• Title/Summary/Keyword: Speech recognition

Search Result 2,019, Processing Time 0.028 seconds

Multi-resolution DenseNet based acoustic models for reverberant speech recognition (잔향 환경 음성인식을 위한 다중 해상도 DenseNet 기반 음향 모델)

  • Park, Sunchan;Jeong, Yongwon;Kim, Hyung Soon
    • Phonetics and Speech Sciences
    • /
    • v.10 no.1
    • /
    • pp.33-38
    • /
    • 2018
  • Although deep neural network-based acoustic models have greatly improved the performance of automatic speech recognition (ASR), reverberation still degrades the performance of distant speech recognition in indoor environments. In this paper, we adopt the DenseNet, which has shown great performance results in image classification tasks, to improve the performance of reverberant speech recognition. The DenseNet enables the deep convolutional neural network (CNN) to be effectively trained by concatenating feature maps in each convolutional layer. In addition, we extend the concept of multi-resolution CNN to multi-resolution DenseNet for robust speech recognition in reverberant environments. We evaluate the performance of reverberant speech recognition on the single-channel ASR task in reverberant voice enhancement and recognition benchmark (REVERB) challenge 2014. According to the experimental results, the DenseNet-based acoustic models show better performance than do the conventional CNN-based ones, and the multi-resolution DenseNet provides additional performance improvement.

Selecting Good Speech Features for Recognition

  • Lee, Young-Jik;Hwang, Kyu-Woong
    • ETRI Journal
    • /
    • v.18 no.1
    • /
    • pp.29-41
    • /
    • 1996
  • This paper describes a method to select a suitable feature for speech recognition using information theoretic measure. Conventional speech recognition systems heuristically choose a portion of frequency components, cepstrum, mel-cepstrum, energy, and their time differences of speech waveforms as their speech features. However, these systems never have good performance if the selected features are not suitable for speech recognition. Since the recognition rate is the only performance measure of speech recognition system, it is hard to judge how suitable the selected feature is. To solve this problem, it is essential to analyze the feature itself, and measure how good the feature itself is. Good speech features should contain all of the class-related information and as small amount of the class-irrelevant variation as possible. In this paper, we suggest a method to measure the class-related information and the amount of the class-irrelevant variation based on the Shannon's information theory. Using this method, we compare the mel-scaled FFT, cepstrum, mel-cepstrum, and wavelet features of the TIMIT speech data. The result shows that, among these features, the mel-scaled FFT is the best feature for speech recognition based on the proposed measure.

  • PDF

Robust Speech Recognition in the Car Interior Environment having Car Noise and Audio Output (자동차 잡음 및 오디오 출력신호가 존재하는 자동차 실내 환경에서의 강인한 음성인식)

  • Park, Chul-Ho;Bae, Jae-Chul;Bae, Keun-Sung
    • MALSORI
    • /
    • no.62
    • /
    • pp.85-96
    • /
    • 2007
  • In this paper, we carried out recognition experiments for noisy speech having various levels of car noise and output of an audio system using the speech interface. The speech interface consists of three parts: pre-processing, acoustic echo canceller, post-processing. First, a high pass filter is employed as a pre-processing part to remove some engine noises. Then, an echo canceller implemented by using an FIR-type filter with an NLMS adaptive algorithm is used to remove the music or speech coming from the audio system in a car. As a last part, the MMSE-STSA based speech enhancement method is applied to the out of the echo canceller to remove the residual noise further. For recognition experiments, we generated test signals by adding music to the car noisy speech from Aurora 2 database. The HTK-based continuous HMM system is constructed for a recognition system. Experimental results show that the proposed speech interface is very promising for robust speech recognition in a noisy car environment.

  • PDF

Noisy Speech Recognition Based on Noise-Adapted HMMs Using Speech Feature Compensation

  • Chung, Yong-Joo
    • Journal of the Institute of Convergence Signal Processing
    • /
    • v.15 no.2
    • /
    • pp.37-41
    • /
    • 2014
  • The vector Taylor series (VTS) based method usually employs clean speech Hidden Markov Models (HMMs) when compensating speech feature vectors or adapting the parameters of trained HMMs. It is well-known that noisy speech HMMs trained by the Multi-condition TRaining (MTR) and the Multi-Model-based Speech Recognition framework (MMSR) method perform better than the clean speech HMM in noisy speech recognition. In this paper, we propose a method to use the noise-adapted HMMs in the VTS-based speech feature compensation method. We derived a novel mathematical relation between the train and the test noisy speech feature vector in the log-spectrum domain and the VTS is used to estimate the statistics of the test noisy speech. An iterative EM algorithm is used to estimate train noisy speech from the test noisy speech along with noise parameters. The proposed method was applied to the noise-adapted HMMs trained by the MTR and MMSR and could reduce the relative word error rate significantly in the noisy speech recognition experiments on the Aurora 2 database.

A Study on the Speech Recognition of Korean Phonemes Using Recurrent Neural Network Models (순환 신경망 모델을 이용한 한국어 음소의 음성인식에 대한 연구)

  • 김기석;황희영
    • The Transactions of the Korean Institute of Electrical Engineers
    • /
    • v.40 no.8
    • /
    • pp.782-791
    • /
    • 1991
  • In the fields of pattern recognition such as speech recognition, several new techniques using Artifical Neural network Models have been proposed and implemented. In particular, the Multilayer Perception Model has been shown to be effective in static speech pattern recognition. But speech has dynamic or temporal characteristics and the most important point in implementing speech recognition systems using Artificial Neural Network Models for continuous speech is the learning of dynamic characteristics and the distributed cues and contextual effects that result from temporal characteristics. But Recurrent Multilayer Perceptron Model is known to be able to learn sequence of pattern. In this paper, the results of applying the Recurrent Model which has possibilities of learning tedmporal characteristics of speech to phoneme recognition is presented. The test data consist of 144 Vowel+ Consonant + Vowel speech chains made up of 4 Korean monothongs and 9 Korean plosive consonants. The input parameters of Artificial Neural Network model used are the FFT coefficients, residual error and zero crossing rates. The Baseline model showed a recognition rate of 91% for volwels and 71% for plosive consonants of one male speaker. We obtained better recognition rates from various other experiments compared to the existing multilayer perceptron model, thus showed the recurrent model to be better suited to speech recognition. And the possibility of using Recurrent Models for speech recognition was experimented by changing the configuration of this baseline model.

Intra-and Inter-frame Features for Automatic Speech Recognition

  • Lee, Sung Joo;Kang, Byung Ok;Chung, Hoon;Lee, Yunkeun
    • ETRI Journal
    • /
    • v.36 no.3
    • /
    • pp.514-517
    • /
    • 2014
  • In this paper, alternative dynamic features for speech recognition are proposed. The goal of this work is to improve speech recognition accuracy by deriving the representation of distinctive dynamic characteristics from a speech spectrum. This work was inspired by two temporal dynamics of a speech signal. One is the highly non-stationary nature of speech, and the other is the inter-frame change of a speech spectrum. We adopt the use of a sub-frame spectrum analyzer to capture very rapid spectral changes within a speech analysis frame. In addition, we attempt to measure spectral fluctuations of a more complex manner as opposed to traditional dynamic features such as delta or double-delta. To evaluate the proposed features, speech recognition tests over smartphone environments were conducted. The experimental results show that the feature streams simply combined with the proposed features are effective for an improvement in the recognition accuracy of a hidden Markov model-based speech recognizer.

Speech Recognition in Noise Environment by Independent Component Analysis and Spectral Enhancement (독립 성분 분석과 스펙트럼 향상에 의한 잡음 환경에서의 음성인식)

  • Choi Seung-Ho
    • MALSORI
    • /
    • no.48
    • /
    • pp.81-91
    • /
    • 2003
  • In this paper, we propose a speech recognition method based on independent component analysis (ICA) and spectral enhancement techniques. While ICA tris to separate speech signal from noisy speech using multiple channels, some noise remains by its algorithmic limitations. Spectral enhancement techniques can compensate for lack of ICA's signal separation ability. From the speech recognition experiments with instantaneous and convolved mixing environments, we show that the proposed approach gives much improved recognition accuracies than conventional methods.

  • PDF

Applying Mobile Agent for Internet-based Distributed Speech Recognition

  • Saaim, Emrul Hamide Md;Alias, Mohamad Ashari;Ahmad, Abdul Manan;Ahmad, Jamal Nasir
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 2005.06a
    • /
    • pp.134-138
    • /
    • 2005
  • There are several application have been developed on internet-based speech recognition. Internet-based speech recognition is a distributed application and there were various techniques and methods have been using for that purposed. Currently, client-server paradigm was one of the popular technique that been using for client-server communication in web application. However, there is a new paradigm with the same purpose: mobile agent technology. Mobile agent technology has several advantages working on distributed internet-based system. This paper presents, applying mobile agent technology in internet-based speech recognition which based on client-server processing architecture.

  • PDF

The Study on Korean Phoneme for Korean Speech Recogintion

  • Hwang, Young-Soo
    • Proceedings of the IEEK Conference
    • /
    • 2000.07b
    • /
    • pp.629-632
    • /
    • 2000
  • In this paper, we studied on the phoneme classification for Korean speech recognition. In the case of making large vocabulary speech recognition system, it is better to use phoneme than syllable or word as recognition unit. And, In order to study the difference of speech recognition according to the number of phoneme as recognition unit, we used the speech toolkit of OGI in U.S.A as recognition system. The result showed that the performance of diphthong being unified was better than that of seperated diphthongs, and we required the better result when we used the biphone than when using mono-phone as recognition unit.

  • PDF

Noise Robust Speech Recognition Based on Noisy Speech Acoustic Model Adaptation (잡음음성 음향모델 적응에 기반한 잡음에 강인한 음성인식)

  • Chung, Yongjoo
    • Phonetics and Speech Sciences
    • /
    • v.6 no.2
    • /
    • pp.29-34
    • /
    • 2014
  • In the Vector Taylor Series (VTS)-based noisy speech recognition methods, Hidden Markov Models (HMM) are usually trained with clean speech. However, better performance is expected by training the HMM with noisy speech. In a previous study, we could find that Minimum Mean Square Error (MMSE) estimation of the training noisy speech in the log-spectrum domain produce improved recognition results, but since the proposed algorithm was done in the log-spectrum domain, it could not be used for the HMM adaptation. In this paper, we modify the previous algorithm to derive a novel mathematical relation between test and training noisy speech in the cepstrum domain and the mean and covariance of the Multi-condition TRaining (MTR) trained noisy speech HMM are adapted. In the noisy speech recognition experiments on the Aurora 2 database, the proposed method produced 10.6% of relative improvement in Word Error Rates (WERs) over the MTR method while the previous MMSE estimation of the training noisy speech produced 4.3% of relative improvement, which shows the superiority of the proposed method.