Proceedings ArticleDOI
Noise independent speech recognition for a variety of noise types
W.C. Treurniet,Y. Gong +1 more
- pp 437-440
Reads0
Chats0
TLDR
By a base transformation technique, a recognizer is reported which gives a noise-adapted recognition rate of 90% under 10 dB SNR on a vocabulary of 206 words, which is 97% of the recognition rate for clean speech.Abstract:
By a base transformation technique, we previously reported a recognizer which gives a noise-adapted recognition rate of 90% under 10 dB SNR on a vocabulary of 206 words. This rate is 97% of the recognition rate for clean speech. The technique is extended here so that the input noise is first recognized as one of a set reference noises, and the noise reference is used for the base transformation of the noisy utterance. Using 32 reference noise classes, for speech signals corrupted by noises of unknown natures (either Gaussian, bus or aircrafts with SNR randomly from 10 to 40 dB), we obtained a noise-independent recognition rate of about 95.5% of the recognition rate for clean speech. >read more
Citations
More filters
Journal ArticleDOI
Speech recognition in noisy environments: a survey
TL;DR: The survey indicates that the essential points in noisy speech recognition consist of incorporating time and frequency correlations, giving more importance to high SNR portions of speech in decision making, exploiting task-specific a priori knowledge both of speech and of noise, using class-dependent processing, and including auditory models in speech processing.
PatentDOI
System and method of recognizing an acoustic environment to adapt a set of based recognition models to the current acoustic environment for subsequent speech recognition
TL;DR: A speech recognition system which effectively recognizes unknown speech from multiple acoustic environments includes a set of secondary models, each associated with one or more particular acoustic environments, integrated with a base set of recognition models.
Proceedings ArticleDOI
Frame level noise classification in mobile environments
TL;DR: The experimental results show that the line spectral frequencies (LSFs) are robust features in distinguishing the different classes of noises.
PatentDOI
Including the category of environmental noise when processing speech signals
TL;DR: In this article, a method and apparatus for identifying a noise environment for a frame of an input signal based on at least one feature for that frame is provided, and the noise environment is identified by determining the probability of each of a set of possible noise environments.
Proceedings ArticleDOI
Stochastic trajectory modeling for speech recognition
Yifan Gong,J.-P. Haton +1 more
TL;DR: The authors provide an algorithm for sentence recognition based on the modeling of phoneme-based speech units as clusters of trajectories in their parameter space that demonstrated substantially better recognition accuracy, compared to a conventional context-dependent, whole word HMM.
References
More filters
Journal ArticleDOI
An Algorithm for Vector Quantizer Design
Y. Linde,A. Buzo,Robert M. Gray +2 more
TL;DR: An efficient and intuitive algorithm is presented for the design of vector quantizers based either on a known probabilistic model or on a long training sequence of data.
Proceedings ArticleDOI
Stochastic trajectory modeling for speech recognition
Yifan Gong,J.-P. Haton +1 more
TL;DR: The authors provide an algorithm for sentence recognition based on the modeling of phoneme-based speech units as clusters of trajectories in their parameter space that demonstrated substantially better recognition accuracy, compared to a conventional context-dependent, whole word HMM.
Proceedings ArticleDOI
Noise reduction using a soft-decision sine-wave vector quantizer
Thomas F. Quatieri,R.J. McAulay +1 more
TL;DR: The results, although preliminary, provide evidence that harmonic zero-phase sine-wave analysis/synthesis, combined with effective estimation of sin-wave amplitudes and probability of voicing, offers a promising approach to noise reduction.
Proceedings ArticleDOI
Signal restoration by spectral mapping
TL;DR: This paper establishes a correspondence between the clean and the noisy signal through spectral mapping, and shows that when the mapping (detection) is based upon the likelihood ratio distortion measure, an SNR improvement of approximately 10 dB is obtainable for a 14 dB SNR noisy signal.
Proceedings ArticleDOI
Speech enhancement using vector quantization and a formant distance measure
TL;DR: A system to improve the intelligibility of noisy speech through the use of vector quantization of linear predictive coding (LPC) spectra and a distance measure involving formants is described, appearing to be a promising way to transform noisy speech into more intelligible signals.