Related papers: Controllable Time-Delay Transformer for Real-Time …

There has been a recent surge of interest in time series modeling using the Transformer architecture. However, forecasting multivariate time series with Transformer presents a unique challenge as it requires modeling both temporal…

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…

The Transformer is a highly successful deep learning model that has revolutionised the world of artificial neural networks, first in natural language processing and later in computer vision. This model is based on the attention mechanism…

This paper presents a novel algorithm for building an automatic speech recognition (ASR) model with imperfect training data. Imperfectly transcribed speech is a prevalent issue in human-annotated speech corpora, which degrades the…

Transient signals are often composed of a series of modes that have multivalued time-dependent instantaneous frequency (IF), which brings challenges to the development of signal processing technology. Fortunately, the group delay (GD) of…

We propose a CTC alignment-based single step non-autoregressive transformer (CASS-NAT) for speech recognition. Specifically, the CTC alignment contains the information of (a) the number of tokens for decoder input, and (b) the time span of…

We introduce dual-decoder Transformer, a new model architecture that jointly performs automatic speech recognition (ASR) and multilingual speech translation (ST). Our models are based on the original Transformer architecture (Vaswani et…

Detection Transformers (DETR) are increasingly adopted in autonomous vehicle (AV) perception systems due to their superior accuracy over convolutional networks. However, concurrently executing multiple DETR tasks presents significant…

We explore options to use Transformer networks in neural transducer for end-to-end speech recognition. Transformer networks use self-attention for sequence modeling and comes with advantages in parallel computation and capturing contexts.…

Existing approaches in disfluency detection focus on solving a token-level classification task for identifying and removing disfluencies in text. Moreover, most works focus on leveraging only contextual information captured by the linear…

Transformers have recently dominated the ASR field. Although able to yield good performance, they involve an autoregressive (AR) decoder to generate tokens one by one, which is computationally inefficient. To speed up inference,…

Time Delay Neural Networks (TDNNs) are widely used in both DNN-HMM based hybrid speech recognition systems and recent end-to-end systems. Nevertheless, the receptive fields of TDNNs are limited and fixed, which is not desirable for tasks…

Query spelling correction is an important function of modern search engines since it effectively helps users express their intentions clearly. With the growing popularity of speech search driven by Automated Speech Recognition (ASR)…

In this work, we introduce a multi-task transformer for speech deepfake detection, capable of predicting formant trajectories and voicing patterns over time, ultimately classifying speech as real or fake, and highlighting whether its…

Decision Transformer (DT) has emerged as a promising class of algorithms in offline reinforcement learning (RL) tasks, leveraging pre-collected datasets and Transformer's capability to model long sequences. Recent works have demonstrated…

Cascaded speech-to-speech translation systems often suffer from the error accumulation problem and high latency, which is a result of cascaded modules whose inference delays accumulate. In this paper, we propose a transducer-based speech…

This paper presents a method to accelerate the inference process of diffusion transformer (DiT)-based text-to-speech (TTS) models by applying a selective caching mechanism to transformer layers. Specifically, I integrate SmoothCache into…

Streaming recognition and segmentation of multi-party conversations with overlapping speech is crucial for the next generation of voice assistant applications. In this work we address its challenges discovered in the previous work on…

Transmission switching (TS) has gained significant attention recently. However, barriers still remain and must be overcome before the technology can be adopted by the industry. The state of the art challenges include AC feasibility and…

The Conformer model is an excellent architecture for speech recognition modeling that effectively utilizes the hybrid losses of connectionist temporal classification (CTC) and attention to train model parameters. To improve the decoding…