Understanding three simultaneous speeches is proposed as a challenge problem to foster artificial intelligence, speech and sound understanding or recognition, and computational auditory scene analysis research. Automatic speech recognition under noisy environments is attacked by speech enhancement techniques such as noise reduction and speaker adaptation. However, the signal-to-noise ratio of s...

In our daily lives, auditory stream segregation allows us to differentiate concurrent sound sources and to make sense of the scene we are experiencing. However, a combination of segregation and the concurrent integration of auditory streams is necessary in order to analyze the relationship between streams and thus perceive a coherent auditory scene. The present functional magnetic resonance ima...

When listeners hear sequences of tones that slowly alternate between a low frequency and a slightly higher frequency, they tend to report hearing a single stream of alternating tones. However, when the alternation rate and/or the frequency difference increases, they often report hearing two distinct streams: a slowly pulsing high and low frequency stream. This experiment used repeating sequence...

We propose a novel method of pitch track correction that uses an ensemble Kalman filter to improve the performance of monaural speech segregation. The proposed method considers all reliable pitch streaks for pitch track correction, whereas the conventional segregation approach relies on only the longest streak in a given speech stream. In addition, unreliable pitch streaks are corrected with an...

Three theories of auditory stream segregation were evaluated. In two-part trials, subjects heard an induction sequence, whose effects upon an immediately subsequent test sequence were measured. The rhythm and total duration of Induction Sequence tones were varied in two experiments. The similarity between induction and test sequences aided segregation, but rhythmic predictability and longer ton...