Related papers: Real-time and Continuous Turn-taking Prediction Us…
We present a system for concurrent activity recognition. To extract features associated with different activities, we propose a feature-to-activity attention that maps the extracted global features to sub-features associated with individual…
Autoregressive decoding in language models is inherently slow, generating only one token per forward pass. We propose Parallel Token Prediction (PTP), a general-purpose framework for predicting multiple tokens in a single model call. PTP…
While vision-language models have advanced significantly, their application in language-conditioned robotic manipulation is still underexplored, especially for contact-rich tasks that extend beyond visually dominant pick-and-place…
The conventional voter model is modified so that an agent's switching rate depends on the `age' of the agent, that is, the time since the agent last switched opinion. In contrast to previous work, age is continuous in the present model. We…
Recent works have validated the possibility of improving energy efficiency in radio access networks (RANs), achieved by dynamically turning on/off some base stations (BSs). In this paper, we extend the research over BS switching operations,…
The real-time prediction of business processes using historical event data is an important capability of modern business process monitoring systems. Existing process prediction methods are able to also exploit the data perspective of…
For speech interaction, voice activity detection (VAD) is often used as a front-end. However, traditional VAD algorithms usually need to wait for a continuous tail silence to reach a preset maximum duration before segmentation, resulting in…
Sharing autonomy between robots and human operators could facilitate data collection of robotic task demonstrations to continuously improve learned models. Yet, the means to communicate intent and reason about the future are disparate…
Speaker diarization for real-life scenarios is an extremely challenging problem. Widely used clustering-based diarization approaches perform rather poorly in such conditions, mainly due to the limited ability to handle overlapping speech.…
This paper introduces FastVC, an end-to-end model for fast Voice Conversion (VC). The proposed model can convert speech of arbitrary length from multiple source speakers to multiple target speakers. FastVC is based on a conditional…
The performance of an Acoustic Scene Classification (ASC) system is highly depending on the latent temporal dynamics of the audio signal. In this paper, we proposed a multiple layers temporal pooling method using CNN feature sequence as…
Voice activity detection (VAD) is an essential pre-processing step for tasks such as automatic speech recognition (ASR) and speaker recognition. A basic goal is to remove silent segments within an audio, while a more general VAD system…
This paper presents ALO-VC, a non-parallel low-latency one-shot phonetic posteriorgrams (PPGs) based voice conversion method. ALO-VC enables any-to-any voice conversion using only one utterance from the target speaker, with only 47.5 ms…
In this paper, we propose the use of self-supervised pretraining on a large unlabelled data set to improve the performance of a personalized voice activity detection (VAD) model in adverse conditions. We pretrain a long short-term memory…
Previous acoustic transfer methods rely on extensive precomputation and storage of data to enable real-time interaction and auditory feedback. However, these methods struggle with complex scenes, especially when dynamic changes in object…
The trajectory prediction is significant for the decision-making of autonomous driving vehicles. In this paper, we propose a model to predict the trajectories of target agents around an autonomous vehicle. The main idea of our method is…
Pretrained language models based on the transformer architecture have shown great success in NLP. Textual training data often comes from the web and is thus tagged with time-specific information, but most language models ignore this…
This study propose a fully automated system for speech correction and accent reduction. Consider the application scenario that a recorded speech audio contains certain errors, e.g., inappropriate words, mispronunciations, that need to be…
This paper proposes a novel memory-based online video representation that is efficient, accurate and predictive. This is in contrast to prior works that often rely on computationally heavy 3D convolutions, ignore actual motion when aligning…
We propose a Short-term Traffic flow Prediction (STP) framework so that transportation authorities take early actions to control flow and prevent congestion. We anticipate flow at future time frames on a target road segment based on…