Page 43

EETE SEPTEMBER 2012

Figure 1. Disturbances in Figure 2. Conexant’s CX20805 voice input processor automobile environment tially from multiple independent tracks. This makes the echo combined with a low power yet high performance 800 MIPS cancelling problem significantly more difficult, as the algorithm DSP to perform the sophisticated algorithms described above. must try to estimate the different echo paths from the different Putting this all together, Conexant is able to offer a solution that speakers for multiple tracks from a limited number of micro- significantly improves the quality of voice reception in multiple phones. Some MAEC algorithms require modification of the environments. In particular, it has the potential to enable voice playback signal to be able to decorrelate the signals to where command systems in automobiles to work reliably and depend- these echo paths can be resolved. For high-fidelity audio such ably to where voice command becomes the preferred method modifications are not acceptable. Conexant has developed an of control by the driver. MAEC algorithm that does not require any such modifications yet is able to deliver true full-duplex performance. The result is that the speech recognition engine can reliably detect speech even with audio playback at a high level, without the need for a button-push to lower or squelch the playback level first. High dynamic range analog to digital converter (ADC) Human hearing has a large dynamic range, allowing people to hear signals over a 100dB span. This in turn means that signals encountered in everyday life span this range, from low-level whispers to rock music testing the upper limits of hearing tolerance. For an audio input system to effectively process its relevant inputs and remove all extraneous noise, the analog to digital converter needs to be able to cleanly convert the signals at all levels without saturating the high-level ones and at the same time avoiding noticeable quantization noise in the ADC itself or noise from the input amplifier. Many of the DSP algo- rithms depend on linearity of the input signal, and if it is satu- rated they will quickly break down. If the speech input itself is saturated, the speech recognition algorithm will perform poorly. To achieve optimal performance, Conexant has developed a microphone pre-amplifier and ADC that can achieve 106 dB dy- namic range, enough to cover the range of signal levels required for an automobile environment. For example, when playing loud music from the car radio, this dynamic range allows the MAEC to estimate and linearly subtract the radio signal echo received at the microphones, leaving only a clean representation of the driver’s commands. Conexant’s dedicated voice input processor Conexant has developed an integrated device, the CX20805, that performs all necessary voice input functions for speech recognition for multiple environments, including the automo- bile. It includes low-noise microphone preamplifiers and high MPLonG, +41e56s4r83 0,4C3H-,5F4a0x5+Dätt56il/49wit30r2and0lez3Sw14432.tnrfäTeAhP dynamic range ADCs supporting up to four microphones, www.electronics-eetimes.com Electronic Engineering Times Europe September 2012 35


EETE SEPTEMBER 2012
To see the actual publication please follow the link above