Related papers: Phonetic accommodation and inhibition in a dynamic…
We present a speaker-aware approach for simulating multi-speaker conversations that captures temporal consistency and realistic turn-taking dynamics. Prior work typically models aggregate conversational statistics under an independence…
In this paper, we propose a deep convolutional neural network-based acoustic word embedding system on code-switching query by example spoken term detection. Different from previous configurations, we combine audio data in two languages for…
Disentangling speaker and content attributes of a speech signal into separate latent representations followed by decoding the content with an exchanged speaker representation is a popular approach for voice conversion, which can be trained…
This study investigates how learners organize perceptual space in early phonetic acquisition by advancing previous studies in two key aspects. Firstly, it examines the shape of the learned hidden representation as well as its ability to…
We study emergent communication in a multi-agent reinforcement learning setting, where the agents solve cooperative tasks and have access to a communication channel. The communication channel may consist of either discrete symbols or…
We explore which linguistic factors -- at the sentence and token level -- play an important role in influencing language model predictions, and investigate whether these are reflective of results found in humans and human corpora (Gries and…
The cognitive process of opinion formation is often characterized by stubbornness or resistance of agents to changes of opinion. To capture such a feature we introduce a constant latency time in the standard voter model of opinion dynamics:…
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…
Multi-agent models often describe populations segregated either in the physical space, i.e. subdivided in metapopulations, or in the ecology of opinions, i.e. partitioned in echo chambers. Here we show how the interplay between homophily…
Encouraged by the success of deep neural networks on a variety of visual tasks, much theoretical and experimental work has been aimed at understanding and interpreting how vision networks operate. Meanwhile, deep neural networks have also…
Phonetics is the scientific field concerned with the study of how speech is produced, heard and perceived. It abounds with data, such as acoustic speech recordings, neuroimaging data, or articulatory data. In this paper, we provide an…
The conversion from text to speech relies on the accurate mapping from linguistic to acoustic symbol sequences, for which current practice employs recurrent statistical models like recurrent neural networks. Despite the good performance of…
In this work, we use language modeling to investigate the factors that influence insertional code-switching. Code-switching occurs when a speaker alternates between one language variety (the primary language) and another (the secondary…
Is it possible to develop a `physics of language' which can explain the spatial, temporal and social patterns we see, and which can predict future change like we forecast the weather? Such a theory is likely to involve ideas from…
Estimation of a speaker's direction and head orientation with binaural recordings can be a critical piece of information in many real-world applications with emerging `earable' devices, including smart headphones and AR/VR headsets.…
The articulatory geometric configurations of the vocal tract and the acoustic properties of the resultant speech sound are considered to have a strong causal relationship. This paper aims at finding a joint latent representation between the…
Most people who have tried to learn a foreign language would have experienced difficulties understanding or speaking with a native speaker's accent. For native speakers, understanding or speaking a new accent is likewise a difficult task.…
Text does not fully specify the spoken form, so text-to-speech models must be able to learn from speech data that vary in ways not explained by the corresponding text. One way to reduce the amount of unexplained variation in training data…
We advance a novel explanation of similarity-based interference effects in subject-verb and reflexive pronoun agreement processing, grounded in surprisal values computed from a pretrained large-scale Transformer model, GPT-2. Specifically,…
Adversarial perturbations in speech pose a serious threat to automatic speech recognition (ASR) and speaker verification by introducing subtle waveform modifications that remain imperceptible to humans but can significantly alter system…