In this paper we introduce a new framework of audio processing, which is essential to achieve a trigger-free speech interface for home appliances. If the speech interface works continually in real environments, it must extract occasional voice commands and reject everything else. It is extremely important to reduce the number of false alarms because the number of irrelevant inputs is much larger than the number of voice commands even for heavy users of appliances. The framework, called Intentional Voice Command Detection, is based on voice activity detection, but enhanced by various speech/audio processing techniques such as emotion recognition. The effectiveness of the proposed framework is evaluated using a newly-collected large-scale corpus. The advantages of combining various features were tested and confirmed, and the simple LDA-based classifier demonstrated acceptable performance. The effectiveness of various methods of user adaptation is also discussed.

This paper proposes an enhanced method for estimating the a priori Signal-to-Disturbance Ratio (SDR) to be employed in the Acoustic Echo and Noise Suppression (AENS) system for full-duplex hands-free communications. The proposed a priori SDR estimation technique is modified based upon the Two-Step Noise Reduction (TSNR) algorithm to suppress the background noise while preserving speech spectral components. In addition, a practical approach to determine accurately the Echo Spectrum Variance (ESV) is presented based upon the linear relationship assumption between the power spectrum of far-end speech and acoustic echo signals. The ESV estimation technique is then employed to alleviate the acoustic echo problem. The performance of the AENS system that employs these two proposed estimation techniques is evaluated through the Echo Attenuation (EA), Noise Attenuation (NA), and two speech distortion measures. Simulation results based upon real speech signals guarantee that our improved AENS system is able to mitigate efficiently the problem of acoustic echo and background noise, while preserving the speech quality and speech intelligibility.

This paper describes a hands-free speech recognition technique based on acoustic model adaptation to reverberant speech. In hands-free speech recognition, the recognition accuracy is degraded by reverberation, since each segment of speech is affected by the reflection energy of the preceding segment. To compensate for the reflection signal we introduce a frame-by-frame adaptation method adding the reflection signal to the means of the acoustic model. The reflection signal is approximated by a first-order linear prediction from the observation signal at the preceding frame, and the linear prediction coefficient is estimated with a maximum likelihood method by using the EM algorithm, which maximizes the likelihood of the adaptation data. Its effectiveness is confirmed by word recognition experiments on reverberant speech.

This paper describes the author's perspective on multimedia quality prediction methodologies for multimedia communications in advanced mobile and internet protocol (IP)-based telephony, and reports related experiments and trials. First, the paper describes the need for perceptual QoS (Quality of Service) assessment in which various quality factors in multimedia communications for advanced mobile and IP-based telephony are analyzed. Then an objective quality prediction scheme is proposed from the viewpoints of quality measurement tools for each quality factor and an opinion model for compound quality factors in mobile and IP-based communications networks. Finally, the author's current trials of measurement tools and opinion models are described.

We investigated the dependence of the desired echo return loss on frequency for various hands-free telecommunication conditions by subjective assessment. The desired echo return loss as a function of frequency (DERLf) is an important factor in the design and performance evaluation of a subband echo canceller, and it is a measure of what is considered an acceptable echo caused by electrical loss in the transmission line. The DERLf during single-talk was obtained as attenuated band-limited echo levels that subjects did not find objectionable when listening to the near-end speech and its band-limited echo under various hands-free telecommunication conditions. When we investigated the DERLf during double-talk, subjects also heard the speech in the far-end room from a loudspeaker. The echo was limited to a 250-Hz bandwidth assuming the use of a subband echo canceller. The test results showed that: (1) when the transmission delay was short (30 ms), the echo component around 2 to 3 kHz was the most objectionable to listeners; (2) as the transmission delay rose to 300 ms, the echo component around 1 kHz became the most objectionable; (3) when the room reverberation time was relatively long (about 500 ms), the echo component around 1 kHz was the most objectionable, even if the transmission delay was short; and (4) the DERLf during double-talk was about 5 to 10 dB lower than that during single-talk. Use of these DERLf values will enable the design of more efficient subband echo cancellers.