The TAx511x and TAx521x devices are a family of high performance stereo codecs suitable for Land Mobile Radio, IP Network and Telephone, Video Conferencing, and Professional Audio Equipment. This family of devices has an extensive set of features that include the following:
This application note describes how to configure the Voice Activity Detection (VAD) feature in TAx511x and TAx521x devices (TAA5111, TAA5112, TAC5111, TAC5112, TAA5211, TAA5212, TAC5211, TAC5212).
All trademarks are the property of their respective owners.
The Voice Activity Detection (VAD) algorithm is a voice-triggered, system wake-up mechanism. The VAD feature enables the device or system (depending on the application) to be in sleep mode: consuming minimal power in the absence of voice activity. The TAx5x1x can generate an interrupt upon the detection of voice activity.Figure 1-1 shows how the VAD responds to voice activity.
The VAD feature is supported on all analog-to-digital converter (ADC) channels of the TAx511x and TAx521x device family, including digital microphone channels, with one channel being monitored at a time. The digital microphone channel is preferred for low-power applications. TI recommends that the audio sampling rate of the device be 8kHz for best performance, however 48kHz is supported if higher fidelity is needed. This application note describes the operation of the VAD, the tunable parameters, and the device configurations required to support VAD.
The VAD algorithm uses a decision tree classification-based algorithm for voice activity detection. The VAD block monitors the input signal from the microphone channels for a voice-like profile and upon detection of a voice activity pattern, the VAD block triggers an interrupt. The VAD monitors for both an onset of voice activity as well as the end of voice activity. Both of these events can be mapped to interrupts.
The TAx511x or TAx521x device also has the capability to automatically power-on and power-off based on the VAD interrupts. As an example, the TAx511x or TAx521x system can be set up to monitor VAD activity on a digital microphone channel and then power on the analog microphone channels based on the VAD trigger. By using the VAD to control the ADC power-on and power-off behavior, power savings can be achieved, compared to leaving the ADC powered on at all times.
The VAD has three modes that determine the behavior of the ADC record path:
Note that in all modes, the device generates an interrupt on the configured pin which can be sent to an external DSP or SOC.
The salient features of VAD are as follows:
Automatic switching between VAD mode and Record mode - The system switches from VAD mode to record mode upon voice activity and switches back to VAD mode upon no voice activity in Auto VAD mode.