Related papers: Semi-Autoregressive Streaming ASR With Label Conte…

Efficient machine translation models are commercially important as they can increase inference speeds, and reduce costs and carbon emissions. Recently, there has been much interest in non-autoregressive (NAR) models, which promise faster…

Automatic speech recognition (ASR) models rely on high-quality transcribed data for effective training. Generating pseudo-labels for large unlabeled audio datasets often relies on complex pipelines that combine multiple ASR outputs through…

Generative Retrieval introduces a new approach to Information Retrieval by reframing it as a constrained generation task, leveraging recent advancements in Autoregressive (AR) language models. However, AR-based Generative Retrieval methods…

There is a growing interest in the speech community in developing Recurrent Neural Network Transducer (RNN-T) models for automatic speech recognition (ASR) applications. RNN-T is trained with a loss function that does not enforce temporal…

Recent advances have demonstrated the potential of decoderonly large language models (LLMs) for automatic speech recognition (ASR). However, enabling streaming recognition within this framework remains a challenge. In this work, we propose…

Encoder-decoder based sequence-to-sequence models have demonstrated state-of-the-art results in end-to-end automatic speech recognition (ASR). Recently, the transformer architecture, which uses self-attention to model temporal context…

Streaming models are an essential component of real-time speech enhancement tools. The streaming regime constrains speech enhancement models to use only a tiny context of future information. As a result, the low-latency streaming setup is…

Large language model (LLM)-based automatic speech recognition (ASR) has recently attracted a lot of attention due to its high recognition accuracy and enhanced multi-dialect support. However, the high decoding latency of LLMs challenges the…

Deploying high-quality automatic speech recognition (ASR) on edge devices requires models that jointly optimize accuracy, latency, and memory footprint while operating entirely on CPU without GPU acceleration. We conduct a systematic…

Self-supervised pretrained models exhibit competitive performance in automatic speech recognition on finetuning, even with limited in-domain supervised data. However, popular pretrained models are not suitable for streaming ASR because they…

Transformer-based models have led to significant innovation in classical and practical subjects as varied as speech processing, natural language processing, and computer vision. On top of the Transformer, attention-based end-to-end…

Non-autoregressive (NAR) machine translation has recently achieved significant improvements, and now outperforms autoregressive (AR) models on some benchmarks, providing an efficient alternative to AR inference. However, while AR…

Automatic speech recognition (ASR) systems based on large language models (LLMs) achieve superior performance by leveraging pretrained LLMs as decoders, but their token-by-token generation mechanism leads to inference latency that grows…

Autoregressive (AR) models remain widely used in time series analysis due to their interpretability, but convencional parameter estimation methods can be computationally expensive and prone to convergence issues. This paper proposes a…

Unpaired text and audio injection have emerged as dominant methods for improving ASR performance in the absence of a large labeled corpus. However, little guidance exists on deploying these methods to improve production ASR systems that are…

Recently very deep transformers have outperformed conventional bi-directional long short-term memory networks by a large margin in speech recognition. However, to put it into production usage, inference computation cost is still a serious…

Having a sequence-to-sequence model which can operate in an online fashion is important for streaming applications such as Voice Search. Neural transducer is a streaming sequence-to-sequence model, but has shown a significant degradation in…

Recent research shows end-to-end ASR systems can recognize overlapped speech from multiple speakers. However, all published works have assumed no latency constraints during inference, which does not hold for most voice assistant…

The Listen, Attend and Spell (LAS) model and other attention-based automatic speech recognition (ASR) models have known limitations when operated in a fully online mode. In this paper, we analyze the online operation of LAS models to…

Recent research has shown that attention-based sequence-to-sequence models such as Listen, Attend, and Spell (LAS) yield comparable results to state-of-the-art ASR systems on various tasks. In this paper, we describe the development of such…