Automated Assessment of Glottal Dysfunction Through Unified Acoustic Voice Analysis.

This paper uses the recent glottal flow model for iterative adaptive inverse filtering to analyze recordings from dysfunctional speakers, namely those with larynx-related impairment such as laryngectomy. The analytical model allows extraction of the voice source spectrum, described by a compact set of parameters. This single model is used to visualize and better understand speech production characteristics across impaired and nonimpaired voices.

Local coding based matching kernel method for image classification.

This paper mainly focuses on how to effectively and efficiently measure visual similarity for local feature based representation. Among existing methods, metrics based on Bag of Visual Word (BoV) techniques are efficient and conceptually simple, at the expense of effectiveness. By contrast, kernel based metrics are more effective, but at the cost of greater computational complexity and increased storage requirements.

Deep bottleneck features for spoken language identification.

A key problem in spoken language identification (LID) is to design effective representations which are specific to language information. For example, in recent years, representations based on both phonotactic and acoustic features have proven their effectiveness for LID. Although advances in machine learning have led to significant improvements, LID performance is still lacking, especially for short duration speech utterances.

A new mechanical index for gauging the human bioeffects of low frequency ultrasound.

Low frequency ultrasound has a diverse set of industrial and medical applications ranging from high power industrial ultrasound equipment through to various therapeutic medical applications. In recent years, several speech interface applications have also been developed which exploit the low ultrasonic frequency region to augment human-computer interfacing. These devices tend to operate just above the threshold of human hearing where signals can be generated and detected using off-the-shelf audio hardware components.