Spoken language understanding (SLU) refers to the process of inferring the semantic information from audio signals.While the neural transformers consistently deliver the best performance among the state-of-the-art neural architectures in field of natural language processing (NLP), their merits in a closely related field, i.e., spoken language understanding (SLU) have not beed investigated. In this paper, we introduce an end-toend neural transformer-based SLU model that can predict the variable-length domain, intent, and slots vectors embedded in an audio signal with no intermediate token prediction architecture. This new architecture leverages the self-attention mechanism by which the audio signal is transformed to various subsubspaces allowing to extract the semantic context implied by an utterance. Our end-to-end transformer SLU predicts the domains, intents and slots in the Fluent Speech Commands dataset with accuracy equal to 98.1 %, 99.6 %, and 99.6 %, respectively and outperforms the SLU models that leverage a combination of recurrent and convolutional neural networks by 1.4 % while the size of our model is 25% smaller than that of these architectures. Additionally, due to independent sub-space projections in the self-attention layer, the model is highly parallelizable which makes it a good candidate for on-device SLU.

Although speech recognition has become a widespread technology, inferring emotion from speech signals remains a challenge. Our paper addresses this problem by proposing a quaternion convolutional neural network (QCNN) based speech emotion recognition (SER) model in which Mel-spectrogram features of speech signals are encoded in an RGB quaternion domain. We demonstrate that our QCNN based SER model outperforms other real-valued methods in the Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS, 8-classes) dataset, achieving, to the best of our knowledge, state-of-the-art results. The QCNN model also achieves comparable results with state-of-the-art methods in the Interactive Emotional Dyadic Motion Capture (IEMOCAP 4-classes) and Berlin EMO-DB (7-classes) datasets. Specifically, the model achieves an accuracy of 77.87%, 70.46%, and 88.78% for the RAVDESS, IEMOCAP, and EMO-DB datasets, respectively.Additionally, model size results reveal that the quaternion unit structure is significantly better able to encode internal dependencies than real-valued structures.

No abstract

Transformers are powerful neural architectures that allow integrating different modalities using attention mechanisms. In this paper, we leverage the neural transformer architectures for multi-channel speech recognition systems, where the spectral and spatial information collected from different microphones are integrated using attention layers. Our multi-channel transformer network mainly consists of three parts: channel-wise self attention layers (CSA), cross-channel attention layers (CCA), and multi-channel encoder-decoder attention layers (EDA). The CSA and CCA layers encode the contextual relationship "within" and "between" channels and across time, respectively. The channel-attended outputs from CSA and CCA are then fed into the EDA layers to help decode the next token given the preceding ones. The experiments show that in a far-field in-house dataset, our method outperforms the baseline single-channel transformer, as well as the super-directive and neural beamformers cascaded with the transformers.

No abstract