Related papers: Pushing the Limits of Beam Search Decoding for Tra…

Sparse attention mechanisms promise to break the quadratic bottleneck of long-context transformers, yet production adoption remains limited by a critical usability gap: optimal hyperparameters vary substantially across layers and models,…

Neural architecture search (NAS) aims to produce the optimal sparse solution from a high-dimensional space spanned by all candidate connections. Current gradient-based NAS methods commonly ignore the constraint of sparsity in the search…

Recently, several studies have explored the use of neural network to solve different routing problems, which is an auspicious direction. These studies usually design an encoder-decoder based framework that uses encoder embeddings of nodes…

Massive MIMO systems are seen by many researchers as a paramount technology toward next generation networks. This technology consists of hundreds of antennas that are capable of sending and receiving simultaneously a huge amount of data.…

The increasing scale and complexity of large language models (LLMs) pose significant inference latency challenges, primarily due to their autoregressive decoding paradigm characterized by the sequential nature of next-token prediction. By…

The increase in the dimensionality of neural embedding models has enhanced the accuracy of semantic search capabilities but also amplified the computational demands for Approximate Nearest Neighbor Searches (ANNS). This complexity poses…

Designing an efficient keyword spotting (KWS) system that delivers exceptional performance on resource-constrained edge devices has long been a subject of significant attention. Existing KWS search algorithms typically follow a…

Combination approaches for speech recognition (ASR) systems cover structured sentence-level or word-based merging techniques as well as combination of model scores during beam search. In this work, we compare model combination across…

There has been a rise in the popularity of algebraic methods for graph algorithms given the development of the GraphBLAS library and other sparse matrix methods. An exemplar for these approaches is Breadth-First Search (BFS). The algebraic…

Decoder-only language models (LMs) have been successfully adopted for speech-processing tasks including automatic speech recognition (ASR). The LMs have ample expressiveness and perform efficiently. This efficiency is a suitable…

Breadth-first search (BFS) is a fundamental graph algorithm that presents significant challenges for parallel implementation due to irregular memory access patterns, load imbalance and synchronization overhead. In this paper, we introduce a…

Recent works have shown that line search methods greatly increase performance of traditional stochastic gradient descent methods on a variety of datasets and architectures [1], [2]. In this work we succeed in extending line search methods…

We propose a one-step constrained (OSC) beam search to accelerate recurrent neural network (RNN) transducer (RNN-T) inference. The original RNN-T beam search has a while-loop leading to speed down of the decoding process. The OSC beam…

This paper presents an efficient decoding approach for end-to-end automatic speech recognition (E2E-ASR) with large language models (LLMs). Although shallow fusion is the most common approach to incorporate language models into E2E-ASR…

ASR Error Detection (AED) models aim to post-process the output of Automatic Speech Recognition (ASR) systems, in order to detect transcription errors. Modern approaches usually use text-based input, comprised solely of the ASR…

In this paper we develop two new Tensor Alternating Steepest Descent algorithms for tensor completion in the low-rank $\star_{M}$-product format, whereby we aim to reconstruct an entire low-rank tensor from a small number of measurements…

Edge detection is a fundamental image analysis task that underpins numerous high-level vision applications. Recent advances in Transformer architectures have significantly improved edge quality by capturing long-range dependencies, but this…

Neural architecture search (NAS) has recently been addressed from various directions, including discrete, sampling-based methods and efficient differentiable approaches. While the former are notoriously expensive, the latter suffer from…

Beam search and exhaustive search are two extreme ends of text decoding algorithms with respect to the search depth. Beam search is limited in both search width and depth, whereas exhaustive search is a global search that has no such…

Stream fusion, also known as system combination, is a common technique in automatic speech recognition for traditional hybrid hidden Markov model approaches, yet mostly unexplored for modern deep neural network end-to-end model…