Challenges in Adopting Speech Control for Assistive Robots

This paper presents a pragmatic report about experiences gathered with the speech command interface of HOBBIT, a mobile assistive robot intended to support older persons in their private home. An outline of the associated problems and challenges in distant speech recognition is given. Far field detection of user’s voice commands is necessary due to user acceptance considerations. A commercially available automatic speech recognition (ASR) serves as base. Measurements of directivity of several microphones were done and ASR performance with a small vocabulary showed low word error rates (WER) in different acoustic environments: anechoic room (0 %), free space (2.6 %), AAL room (3.8 %) when using a small array microphone with beam forming. Further explorative trials in a free space setting with a second (disturbing) signal source resulted in a WER of 3.9 % (two voices) and 11.1 % (one voice and radio news) compared to 2.6 % in case of only one speaker.

[1]  Peter Mayer,et al.  A Laboratory for AAL Applications , 2013, Biomedizinische Technik. Biomedical engineering.

[2]  Stefan Goetze,et al.  Ambient Voice Control for a Personal Activity and Household Assistant , 2011 .

[3]  Rico Petrick Robuste Spracherkennung unter raumakustischen Umgebungsbedingungen , 2009 .

[4]  Elena Torta,et al.  Socially Assistive Robots: A Comprehensive Approach to Extending Independent Living , 2013, International Journal of Social Robotics.

[5]  P. Mayer,et al.  Examples of multimodal user interfaces for socially assistive robots in Ambient Assisted Living environments , 2012, 2012 IEEE 3rd International Conference on Cognitive Infocommunications (CogInfoCom).

[6]  Kerstin Dautenhahn,et al.  Socially intelligent robots: dimensions of human–robot interaction , 2007, Philosophical Transactions of the Royal Society B: Biological Sciences.

[7]  John McDonough,et al.  Distant Speech Recognition , 2009 .

[8]  Adriana Tapus,et al.  User—robot personality matching and assistive robot behavior adaptation for post-stroke rehabilitation therapy , 2008, Intell. Serv. Robotics.

[9]  Kai-Fu Lee,et al.  Automatic Speech Recognition , 1989 .

[10]  Paul Panek,et al.  A Social Assistive Robot in an Intelligent Environment , 2013, Biomedizinische Technik. Biomedical engineering.

[11]  D. Feil-Seifer,et al.  Defining socially assistive robotics , 2005, 9th International Conference on Rehabilitation Robotics, 2005. ICORR 2005..