Related papers: Emformer: Efficient Memory Transformer Based Acous…

In this paper we propose a robust loudspeaker beamforming algorithm which is used to enhance the performance of voice driven applications in scenarios where the loudspeakers introduce the majority of the noise, e.g. when music is playing…

In this work, we present Eformer - Edge enhancement based transformer, a novel architecture that builds an encoder-decoder network using transformer blocks for medical image denoising. Non-overlapping window-based self-attention is used in…

Automatic speech quality assessment is essential for audio researchers, developers, speech and language pathologists, and system quality engineers. The current state-of-the-art systems are based on framewise speech features (hand-engineered…

As Large Language Models (LLMs) are increasingly used for long-duration tasks, maintaining effective long-term memory has become a critical challenge. Current methods often face a trade-off between cost and accuracy. Simple storage methods…

Recent speaker verification (SV) systems have shown a trend toward adopting deeper speaker embedding extractors. Although deeper and larger neural networks can significantly improve performance, their substantial memory requirements hinder…

The advent of Transformer-based models has surpassed the barriers of text. When working with speech, we must face a problem: the sequence length of an audio input is not suitable for the Transformer. To bypass this problem, a usual approach…

Speech recognition on smart devices is challenging owing to the small memory footprint. Hence small size ASR models are desirable. With the use of popular transducer-based models, it has become possible to practically deploy streaming…

Transformers have shown dominant performance across a range of domains including language and vision. However, their computational cost grows quadratically with the sequence length, making their usage prohibitive for resource-constrained…

While large language models (LLMs) have been applied to automatic speech recognition (ASR), the task of making the model streamable remains a challenge. This paper proposes a novel model architecture, Transducer-Llama, that integrates LLMs…

Attention-based encoder-decoder architectures such as Listen, Attend, and Spell (LAS), subsume the acoustic, pronunciation and language model components of a traditional automatic speech recognition (ASR) system into a single neural…

Conformer, combining convolution and self-attention sequentially to capture both local and global information, has shown remarkable performance and is currently regarded as the state-of-the-art for automatic speech recognition (ASR).…

Transformer-based large language models (LLMs) exhibit impressive performance in generative tasks but also introduce significant challenges in real-world serving due to inefficient use of the expensive, computation-optimized accelerators.…

Long short-term memory (LSTM) based acoustic modeling methods have recently been shown to give state-of-the-art performance on some speech recognition tasks. To achieve a further performance improvement, in this research, deep extensions on…

While Transformers have revolutionized deep learning, their quadratic attention complexity hinders their ability to process infinitely long inputs. We propose Feedback Attention Memory (FAM), a novel Transformer architecture that leverages…

User studies have shown that reducing the latency of our simultaneous lecture translation system should be the most important goal. We therefore have worked on several techniques for reducing the latency for both components, the automatic…

Transformer-based architectures are the most used architectures in many deep learning fields like Natural Language Processing, Computer Vision or Speech processing. It may encourage the direct use of Transformers in the constrained tasks,…

In this paper, we propose an efficient and accurate streaming speech recognition model based on the FastConformer architecture. We adapted the FastConformer architecture for streaming applications through: (1) constraining both the…

Recent advancements in Large Language Models (LLMs) have yielded remarkable success across diverse fields. However, handling long contexts remains a significant challenge for LLMs due to the quadratic time and space complexity of attention…

End-to-end models are fast replacing the conventional hybrid models in automatic speech recognition. Transformer, a sequence-to-sequence model, based on self-attention popularly used in machine translation tasks, has given promising results…

Self-attention models have been successfully applied in end-to-end speech recognition systems, which greatly improve the performance of recognition accuracy. However, such attention-based models cannot be used in online speech recognition,…