8 accepted papers
Large speech emotion recognition datasets are hard to obtain, and small datasets may contain biases. Deep-net-based classifiers, in turn, are prone to exploit those biases and find shortcuts such as speaker characteristics. These shortcuts usually harm a model’s ability to generalize. To address thi…
Self-supervised pre-trained features have consistently delivered state-of-art results in the field of natural language processing (NLP); however, their merits in the field of speech emotion recognition (SER) still need further investigation. In this paper we introduce a modular End-to-End (E2E) SER…
Recent innovations in self-supervised representation learning have led to remarkable advances in natural language processing. That said, in the speech processing domain, self-supervised representation learning-based systems are not yet considered state-of-the-art.We propose leveraging recent advance…
Speaker change detection is often addressed as a key component in speaker diarization systems. In this work we focus on online speaker change detection as a standalone task which is required for online closed captioning of broadcast television. Contrary to related works, we do not operate on frame-l…
Neural network based attention modeling has found utility in areas such as visual analysis, speech recognition and more recently speaker recognition. Attention represents a gating (or weighting) function on information and governs how the corresponding statistics are accumulated. In the context of s…
This paper discusses some challenges and opportunities in developing a speaker diarization system for operation on real world call center telephony data. We contrast some of the differences between a standard data set akin to NIST evaluations and those found in call centers. In exploring these diffe…
Many speaker diarization systems operate in an off-line mode. Such systems typically find homogeneous segments and then cluster these segments according to speaker. Such algorithms, like bottom-up clustering, k-means or spectral clustering, generally require the registration of all segments before c…
Many state-of-the-art speaker recognition engines use i-vectors to represent variable-length acoustic signals in a fixed low-dimensional total variability subspace. While such systems perform well under seen channel conditions, their performance greatly degrades under unseen channel scenarios. Accor…