1. HNS [1] HNS HNS HNS [2] HNS [3] [4] [5] HNS 16ch SNR [6] 1 16ch 1 3 SNR [4] [5] 2. 2 HNS API HNS CS27-HNS [1] (SOA) [7] API Web 2

Transcription

1 THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS TECHNICAL REPORT OF IEICE {soda,matsubara}@ws.cs.kobe-u.ac.jp, {masa-n,shinsuke,shin,yosimoto}@cs.kobe-u.ac.jp, [email protected], [email protected] (HNS) HNS HNS 16ch Handsfree Voice Interface for Home Network Service Using a Microphone Array Network Shimpei SODA, Masahide NAKAMURA, Shinsuke MATSUMOTO, Noriyuki MATSUBARA, Koji KUGATA, Shintaro IZUMI, Hiroshi KAWAGUCHI, and Masahiko YOSHIMOTO Kobe University Rokkoudai-cho 1 1, Nada-ku, Kobe, Hyogo, Japan {soda,matsubara}@ws.cs.kobe-u.ac.jp, {masa-n,shinsuke,shin,yosimoto}@cs.kobe-u.ac.jp, [email protected], [email protected] Abstract The voice control is a promising user interface for the home network system (HNS). In our previous interface, a user had to be equipped with an actual microphone device, which imposed a burden on the user. This paper presents a hands-free voice interface using a microphone array network. The microphone array network enables voice quality enhancement, as well as sound source localization, by networking multiple microphone arrays. Attaching the arrays to the walls or ceiling, users can input voice operations to the HNS from anywhere in the room, without being aware of the microphone devices. We implement a prototype system with a 16ch microphone array, and evaluate the accuracy of speech recognition, sound source localization, and voice activity detection in a real home network environment. The hands-free operation service and automatic speech logging service are implemented as practical services. Key words microphone array network, home netwrok services, voice interface, hands free 1

2 1. HNS [1] HNS HNS HNS [2] HNS [3] [4] [5] HNS 16ch SNR [6] 1 16ch 1 3 SNR [4] [5] 2. 2 HNS API HNS CS27-HNS [1] (SOA) [7] API Web 2

3 2 3 (a) (b) TD-BD-16USB HNS R1 HNS R2 HNS R3 HNS (location-aware) 3. 2 R3 R1, R2 16ch 2 (Voice Activity Detection VAD) C++ (Sound Source Localization, SSL) (Sound SourceSeparation, SSS) Matlab 16 ch Matlab 4 1ch HNS (a) 30cm 16 3(b) (TD-BD-16USB ) PC PC / 3. 4 (VAD) [8] 0 ( 4) ch 3

4 (SSL) 5 MUSIC [9] P (ω, θ, ϕ) (θ, ϕ) P (ω, θ, ϕ) = v(ω, θ, ϕ) 2 (1) v H (ω, θ, ϕ)e n 2 v(ω, θ, ϕ) E n θ ϕ v(ω, θ, ϕ) P (ω, θ, ϕ) 5 3 P m 3. 6 (SSS) [10] ( 6) Delay 4. HNS HNS [2] 7 SNR Web 4

5 HNS HNS m HNS m 3.0m 4.0m ( 9) m (5 4 ) IC (PCM-D50 sony ) IC

6 2 Clipping ratio Sleeping ratio IC 16 IC Clipping ratio: Sleeping ratio: Clipping ratio 72 Sleeping ratio Clipping ratio Sleeping ratio Sleeping ratio Clipping ratio 16ch m 74 HNS 7. (STARC) B , B [1] M.Nakamura, A.Tanaka, H.Igaki, H.Tamada, and K.Matsumoto, Constructing home network systems and integrated services using legacy home appliances and web services, International Journal of Web Services Research, vol.5, no.1, pp.82 98, [2] 109 pp [3] T. Takagi, H. Noguchi, K. Kugata, M. Yoshimoto, and H. Kawaguchi, Microphone array network for ubiquitous sound acquisition, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp , [4] 2010 pp [5] S. Izumi, H. Noguchi, T. Takagi, K. Kugata, S.S. andm.yoshimoto, and H. Kawaguchi, Data aggregation protocol for multiple sound sources acquisition with microphone array network, 20th International Conference on Computer Communications and Networks(ICCCN), pp.1 6, [6] C. Australia and J. Glass, Loud: A 1020-node microphone array and acoustic, [7] M.P.Papazoglou and D.Georgakopoulos, Service-oriented computing, Communication of the ACM, vol.46, no.10, pp.25 28, [8] M.M.S. J. Benesty and Y. Huang, Springer handbook of speech processing, Springer-Verlag, [9] R. Schmidt, Multiple emitter location and signal parameter estimation, Antennas and Propagation, IEEE Transactions on, vol.34, pp , [10] K.B. Van Veen, Beamforming: a versatile approach to spatial filtering, ASSP Magazine, IEEE, vol.5, pp.4 24, HNS 6