Related papers: Bottleneck Transformer-Based Approach for Improved…
The calculation of most objective speech intelligibility assessment metrics requires clean speech as a reference. Such a requirement may limit the applicability of these metrics in real-world scenarios. To overcome this limitation, we…
Speech translation for subtitling (SubST) is the task of automatically translating speech data into well-formed subtitles by inserting subtitle breaks compliant to specific displaying guidelines. Similar to speech translation (ST), model…
The scale of transformer model pre-training is constrained by the increasing computation and communication cost. Low-rank bottleneck architectures offer a promising solution to significantly reduce the training time and memory footprint…
In this paper we proposed an end-to-end short utterances speech language identification(SLD) approach based on a Long Short Term Memory (LSTM) neural network which is special suitable for SLD application in intelligent vehicles. Features…
Speech enhancement model is used to map a noisy speech to a clean speech. In the training stage, an objective function is often adopted to optimize the model parameters. However, in most studies, there is an inconsistency between the model…
Self-attention mechanisms have enabled transformers to achieve superhuman-level performance on many speech-to-text (STT) tasks, yet the challenge of automatic prosodic segmentation has remained unsolved. In this paper we finetune Whisper, a…
In this paper we propose a Deep Neural Network (DNN) based Speech Enhancement (SE) system that is designed to maximize an approximation of the Short-Time Objective Intelligibility (STOI) measure. We formalize an approximate-STOI cost…
End-to-end spoken language understanding (SLU) systems benefit from pretraining on large corpora, followed by fine-tuning on application-specific data. The resulting models are too large for on-edge applications. For instance, BERT-based…
The estimation of speech intelligibility is still far from being a solved problem. Especially one aspect is problematic: most of the standard models require a clean reference signal in order to estimate intelligibility. This is an issue of…
Auto-regressive speech-text models pre-trained on interleaved text tokens and discretized speech tokens demonstrate strong speech understanding and generation, yet remain substantially less compute-efficient than text LLMs, partly due to…
Recent advances in sophisticated synthetic speech generated from text-to-speech (TTS) or voice conversion (VC) systems cause threats to the existing automatic speaker verification (ASV) systems. Since such synthetic speech is generated from…
Speech-to-text translation (ST), which translates source language speech into target language text, has attracted intensive attention in recent years. Compared to the traditional pipeline system, the end-to-end ST model has potential…
We present BoTNet, a conceptually simple yet powerful backbone architecture that incorporates self-attention for multiple computer vision tasks including image classification, object detection and instance segmentation. By just replacing…
The majority of deep neural network (DNN) based speech enhancement algorithms rely on the mean-square error (MSE) criterion of short-time spectral amplitudes (STSA), which has no apparent link to human perception, e.g. speech…
Our goal is to develop a principled and general algorithmic framework for task-driven estimation and control for robotic systems. State-of-the-art approaches for controlling robotic systems typically rely heavily on accurately estimating…
Thanks to the latest deep learning algorithms, silent speech interfaces (SSI) are now able to synthesize intelligible speech from articulatory movement data under certain conditions. However, the resulting models are rather…
Non-intrusive assessment of speech quality and intelligibility is essential when clean reference signals are unavailable. In this work, we propose a multimodal framework that integrates audio features and visual cues to predict PESQ and…
Controllable generation requires language models to realize output characteristics such as reading level, politeness, and toxicity. Existing steering methods are often indirect, require access to internal activations, or depend on auxiliary…
Deep reinforcement learning has recently shown many impressive successes. However, one major obstacle towards applying such methods to real-world problems is their lack of data-efficiency. To this end, we propose the Bottleneck Simulator: a…
Cross-speaker style transfer is crucial to the applications of multi-style and expressive speech synthesis at scale. It does not require the target speakers to be experts in expressing all styles and to collect corresponding recordings for…