13 April 2015 in Promet - Traffic&Transportation
Understanding the nature of rail transit dwell time has potential benefits for both the users and the operators. Crowded passenger trains cause longer dwell times and may prevent some passengers from boarding the first available train that arrives. Actual dwell time and the process of passenger alighting and boarding are interdependent through the sequence of train stops and propagated delays. A comprehensive and feasible dwell time simulation model was developed and optimized to address the problems associated with scheduled timetables. The paper introduces the factors that affect dwell time in urban rail transit systems, including train headway, the process and number of passengers alighting and boarding the train, and the inability of train doors to properly close the first time because of overcrowded vehicles. Finally, based on a time-driven micro-simulation system, Shanghai rail transit Line 8 is used as an example to quantify the feasibility of scheduled dwell times for different stations, directions of travel and time periods, and a proposed dwell time during peak hours in several crowded stations is presented according to the simulation results.
20 September 2023 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
Voiceconversion (VC) refers to the transformation of the speaker identity of a speech to the target one without altering the linguistic content. As recent VC techniques have made significant progress, implementing them in real-world scenarios is also considered, where speech data have some inevitable interferences, the most common of which are background sounds. On the other hand, background sounds are informative and need to be retained in some applications, such as VC in movies/videos. To address these issues, we have proposed a noisy-to-noisy (N2N) VC framework that does not rely on clean VC data and models the noisy speech directly by using noise as conditions. Previous experimental results have proven its effectiveness. In this article, we further improve its performance by introducing the pre-trained noise-conditioned VC model. Moreover, to further explore the impacts of introducing noise conditions, the performance in more realistic situations is evaluated in which the training set possesses speaker-dependent noisy conditions. The experimental results demonstrate the effectiveness of the pre-training strategy and the degradation of its performance under strict noisy conditions. We then proposed a noise augmentation method to overcome the limitation. Further experiments showed the effectiveness of the augmentation method.
12 June 2025 in IEEE Transactions on Audio, Speech and Language Processing
Recent developments in voice conversion (VC) systems aim to improve speech quality and speaker similarity even under challenging background factors, such as noise or reverberation. Although these factors have traditionally been viewed as unwanted interference, they can also provide valuable information in certain applications like movie dubbing. In this paper, we present a new approach to VC that allows for better control over background factors like noise and reverberation. Our method is capable of generating both clean and noisy-reverberant converted speech. During inference, we first enhance interfered input speech data using speech enhancement models to reduce noise and reverberation. We also use a denoising model and a reverberation time (T60) estimator to extract important background information from the interfered speech data, which is then used alongside a target speaker's code to generate converted speech with the background factors. Our experiments show that the use of speech data with various acoustic conditions during training leads to improved speech quality and speaker similarity, even when clean data are not available. Moreover, optimizing the model with clean and pseudo-clean data further enhances the results.