The location of the desired speaker can be between −90°≤θ≤90°, as illustrated in Fig. 1.
However, to avoid the signal cancellation problem, the beamformer adaptation is halted when the desired speaker is active.
The compact clusters obtained for proposed method imply its ability to capture the formant structure of desired speaker.
Figure 7 Target and transformed spectral envelopes of the desired speaker using proposed method and baseline method.
We consider a multimodal setting, in which the speech signal is captured by a microphone, and a video camera is pointed at the face of the desired speaker.
A compact array of M microphones captures the signal of a desired speaker, unknown number of competing speakers, and background noise.
Preserving the binaural cues of the speech signal, particularly ILD and ITD, helps the listener to localize the desired speaker more precisely.
In the conversion stage, a given speech signal is decomposed into phonological and speaker-related information, the speaker-related information is replaced with that of the desired speaker, and then voice-converted speech is obtained by combining the two.
Since changes in the array's position correspond to the desired speaker's movement, the relative source-receiver position remains unchanged; hence, the need to track fluctuations of the steering vector is avoided.
where S m, I m, and V m are the signals of the desired speaker, the sum of competing speakers, and the noise, and t and k are time and frequency indices.
