Related papers: Time-Masked Transformers with Lightweight Test-Tim…
Learning intents and slot labels from user utterances is a fundamental step in all spoken language understanding (SLU) and dialog systems. State-of-the-art neural network based methods, after deployment, often suffer from performance…
Error correction code is a major part of the communication physical layer, ensuring the reliable transfer of data over noisy channels. Recently, neural decoders were shown to outperform classical decoding techniques. However, the existing…
With recent research advancements, deep learning models are becoming attractive and powerful choices for speech enhancement in real-time applications. While state-of-the-art models can achieve outstanding results in terms of speech quality…
We propose an algorithm to denoise speakers from a single microphone in the presence of non-stationary and dynamic noise. Our approach is inspired by the recent success of neural network models separating speakers from other speakers and…
The aim of the study is to investigate the complex mechanisms of speech perception and ultimately decode the electrical changes in the brain accruing while listening to speech. We attempt to decode heard speech from intracranial…
With the popularity of deep neural network, speech synthesis task has achieved significant improvements based on the end-to-end encoder-decoder framework in the recent days. More and more applications relying on speech synthesis technology…
Recently, Transformer-based encoder-decoder models have demonstrated strong performance in multilingual speech recognition. However, the decoder's autoregressive nature and large size introduce significant bottlenecks during inference.…
Intra-cortical brain-machine interfaces (iBMIs) present a promising solution to restoring and decoding brain activity lost due to injury. However, patients with such neuroprosthetics suffer from permanent skull openings resulting from the…
This work proposes the use of clean speech vocoder parameters as the target for a neural network performing speech enhancement. These parameters have been designed for text-to-speech synthesis so that they both produce high-quality…
We propose an approach for pre-training speech representations via a masked reconstruction loss. Our pre-trained encoder networks are bidirectional and can therefore be used directly in typical bidirectional speech recognition models. The…
We present a transformer-based speech-declipping model that effectively recovers clipped signals across a wide range of input signal-to-distortion ratios (SDRs). While recent time-domain deep neural network (DNN)-based declippers have…
Automatic recognition of disordered speech remains a highly challenging task to date. Sources of variability commonly found in normal speech including accent, age or gender, when further compounded with the underlying causes of speech…
Neural transducers have achieved human level performance on standard speech recognition benchmarks. However, their performance significantly degrades in the presence of cross-talk, especially when the primary speaker has a low…
We explore whether neural networks can decode brain activity into speech by mapping EEG recordings to audio representations. Using EEG data recorded as subjects listened to natural speech, we train a model with a contrastive CLIP loss to…
We present a methodology that explores how sentence structure is reflected in neural representations of machine translation systems. We demonstrate our model-agnostic approach with the Transformer English-German translation model. We…
High-resolution neural datasets enable foundation models for the next generation of brain-computer interfaces and neurological treatments. The community requires rigorous benchmarks to discriminate between competing modeling approaches, yet…
Decoding continuous language from brain activity is a formidable yet promising field of research. It is particularly significant for aiding people with speech disabilities to communicate through brain signals. This field addresses the…
Most text-to-speech (TTS) methods use high-quality speech corpora recorded in a well-designed environment, incurring a high cost for data collection. To solve this problem, existing noise-robust TTS methods are intended to use noisy speech…
State-of-the-art neural network language models (NNLMs) represented by long short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming highly complex. They are prone to overfitting and poor generalization when…
Transformer-based neural speech processing has achieved state-of-the-art performance. Since speech audio signals are known to be highly compressible, here we seek to accelerate neural speech transcription by time-domain signal…