Research Article Implementation of a Tour Guide Robot System Using RFID Technology and Viterbi Algorithm-Based HMM for Speech Recognition

Transcription

1 Mathematical Problems in Engineering, Article ID , 7 pages Research Article Implementation of a Tour Guide Robot System Using RFID Technology and Viterbi Algorithm-Based HMM for Speech Recognition Neng-Sheng Pai, Hua-Jui Kuang, Ting-Yuan Chang, Ying-Che Kuo, and Chun-Yuan Lai Department of Electrical Engineering, National Chin-Yi University of Technology, No. 57, Section 2, Zhongshan Road, Taiping District, Taichung 41170, Taiwan Correspondence should be addressed to Neng-Sheng Pai; pai@mail.ncut.edu.tw Received 3 January 2014; Accepted 1 March 2014; Published 24 March 2014 Academic Editor: Her-Terng Yau Copyright 2014 Neng-Sheng Pai et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. This paper applied speech recognition and RFID technologies to develop an omni-directional mobile robot into a robot with voice control and guide introduction functions. For speech recognition, the speech signals were captured by short-time processing. The speaker first recorded the isolated words for the robot to create speech database of specific speakers. After the speech pre-processing of this speech database, the feature parameters of cepstrum and delta-cepstrum were obtained using linear predictive coefficient (LPC). Then, the Hidden Markov Model (HMM) was used for model training of the speech database, and the Viterbi algorithm was used to find an optimal state sequence as the reference sample for speech recognition. The trained reference model was put into the industrial computer on the robot platform, and the user entered the isolated words to be tested. After processing by the same reference model and comparing with previous reference model, the path of the maximum total probability in various models found using the Viterbi algorithm in the recognition was the recognition result. Finally, the speech recognition and RFID systems were achieved in an actual environment to prove its feasibility and stability, and implemented into the omni-directional mobile robot. 1. Introduction For speech recognition, the dissimilarity between the signal characteristic values and the characteristic values in the database was calculated in early stages to identify the minimum difference as the recognition result. However, this method has a problem of poor recognition effect due to different talking speeds. Afterwards, some scholars proposed the dynamic time warping (DTW) to improve the recognition effect [1, 2]. This method assumes two speech signal segments to be compared, and the short-time feature parameters of the two segments of speech are extracted, namely, separated into a string of frames to determine a group of parameters from each frame. The comparison between two segments of speech is indeed the comparison between two sequence feature parameters. The DTW can adjust the speech length to reduce the errors in the speech time span. In the recognition system following DTW, the Artificial Neural Network (ANN) and HMM algorithms were proposed. The ANN is a method often used in the artificial intelligence domain [3, 4]. The ANN does not need to know the mathematical model of the system in experimental data modeling and highly complex recognition of images, letters, or sound, so that it can replace system models. Knowing the typeofoutputsgeneratedfromthetypeofinputcouldachieve good recognition effect after learning and repeated training. However, the ANN updates weights and bias iteratively, and the amount of calculation is large, so it consumes a lot of computer resources. The HMM uses probability model to describe the pronunciation in statistics [5 7]. A continuous statetransitioninmarkovmodelcanberegardedasthe phonation of a short speech segment, namely, a string of connected HMM, which is the representative for segment of speech. The HMM is a method mostly used in speech

2 2 Mathematical Problems in Engineering RF 9 V Computer side RFID reader RFID tag 24 V lead acid battery Transform to 5 V. 9 V. 24 V Power circuit RS232 RF 110 V 5 V 5 V User side Industrial computer Motor encoder I/O RS232 Encoder board Wireless handset Bluetooth I/O USB 5 V 9 V RFID tag Bluetooth dongle Bluetooth serial adapter RS232 PIC microcontroller 12 V lead acid battery 5 V Ultrasonic seneor I/O 9 V 12 C PIC microcontroller Omnidirectional mobile robot side 500 W power inverter DC motor 24 V PWM Motor driver Figure 1: Robot system hardware link. recognition in recent years. This paper uses the HMM as the speech recognition core. 2. Hardware Design The direction of the voice controlled guide type omnidirectional mobile robot is controlled by voice, and the robot has the RFID guide system and infrared image tracking and ultrasonic obstacle avoidance functions [8]. All of the proposed robot systems are configured with three subsystems; they are omnidirectional mobile robot side, computer side, and user side and shown in Figure 1. ThePeripheral Interface Controller (PIC) microcontroller is the core on the omnidirectional mobile robot side; its main function includes signal process of peripheral devices and motor drive control for three wheels. The computer side uses an industrial computer processing speech recognition calculation, RFID guidesystem,andinfraredimagetracking.theusersideuses a wireless headset and the RFID active tag as voice control equipments. 3. HMM-Based Speech Recognition System 3.1. Preprocessing and Feature Parameter Extraction. The speech signals are preprocessed before speech recognition. The speech preprocessing contains sampling, frame, endpoint detection, preemphasis, and windowing. After the speech signal preprocessing, the characteristic feature parameters are identified for subsequent recognition calculation. In this paper, the Linear Predictive Coefficient (LPC) is used to deduce the cepstrum and delta-cepstrum as the most important feature parameters. The concept of linear prediction originates from that the amplitude of a sampling point is related to the amplitude of an adjacent sampling point during pronunciation. If the postsampling sequence of speech signals is S(n), the present sample of speech signal, that is, S(n), isthesamplevaluesof time n.if S(n) isthepredictedvalueofs(n),sincetheremust be an error between the predicted value and the actual value, the predicted error can be expressed as e(n), as follows: e (n) =S(n) S (n) =S(n) l j=1 a j S(n j), (1) where a j is the linear predictive coding and l is the order number of linear prediction. The coefficient a j is adjusted; as long as the squared error value of (1) is minimized, an optimal linear predictive coefficient a j can be obtained. The autocorrelation is determined before solving the linear predictive coefficient, and then the wanted linear predictive coefficient is obtained from the obtained autocorrelation using the Durbin algorithm. After determining the LPC, the cepstrum coefficient is deduced from the LPC [9]. The cepstrum coefficient separates the vocal tract model from excitation signal, and it can calculate the vocal tract parameters more precisely, so as to control

3 Mathematical Problems in Engineering 3 Start RFID actives tag transmits signal No Whether RFID reader receives tag signal or not RFID reader continues detection Yes Fixed tag is read Tag ID recognition Tag in user's hand is read No Introduce or not (speech recognition system) Yes Introduce the site End Enter verbal command on direction Speech recognition system Robot movement control Figure 2: System operation flow of voice controlled guide type omnidirectional mobile robot. j 1 c j =a j + k=1 (1 k j ) a k c j k, (1 < j l), c j = p k=1 (1 k j ) a k c j k, (j > l). (2) In a practical environment, the external noise influences the speech receiving, so that the tone in the spectrum is disturbed and distorted. The delta-cepstrum can reduce this noise effect. The delta-cepstrum parameter Δ c j (t) is shown in (3), where τ isthenumberofrelatedformer( K)orlatter frames (K). The cepstrum and delta-cepstrum parameters are to be used as feature parameters for recognition: Figure 3: Omnidirectional mobile robot. the speech spectrum characteristics. The cepstrum coefficient c j is determined from the linear predictive coefficient a j, where l is the order number of linear prediction, shown as follows: c 1 =a 1, Δ c j (t) = d c j (t) dt 3.2. HMM and Training Reference Model = K τ= K τ c j (t+τ) K τ= K τ2. (3) Build the Initial Model. The states and frames are separated averagely from the audio part of a segment of speech according to the preset HMM state number, and the feature vectors in the frames are used to calculate the mean value M j and variance Var j,asshownin(4), where A is a state of HMM, i is the frame, j is the feature parameter, T is thenumberofframesinastate,andq is the number of feature vectors of cepstrum and delta-cepstrum. This paper uses 15

4 4 Mathematical Problems in Engineering (a) (b) (c) (d) Figure 4: User using speech to control robot to move forward and turn left. (a) User commands robot to move forward. (b) User commands robot to stop. (c) User commands robot to turn left. (d) Robot turns left and moves on. cepstrum and 15 delta-cepstrum as characteristic values, and q is 30: M j = T i=1 A (i, j), 1 j q, T Var j = T i=1 [A (i, j)]2 (M T j ) 2, 1 j q. (4) Viterbi Algorithm. In order to obtain the correct relationshipbetweenframeandhmmstatemoreaccurately,this paperusesagaussian probabilityfunction [10] to determine thesimilarityprobabilityvalueofstateandframe.ahigher probability value indicates a higher similarity between the corresponding frame and the state, as shown in (5), where G i (x T ) is the probability value of each state corresponding to its frame, d is the feature vector dimension, x T is the feature vector, τ Ri isthemeanvalueofstates,r i is the covariance

5 Mathematical Problems in Engineering 5 (a) (b) (c) (d) Figure 5: Robot guide experiment. (a) User commands robot to move forward. (b) Robot detects tag and asks user whether he needs any introduction to the place or not. (c) User says YES. (d) Robot plays video. matrix of the density function, and G i (x T ) is the probability value of similarity between the feature vector x T and state i: 1 G i (x T )= exp { 1 (2π) d R 2 (x T τ Ri ) T R 1 i (x T τ Ri )}. i (5) The HMM can be represented by λ={π, A, B, S, V}, (6) where S = {s 1,s 2,...,s N } is the state sequence, N is the state number, V is the observed results, π = {π i } is the initial state probability, A = {a ij } is the state transition probability, B={b j (O t )} is the state observation probability, O t ={O 1,O 2,...,O T } is the observation sequence, and T is thesequencelength. The Gaussian probability density function determines the probability value between frame and state. The HMM has many optional paths for state transition, and the path with the maximum total probability value among all possible paths is

6 6 Mathematical Problems in Engineering required to be found. This paper uses the Viterbi algorithm [11, 12], as shown in (7) (10), where δ i (i) is the probability of staying in state i at time t. ψ t (i) is the probability of reaching state i at time t, p isthefinalprobabilityvalueoftheviterbi algorithm, and S T is the optimal state sequence. Step 1. Initializing Step 2. Recursing Step 3. Terminating δ t (i) =π i b i (o 1 ), ψ t (i) =0. 1 i N, δ t+1 (j) = max 1 i N [δ t (i) a ij ] b j (o t+1 ) Step 4. Path backtracking ψ t+1 (j) = arg max [δ t (i) a ij ], 1 i N 1 t T 1; 1 j N. p= max [δ t (i)], 1 i N S T = arg max [δ t (i)]. 1 i N (7) (8) (9) S t =ψ t+1 (S t+! ), t=t 1,T 2,T 3,...1. (10) Reevaluation. After the new relationship between state and frame is obtained using the Viterbi algorithm, the mean value and variance in old state are updated, and the Gaussian density function is used to determine the updated probabilitybetweenstateandframeagain.thenewtotal probability value is obtained using the Viterbi algorithm. The update continues until the maximum total probability value is converged, and this is the reference model after training Speech Recognition. The needed commands are trained into models, which serve as reference database of speech recognition. The feature parameters are determined according to previous procedure during recognition. The reference modelsofdatabasearecomparedusingtheviterbialgorithm to determine the probability value of each model and find the optimal state sequence. The time warping of speech signals is solved automatically when corresponding to a sequence of frames to the state sequence. The key point in the speech training procedure is to identify the correlation betweenframeandstate.therelationshipbetweenframeand state should be updated by continuous path backtracking of Viterbi, until the path with the maximum total probability is determined. The most important step in the recognition procedure is to compare the reference models of training and obtain the maximum total probability value in reference models. Table 1: Recognition rates for the speaker dependent and speaker independent. Speaker dependent Recognition rates Chun-Yuan 96.7% Jian-Min 93.3% Yi-Chung 90% Wei 96.7% Hung-Hui 93.3% Average recognition rates 94% Speaker independent Recognition rates Jason 66.7% Ian 73.3% Andy 90% Momo 83.3% Apple 50% Average recognition rates 74.7% 4. Experiment Results Figure 2 shows the system operation flow of the voice controlled guide type omnidirectional mobile robot. In the RFID guide system, the Reader captures Tag data and then attaches environmental information to the Tags of different ID codes or starts up the speech function. Figure 3 shows the picture of the proposed omnidirectional mobile robot. We place the robot in the actual environment and test various moving actions (forward, backward, turn left, turn right, stop, and turn back). The voice control of speaker dependent and speaker independent are tested by five users, respectively, and the experimental results of speech recognition rates are shown in Table 1. Figure 4 shows the experiment of the user using speech to control the robot to move forward and turn left. Figure 5 shows the user using speech to control the robot to move forward, receiving the Tag of the classroom when passingbytheclassroom,theusercanuseyesornotochoose whether accessing detailed information on the site. The site is introduced in the video format, so that the user can get acquainted with the environment quickly. 5. Conclusions This paper used the HMM-based speech recognition method to complete a voice controlled guide type omnidirectional mobile robot. The first convenience of voice control is that the operation does not require manual operation, which makes the robot more user-friendly. The guide system based on RFID technology enables the users to know the information of an unfamiliar environment quickly. Finally, the robot movement experiment and the robot guide system experiment proved the feasibility and stability of this voice controlled guide type omnidirectional mobile robot. Conflict of Interests The authors declare no conflict of interests.

7 Mathematical Problems in Engineering 7 Acknowledgment The financial support of this research by the National Science Council of Taiwan, under Grant no. NSC E is greatly appreciated. References [1] H. Sakoe and S. Chiba, Dynamic programming algorithm optimization for spoken word recognition, IEEE Transactions on Acoustics, Speech, and Signal Processing,vol.26,no.1,pp.43 49, [2] C. Kim and K.-D. Seo, Robust DTW-based recognition algorithmforhand-heldconsumerdevices, IEEE Transactions on Consumer Electronics,vol.51,no.2,pp ,2005. [3] D. P. Morgan and C. L. Scofield, Eds., Neural Networks and Speech Processing, Kluwer Academic Publishers, [4] C.-F. Juang, C.-T. Chiou, and C.-L. Lai, Hierarchical singletontype recurrent neural fuzzy networks for noisy speech recognition, IEEE Transactions on Neural Networks, vol.18,no.3,pp , [5] L. R. Rabiner, A tutorial on hidden Markov Models and selected applications in speech recognition, IEEE T Acoust Speech, vol. 77, pp , [6] S.Yoshizawa,N.Wada,N.Hayasaka,andY.Miyanaga, Scalable architecture for word HMM-based speech recognition and VLSI implementation in complete system, IEEE Transactions on Circuits and Systems I: Regular Papers,vol.53,no.1,pp.70 77, [7] J.-H. Im and S.-Y. Lee, Unified training of feature extractor and HMM classifier for speech recognition, IEEE Signal Processing Letters,vol.19,no.2,pp ,2012. [8] S. F. Huang, Design and Implementation of an Autonomous Following Omni-Directional Mobile Robot, National Digital Library of Theses and Dissertations, Taipei, Taiwan, [9] Y. Yuan, P. Zhao, and Q. Zhou, Research of speaker recognition based on combination of LPCC and MFCC, in Proceedings of the IEEE International Conference on Intelligent Computing and Intelligent Systems (ICIS 10), pp , Xiamen, China, October [10] L. Liu and J. He, On the use of orthogonal GMM in speaker recognition, in Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 99), pp , Phoenix, Ariz, USA, March [11] C. C. Wen, Ed., Multimedia Applications for Speech Recognition System, National Digital Library of Theses and Dissertations, Taipei, Taiwan, [12] D. F. Tseng, Robust decoding for convolutionally coded systems impaired by memoryless impulsive noise, IEEE Transactions on Communications,vol.61,pp ,2013.

8 Advances in Operations Research Advances in Decision Sciences Applied Mathematics Algebra Probability and Statistics The Scientific World Journal International Differential Equations Submit your manuscripts at International Advances in Combinatorics Mathematical Physics Complex Analysis International Mathematics and Mathematical Sciences Mathematical Problems in Engineering Mathematics Discrete Mathematics Discrete Dynamics in Nature and Society Function Spaces Abstract and Applied Analysis International Stochastic Analysis Optimization