Subjective assessment of the desired echo return loss for subband acousticecho cancellers

We investigated the dependence of the desired echo return loss on frequency for various hands-free telecommunication conditions by subjective assessme nt The desired echo return loss as a function of frequency (DERLf) is all i mportant factor in the design and performance evaluation of a subband echo canceller, and it is a measure of what is considered all acceptable echo ca used by electrical loss in the transmission line. The DERLf during single t alk was obtained as attenuated band-limited echo levels that subjects did n ot find objectionable when listening to the near-end speech and its band-li mited echo under various hands-free telecommunication conditions. When we i nvestigated 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 band width assuming the use of a subband echo canceller. The test results showed that: (1) when the transmission delay was short (30 ms), the echo componen t around 2 to 3 kHz was the most objectionable to listeners. (2) as the tra nsmission delay rose to 300 ms, the echo component around 1 kHz became the most objectionable; (3) when the room reverberation time was relatively lon g (about 500 ms). the echo cumyonent around 1 kHz was the most objectionabl e even if the transmission delay was short; and ( 1) the DERLf during doubl e-talk was about 5 to 10dB lower than that during single-talk. Use of these DERLf values will enable the design of mure efficient subband echo cancell ers.