Markus Müller

Kai Wei, Dillon Knox, Martin Radfar et al.

Dialogue act classification (DAC) is a critical task for spoken language understanding in dialogue systems. Prosodic features such as energy and pitch have been shown to be useful for DAC. Despite their importance, little research has explored neural approaches to integrate prosodic features into end-to-end (E2E) DAC models which infer dialogue acts directly from audio signals. In this work, we propose an E2E neural architecture that takes into account the need for characterizing prosodic phenomena co-occurring at different levels inside an utterance. A novel part of this architecture is a learnable gating mechanism that assesses the importance of prosodic features and selectively retains core information necessary for E2E DAC. Our proposed model improves DAC accuracy by 1.07% absolute across three publicly available benchmark datasets.

Gencer Sumbul, Markus Müller, Begüm Demir

Due to the availability of multi-modal remote sensing (RS) image archives, one of the most important research topics is the development of cross-modal RS image retrieval (CM-RSIR) methods that search semantically similar images across different modalities. Existing CM-RSIR methods require the availability of a high quality and quantity of annotated training images. The collection of a sufficient number of reliable labeled images is time consuming, complex and costly in operational scenarios, and can significantly affect the final accuracy of CM-RSIR. In this paper, we introduce a novel self-supervised CM-RSIR method that aims to: i) model mutual-information between different modalities in a self-supervised manner; ii) retain the distributions of modal-specific feature spaces similar to each other; and iii) define the most similar images within each modality without requiring any annotated training image. To this end, we propose a novel objective including three loss functions that simultaneously: i) maximize mutual information of different modalities for inter-modal similarity preservation; ii) minimize the angular distance of multi-modal image tuples for the elimination of inter-modal discrepancies; and iii) increase cosine similarity of the most similar images within each modality for the characterization of intra-modal similarities. Experimental results show the effectiveness of the proposed method compared to state-of-the-art methods. The code of the proposed method is publicly available at https://git.tu-berlin.de/rsim/SS-CM-RSIR.

Bhuvan Agrawal, Markus Müller, Martin Radfar et al.

End-to-end (E2E) spoken language understanding (SLU) systems can infer the semantics of a spoken utterance directly from an audio signal. However, training an E2E system remains a challenge, largely due to the scarcity of paired audio-semantics data. In this paper, we treat an E2E system as a multi-modal model, with audio and text functioning as its two modalities, and use a cross-modal latent space (CMLS) architecture, where a shared latent space is learned between the `acoustic' and `text' embeddings. We propose using different multi-modal losses to explicitly guide the acoustic embeddings to be closer to the text embeddings, obtained from a semantically powerful pre-trained BERT model. We train the CMLS model on two publicly available E2E datasets, across different cross-modal losses and show that our proposed triplet loss function achieves the best performance. It achieves a relative improvement of 1.4% and 4% respectively over an E2E model without a cross-modal space and a relative improvement of 0.7% and 1% over a previously published CMLS model using $L_2$ loss. The gains are higher for a smaller, more complicated E2E dataset, demonstrating the efficacy of using an efficient cross-modal loss function, especially when there is limited E2E training data available.

Surabhi Punjabi, Harish Arsikere, Zeynab Raeesy et al.

Multilingual ASR technology simplifies model training and deployment, but its accuracy is known to depend on the availability of language information at runtime. Since language identity is seldom known beforehand in real-world scenarios, it must be inferred on-the-fly with minimum latency. Furthermore, in voice-activated smart assistant systems, language identity is also required for downstream processing of ASR output. In this paper, we introduce streaming, end-to-end, bilingual systems that perform both ASR and language identification (LID) using the recurrent neural network transducer (RNN-T) architecture. On the input side, embeddings from pretrained acoustic-only LID classifiers are used to guide RNN-T training and inference, while on the output side, language targets are jointly modeled with ASR targets. The proposed method is applied to two language pairs: English-Spanish as spoken in the United States, and English-Hindi as spoken in India. Experiments show that for English-Spanish, the bilingual joint ASR-LID architecture matches monolingual ASR and acoustic-only LID accuracies. For the more challenging (owing to within-utterance code switching) case of English-Hindi, English ASR and LID metrics show degradation. Overall, in scenarios where users switch dynamically between languages, the proposed architecture offers a promising simplification over running multiple monolingual ASR models and an LID classifier in parallel.