing processing time. Noise Immunity learning is performed using noisy speech data and Noise data. Data from 39 male speakers were used to evaluate the recognition performance; the remaining data were used for the learning. Recognition scores obtained by word-spotting alone and with Noise Immunity learning were 88.5% and 98.4%, respectively, for an SNR of 10 dB. >

  • ICASSP - A robust speech recognition system using word-spotting with Noise Immunity learning
    [Proceedings] ICASSP 91: 1991 International Conference on Acoustics Speech and Signal Processing, 1991
    Co-Authors: Yoichi Takebayashi, Hiroyuki Tsuboi, Hiroshi Kanazawa
    Abstract:

    A speech recognition system using word-spotting with Noise Immunity learning has been developed to achieve robust performance under noisy environments. The system employs word-spotting based on the multiple similarity (MS) method for eliminating word boundary detection errors, Noise Immunity learning for improving Noise robustness, and an accelerator for reducing processing time. Noise Immunity learning is performed using noisy speech data and Noise data. Data from 39 male speakers were used to evaluate the recognition performance; the remaining data were used for the learning. Recognition scores obtained by word-spotting alone and with Noise Immunity learning were 88.5% and 98.4%, respectively, for an SNR of 10 dB. >

Yoichi Takebayashi - One of the best experts on this subject based on the ideXlab platform.

  • keyword spotting in noisy continuous speech using word pattern vector subabstraction and Noise Immunity learning
    International Conference on Acoustics Speech and Signal Processing, 1992
    Co-Authors: Yoichi Takebayashi, Hiroyuki Tsuboi, Hiroshi Kanazawa
    Abstract:

    Noise Immunity learning, previously proposed by the authors (1991) for isolated word recognition in noisy environments, is extended to keyword spotting in noisy continuous speech. The powerful features of the Noise Immunity keyword-spotting method are keyword spotting based on the multiple similarity (MS) method for reliable keyword detection, Noise Immunity learning for greater robustness in recognition of spontaneous or noisy speech, and word pattern vector subabstraction to represent noisy keyword patterns from different viewpoints. Integrating the spotting results obtained by different kinds of subabstracted word pattern vectors significantly improved the performance of the keyword spotting. A system to spot 30 keywords currently runs in real-time on a workstation with two accelerators. The spotted keywords are fed into a keyword sequence LR parser for spontaneous speech understanding. >

  • ICASSP - Keyword-spotting in noisy continuous speech using word pattern vector subabstraction and Noise Immunity learning
    [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics Speech and Signal Processing, 1992
    Co-Authors: Yoichi Takebayashi, Hiroyuki Tsuboi, Hiroshi Kanazawa
    Abstract:

    Noise Immunity learning, previously proposed by the authors (1991) for isolated word recognition in noisy environments, is extended to keyword spotting in noisy continuous speech. The powerful features of the Noise Immunity keyword-spotting method are keyword spotting based on the multiple similarity (MS) method for reliable keyword detection, Noise Immunity learning for greater robustness in recognition of spontaneous or noisy speech, and word pattern vector subabstraction to represent noisy keyword patterns from different viewpoints. Integrating the spotting results obtained by different kinds of subabstracted word pattern vectors significantly improved the performance of the keyword spotting. A system to spot 30 keywords currently runs in real-time on a workstation with two accelerators. The spotted keywords are fed into a keyword sequence LR parser for spontaneous speech understanding. >

  • Noise Immunity learning for word-spotting speech recognition
    Systems and Computers in Japan, 1992
    Co-Authors: Yoichi Takebayashi, Hiroshi Kanazawa
    Abstract:

    This paper discusses Noise Immunity learning in speech recognition by word-spotting. In the proposed method, the learning speech data with superposed Noise is constructed by adding the Noise data to the clean speech data collected beforehand. Then the recognition dictionary for word-spotting is trained to improve Noise Immunity. In the learning, the recognition by word-spotting is attempted for the artificially synthesized learning data while gradually increasing the ratio of the contained Noise. The recognition is executed using the learning word feature vector automatically extracted based on the similarity. The Noise Immunity is realized by the simulation in the noisy environment and the automatic learning. The recognition and learning use the word as the unit and the multiple similarity method, which can cope with a wide range of pattern deformation. An evaluation experiment is executed using 13-word speech data (plus Noise in a railway station). For the case of 96-dimensional word feature vector (eight dimensions for frequency and 12 dimensions for time), and S/N ratio of 10 dB, the recognition rate is improved from 85.5 percent in the word-spotting method without learning to 94.1 percent with learning. This indicates the usefulness of the proposed method.

  • a robust speech recognition system using word spotting with Noise Immunity learning
    International Conference on Acoustics Speech and Signal Processing, 1991
    Co-Authors: Yoichi Takebayashi, Hiroyuki Tsuboi, Hiroshi Kanazawa
    Abstract:

    A speech recognition system using word-spotting with Noise Immunity learning has been developed to achieve robust performance under noisy environments. The system employs word-spotting based on the multiple similarity (MS) method for eliminating word boundary detection errors, Noise Immunity learning for improving Noise robustness, and an accelerator for reducing processing time. Noise Immunity learning is performed using noisy speech data and Noise data. Data from 39 male speakers were used to evaluate the recognition performance; the remaining data were used for the learning. Recognition scores obtained by word-spotting alone and with Noise Immunity learning were 88.5% and 98.4%, respectively, for an SNR of 10 dB. >

  • ICASSP - A robust speech recognition system using word-spotting with Noise Immunity learning
    [Proceedings] ICASSP 91: 1991 International Conference on Acoustics Speech and Signal Processing, 1991
    Co-Authors: Yoichi Takebayashi, Hiroyuki Tsuboi, Hiroshi Kanazawa
    Abstract:

    A speech recognition system using word-spotting with Noise Immunity learning has been developed to achieve robust performance under noisy environments. The system employs word-spotting based on the multiple similarity (MS) method for eliminating word boundary detection errors, Noise Immunity learning for improving Noise robustness, and an accelerator for reducing processing time. Noise Immunity learning is performed using noisy speech data and Noise data. Data from 39 male speakers were used to evaluate the recognition performance; the remaining data were used for the learning. Recognition scores obtained by word-spotting alone and with Noise Immunity learning were 88.5% and 98.4%, respectively, for an SNR of 10 dB. >

Hiroyuki Tsuboi - One of the best experts on this subject based on the ideXlab platform.

  • keyword spotting in noisy continuous speech using word pattern vector subabstraction and Noise Immunity learning
    International Conference on Acoustics Speech and Signal Processing, 1992
    Co-Authors: Yoichi Takebayashi, Hiroyuki Tsuboi, Hiroshi Kanazawa
    Abstract:

    Noise Immunity learning, previously proposed by the authors (1991) for isolated word recognition in noisy environments, is extended to keyword spotting in noisy continuous speech. The powerful features of the Noise Immunity keyword-spotting method are keyword spotting based on the multiple similarity (MS) method for reliable keyword detection, Noise Immunity learning for greater robustness in recognition of spontaneous or noisy speech, and word pattern vector subabstraction to represent noisy keyword patterns from different viewpoints. Integrating the spotting results obtained by different kinds of subabstracted word pattern vectors significantly improved the performance of the keyword spotting. A system to spot 30 keywords currently runs in real-time on a workstation with two accelerators. The spotted keywords are fed into a keyword sequence LR parser for spontaneous speech understanding. >

  • ICASSP - Keyword-spotting in noisy continuous speech using word pattern vector subabstraction and Noise Immunity learning
    [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics Speech and Signal Processing, 1992
    Co-Authors: Yoichi Takebayashi, Hiroyuki Tsuboi, Hiroshi Kanazawa
    Abstract:

    Noise Immunity learning, previously proposed by the authors (1991) for isolated word recognition in noisy environments, is extended to keyword spotting in noisy continuous speech. The powerful features of the Noise Immunity keyword-spotting method are keyword spotting based on the multiple similarity (MS) method for reliable keyword detection, Noise Immunity learning for greater robustness in recognition of spontaneous or noisy speech, and word pattern vector subabstraction to represent noisy keyword patterns from different viewpoints. Integrating the spotting results obtained by different kinds of subabstracted word pattern vectors significantly improved the performance of the keyword spotting. A system to spot 30 keywords currently runs in real-time on a workstation with two accelerators. The spotted keywords are fed into a keyword sequence LR parser for spontaneous speech understanding. >

  • a robust speech recognition system using word spotting with Noise Immunity learning
    International Conference on Acoustics Speech and Signal Processing, 1991
    Co-Authors: Yoichi Takebayashi, Hiroyuki Tsuboi, Hiroshi Kanazawa
    Abstract:

    A speech recognition system using word-spotting with Noise Immunity learning has been developed to achieve robust performance under noisy environments. The system employs word-spotting based on the multiple similarity (MS) method for eliminating word boundary detection errors, Noise Immunity learning for improving Noise robustness, and an accelerator for reducing processing time. Noise Immunity learning is performed using noisy speech data and Noise data. Data from 39 male speakers were used to evaluate the recognition performance; the remaining data were used for the learning. Recognition scores obtained by word-spotting alone and with Noise Immunity learning were 88.5% and 98.4%, respectively, for an SNR of 10 dB. >

  • ICASSP - A robust speech recognition system using word-spotting with Noise Immunity learning
    [Proceedings] ICASSP 91: 1991 International Conference on Acoustics Speech and Signal Processing, 1991
    Co-Authors: Yoichi Takebayashi, Hiroyuki Tsuboi, Hiroshi Kanazawa
    Abstract:

    A speech recognition system using word-spotting with Noise Immunity learning has been developed to achieve robust performance under noisy environments. The system employs word-spotting based on the multiple similarity (MS) method for eliminating word boundary detection errors, Noise Immunity learning for improving Noise robustness, and an accelerator for reducing processing time. Noise Immunity learning is performed using noisy speech data and Noise data. Data from 39 male speakers were used to evaluate the recognition performance; the remaining data were used for the learning. Recognition scores obtained by word-spotting alone and with Noise Immunity learning were 88.5% and 98.4%, respectively, for an SNR of 10 dB. >

Minchul Shin - One of the best experts on this subject based on the ideXlab platform.

  • power ground Noise Immunity test in wireless and high speed uwb communication system
    International Symposium on Electromagnetic Compatibility, 2008
    Co-Authors: Changwook Yoon, Hyunjeong Park, Minchul Shin
    Abstract:

    This paper presents a wireless and high-speed transceiver system for Ultra-Wideband (UWB) communication with a high Noise Immunity. A proposed transceiver system has a high-speed data transmission up to 130 Mbps. Then, the measurement setup for the Noise Immunity test is introduced. Also, in order to demonstrate a Noise Immunity of the system, timing jitter, accumulated waveform, and bit error rate (BER) are measured in the presence of a power/ground Noise with various frequencies or amplitudes. The numerous measurement results help to understand the relationship between the power/ground Noise and the Noise Immunity of the proposed transceiver system.

  • Power/ground Noise Immunity test in wireless and high-speed UWB communication system
    2008 IEEE International Symposium on Electromagnetic Compatibility, 2008
    Co-Authors: Changwook Yoon, Hyunjeong Park, Minchul Shin
    Abstract:

    This paper presents a wireless and high-speed transceiver system for Ultra-Wideband (UWB) communication with a high Noise Immunity. A proposed transceiver system has a high-speed data transmission up to 130 Mbps. Then, the measurement setup for the Noise Immunity test is introduced. Also, in order to demonstrate a Noise Immunity of the system, timing jitter, accumulated waveform, and bit error rate (BER) are measured in the presence of a power/ground Noise with various frequencies or amplitudes. The numerous measurement results help to understand the relationship between the power/ground Noise and the Noise Immunity of the proposed transceiver system.

V. K. Marigodov - One of the best experts on this subject based on the ideXlab platform.

  • A technique for enhancing the Noise Immunity of multichannel communications systems with repetition
    Radioelectronics and Communications Systems, 2009
    Co-Authors: V. K. Marigodov
    Abstract:

    This study presents the estimation of the Noise Immunity of multichannel communications systems with repetition of messages transmitted, where each of channels employs the nonlinear predistortion and correction of signals and also the channel having the highest Noise Immunity employs adaptive linear filtration.

  • Noise Immunity enhancement of BLN system
    Radioelectronics and Communications Systems, 2008
    Co-Authors: E. F. Baburov, V. K. Marigodov
    Abstract:

    The possibility of enhancing the Noise Immunity was investigated with respect to the BLN system that is applied in radio receivers operating under the conditions of exposure to pulse interferences. To this end, additional processing of the received signals was proposed implying the introduction of predistortion and correction, and also the second clipping device. It was shown that the actual gain in Noise Immunity for the proposed system may reach 4…16 times in terms of power.

  • Technique of enhancing the Noise Immunity of broadband communications systems
    Radioelectronics and Communications Systems, 2007
    Co-Authors: V. K. Marigodov
    Abstract:

    A technique is considered for enhancing the Noise Immunity of broadband communications systems with repetition. This technique is based on generating a broadband Noise-like signal in the transmitting circuit of the system and adaptive compensation of broadband localized interferences in the receiver. In this case, an adaptive variation of transmitter carriers is conducted in each of the channels. The gain in Noise Immunity provided by the technique proposed was calculated in comparison with other known techniques.