Related papers: Decoupling entrainment from consistency using deep…

Speech signals encompass various information across multiple levels including content, speaker, and style. Disentanglement of these information, although challenging, is important for applications such as voice conversion. The contrastive…

Disfluency, though originating from human spoken utterances, is primarily studied as a uni-modal text-based Natural Language Processing (NLP) task. Based on early-fusion and self-attention-based multimodal interaction between text and…

Interspike intervals describe the output of neurons. Signal transmission in a neuronal network implies that the output of some neurons becomes the input of others. The output should reproduce the main features of the input to avoid a…

In recent years, convolutional neural networks (CNNs) took over the field of document analysis and they became the predominant model for word spotting. Especially attribute CNNs, which learn the mapping between a word image and an attribute…

This paper proposes a framework for modeling sound change that combines deep learning and iterative learning. Acquisition and transmission of speech is modeled by training generations of Generative Adversarial Networks (GANs) on unannotated…

We explore the task of improving persona consistency of dialogue agents. Recent models tackling consistency often train with additional Natural Language Inference (NLI) labels or attach trained extra modules to the generative agent for…

While both the data volume and heterogeneity of the digital music content is huge, it has become increasingly important and convenient to build a recommendation or search system to facilitate surfacing these content to the user or consumer…

Speech enhancement attenuates interfering sounds in speech signals but may introduce artifacts that perceivably deteriorate the output signal. We propose a method for controlling the trade-off between the attenuation of the interfering…

Sentence matching is widely used in various natural language tasks such as natural language inference, paraphrase identification, and question answering. For these tasks, understanding logical and semantic relationship between two sentences…

Decoding behavior, perception, or cognitive state directly from neural signals has applications in brain-computer interface research as well as implications for systems neuroscience. In the last decade, deep learning has become the…

Conversation is like an intricate partner dance and behavioral convergence, or the similarity in observable behaviors of partners over time, can lead to shared understanding, changed beliefs and increased rapport. This article describes a…

Text-to-speech models trained on large-scale datasets have demonstrated impressive in-context learning capabilities and naturalness. However, control of speaker identity and style in these models typically requires conditioning on reference…

This paper proposes a guided speaker embedding extraction system, which extracts speaker embeddings of the target speaker using speech activities of target and interference speakers as clues. Several methods for long-form overlapped…

We present a new approach for predictive modeling and its uncertainty quantification for mechanical systems, where coarse-grained models such as constitutive relations are derived directly from observation data. We explore the use of a…

In this paper the task of emotion recognition from speech is considered. Proposed approach uses deep recurrent neural network trained on a sequence of acoustic features calculated over small speech intervals. At the same time special…

Voice assistants overhear conversations and a consent management mechanism is required. Consent management can be implemented using speaker recognition. Users that do not give consent enrol their voice and all their further recordings are…

Despite the success of language models using neural networks, it remains unclear to what extent neural models have the generalization ability to perform inferences. In this paper, we introduce a method for evaluating whether neural models…

We introduce a method to disentangle controllable and uncontrollable factors of variation by interacting with the world. Disentanglement leads to good representations and is important when applying deep neural networks (DNNs) in fields…

Huge amounts of textual conversations occur online every day, where multiple conversations take place concurrently. Interleaved conversations lead to difficulties in not only following the ongoing discussions but also extracting relevant…

Speaker recognition systems based on deep speaker embeddings have achieved significant performance in controlled conditions according to the results obtained for early NIST SRE (Speaker Recognition Evaluation) datasets. From the practical…