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

Current de-facto dysfluency modeling methods utilize template matching algorithms which are not generalizable to out-of-domain real-world dysfluencies across languages, and are not scalable with increasing amounts of training data. To…

Connectionist temporal classification (CTC) -based models are attractive because of their fast inference in automatic speech recognition (ASR). Language model (LM) integration approaches such as shallow fusion and rescoring can improve the…

The task-conditional model is a distinctive stream for efficient multi-task learning. Existing works encounter a critical limitation in learning task-agnostic and task-specific representations, primarily due to shortcomings in global…

Transformer-based language models have become the standard approach to solving natural language processing tasks. However, industry adoption usually requires the maximum throughput to comply with certain latency constraints that prevents…

When applying automated speech recognition (ASR) for Belgian Dutch (Van Dyck et al. 2021), the output consists of an unsegmented stream of words, without any punctuation. A next step is to perform segmentation and insert punctuation, making…

Transformer encoder-decoder models have achieved great performance in dialogue generation tasks, however, their inability to process long dialogue history often leads to truncation of the context To address this problem, we propose a novel…

Variable count is among the main scalability bottlenecks for transformer modeling in multivariate time series (MTS) data. On top of this, a growing consensus in the field points to indiscriminate inter-variable mixing as a potential source…

For real-world deployment of automatic speech recognition (ASR), the system is desired to be capable of fast inference while relieving the requirement of computational resources. The recently proposed end-to-end ASR system based on…

Non-autoregressive mechanisms can significantly decrease inference time for speech transformers, especially when the single step variant is applied. Previous work on CTC alignment-based single step non-autoregressive transformer (CASS-NAT)…

Pre-trained language models like BERT have proven to be highly performant. However, they are often computationally expensive in many practical scenarios, for such heavy models can hardly be readily implemented with limited resources. To…

Transformers have been the dominant architecture for Speech Translation in recent years, achieving significant improvements in translation quality. Since speech signals are longer than their textual counterparts, and due to the quadratic…

Streaming Machine Translation (MT) is the task of translating an unbounded input text stream in real-time. The traditional cascade approach, which combines an Automatic Speech Recognition (ASR) and an MT system, relies on an intermediate…

Non-autoregressive (NAR) transformer models have achieved significantly inference speedup but at the cost of inferior accuracy compared to autoregressive (AR) models in automatic speech recognition (ASR). Most of the NAR transformers take a…

Time series data is a key element of big data analytics, commonly found in domains such as finance, healthcare, climate forecasting, and transportation. In large scale real world settings, such data is often high dimensional and…

Recently, several types of end-to-end speech recognition methods named transformer-transducer were introduced. According to those kinds of methods, transcription networks are generally modeled by transformer-based neural networks, while…

Simultaneous translation is a task in which the translation begins before the end of an input speech segment. Its evaluation should be conducted based on latency in addition to quality, and for users, the smallest possible amount of latency…

Targeting at both high efficiency and performance, we propose AlignTTS to predict the mel-spectrum in parallel. AlignTTS is based on a Feed-Forward Transformer which generates mel-spectrum from a sequence of characters, and the duration of…

Modern systems for automatic speech recognition, including the RNN-Transducer and Attention-based Encoder-Decoder (AED), are designed so that the encoder is not required to alter the time-position of information from the audio sequence into…

Automatic detection of speech dysfluency aids speech-language pathologists in efficient transcription of disordered speech, enhancing diagnostics and treatment planning. Traditional methods, often limited to classification, provide…

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…